CN107992591A - People search method and device, electronic equipment and computer-readable recording medium - Google Patents

Abstract

The invention provides a person search method and device, electronic equipment and a computer-readable storage medium. The person search method includes: obtaining a picture of the target person; identifying the face features and clothing features of the target person in the picture of the target person; obtaining a first filter condition; feature, and the first filter condition is to obtain a first picture set from the picture data set; to obtain a second filter condition; to obtain a second picture set from the first picture set according to the second filter condition; to obtain a second picture set from the first picture set according to the second filter condition; The data of the pictures included in the picture collection determines the activity track of the target person. The present invention can quickly and accurately determine the activity track of the target person through multiple filtering conditions and in combination with the facial features and clothing features of the target person, so as to bring better user experience to the user.

Description

Person search method and device, electronic device, and computer-readable storage medium

technical field

The present invention relates to the technical field of intelligent search, in particular to a person search method and device, electronic equipment, and a computer-readable storage medium.

Background technique

Among the existing technical solutions, face recognition technology has been relatively mature, and is widely used in various person search scenarios.

However, in a specific search situation, when simply relying on face recognition technology to search for people, only face features are used as search conditions, and the search range is too large, which often cannot meet the needs of users. In addition, because the face recognition technology needs to recognize many details of the face, the recognition process is cumbersome, which not only increases the workload of the server, but also takes a long time. Therefore, simply relying on face recognition technology to search for people has been unable to meet the needs of users.

Contents of the invention

In view of the above, it is necessary to provide a person search method and device, electronic equipment and computer-readable storage medium, which can quickly and accurately determine the target person through multiple filtering conditions and in combination with the facial features and clothing features of the target person. Describe the activity trajectory of the target person to bring a better user experience to the user.

A person search method, the method comprising:

Obtain a picture of the target person;

Recognizing the facial features and clothing features of the target person in the picture of the target person;

Get the first filter condition;

Obtaining a first picture set from the picture data set according to the face features and clothing features of the target person, and the first filter condition;

Get the second filter condition;

Acquiring a second picture set from the first picture set according to the second filter condition;

The activity track of the target person is determined according to the data of the pictures included in the second picture set.

According to a preferred embodiment of the present invention, the identification of the wearing characteristics of the target person in the picture of the target person includes:

Determine the clothing area from the picture of the target person, and extract the features of the clothing in the clothing area. The features of the clothing include the style, color and color ratio of the clothing, and combine the extracted features with the pre-trained clothing feature model. Match the corresponding features of the target person to determine the wearing features of the target person including the style, color and color ratio information.

According to a preferred embodiment of the present invention, the acquisition of the first picture set from the picture data set according to the facial features and clothing features of the target person and the first filtering condition includes one or more combinations of the following:

According to the first designated time period contained in the first filter condition, search in the picture data set and determine a first candidate picture set, the pictures in the first candidate picture set have the information of the first designated time period ; According to the facial features of the target person, determine the first picture set from the first candidate picture set, and each face in the first picture set has the facial features; and/or

According to the wearing characteristics of the target person and the first designated clothing color included in the first filter condition, search in the picture data set, and determine a first candidate picture set, the pictures in the first candidate picture set have The first designated clothing color information; according to the facial features of the target person, determine the first picture set from the first candidate picture set, each face in the first picture set has the facial features; and/or

According to the wearing characteristics of the target person and the first designated clothing color ratio contained in the first filter condition, search in the picture data set, and determine the first candidate picture set, the pictures in the first candidate picture set Having the first specified clothing color ratio information; according to the facial features of the target person, determining the first picture set from the first candidate picture set, each face in the first picture set has the facial features; and/or

According to the wearing characteristics of the target person and the first designated clothing style contained in the first filter condition, search in the picture data set, and determine a first candidate picture set, the pictures in the first candidate picture set have The first designated clothing style information; according to the face features of the target person, determine the first picture set from the first candidate picture set, each face in the first picture set has the facial features; and/or

According to the first designated area contained in the first filter condition, search in the picture data set, and determine a first candidate picture set, the pictures in the first candidate picture set have the information of the first designated area; according to For the facial features of the target person, the first picture set is determined from the first candidate picture set, and each face in the first picture set has the human face feature.

According to a preferred embodiment of the present invention, the acquiring the second picture set from the first picture set according to the second filter condition includes one or more combinations of the following:

Determining the pictures in the first picture set that meet the second filter condition within a second specified time period as the second picture set, and the pictures in the second picture set have information about the second specified time period, said first specified time period includes said second specified time period; and/or

Determining the pictures in the first picture set that meet the second filter condition in the second specified area as the second picture set, the pictures in the second picture set have the information of the second specified area, the The first specified area includes the second specified area.

According to a preferred embodiment of the present invention, the determining the activity track of the target person according to the data of the pictures contained in the second picture set includes:

Obtain the shooting time and shooting location corresponding to each picture in the second picture set;

sorting the pictures in the second picture set based on the shooting time corresponding to each picture, and determining the activity track of the target person; or

Classify the pictures in the second picture set based on the shooting location corresponding to each picture, and determine the activity track of the target person.

According to a preferred embodiment of the present invention, the method further includes:

Obtain the last location where the target person appears;

determining a direction of movement of the target person at the final location;

According to the movement direction of the target person, the activity area of the target person is predicted.

According to a preferred embodiment of the present invention, the method further includes:

Real-time acquisition of pictures captured by the camera device in the predicted activity area;

identifying the target person from the captured picture, and tracking the target person;

When the target person is a dangerous person, sending the activity track of the target person and the predicted activity area corresponding to the target person to at least one user equipment.

A person search device, said device comprising:

an acquisition unit, configured to acquire a picture of a target person;

An identification unit, configured to identify the facial features and clothing features of the target person in the picture of the target person;

The acquiring unit is further configured to acquire a first filter condition;

The acquiring unit is further configured to acquire a first picture set from the picture data set according to the facial features and clothing features of the target person, and the first filter condition;

The obtaining unit is also used to obtain a second filter condition;

The acquisition unit is further configured to acquire a second picture set from the first picture set according to the second filter condition;

A determining unit, configured to determine the activity track of the target person according to the data of the pictures included in the second picture set.

According to a preferred embodiment of the present invention, the identifying unit identifying the wearing characteristics of the target person in the picture of the target person includes:

Determine the clothing area from the picture of the target person, and extract the features of the clothing in the clothing area. The features of the clothing include the style, color and color ratio of the clothing, and combine the extracted features with the pre-trained clothing feature model. Match the corresponding features of the target person to determine the wearing features of the target person including the style, color and color ratio information.

According to a preferred embodiment of the present invention, the acquisition unit acquires the first picture set from the picture data set according to the facial features and clothing features of the target person and the first filter condition, including one or more of the following combinations:

According to the first designated time period contained in the first filter condition, search in the picture data set and determine a first candidate picture set, the pictures in the first candidate picture set have the information of the first designated time period ; According to the facial features of the target person, determine the first picture set from the first candidate picture set, and each face in the first picture set has the facial features; and/or

According to the wearing characteristics of the target person and the first designated clothing color included in the first filter condition, search in the picture data set, and determine a first candidate picture set, the pictures in the first candidate picture set have The first designated clothing color information; according to the facial features of the target person, determine the first picture set from the first candidate picture set, each face in the first picture set has the facial features; and/or

According to the wearing characteristics of the target person and the first designated clothing color ratio contained in the first filter condition, search in the picture data set, and determine the first candidate picture set, the pictures in the first candidate picture set Having the first specified clothing color ratio information; according to the facial features of the target person, determining the first picture set from the first candidate picture set, each face in the first picture set has the facial features; and/or

According to the wearing characteristics of the target person and the first designated clothing style contained in the first filter condition, search in the picture data set, and determine a first candidate picture set, the pictures in the first candidate picture set have The first designated clothing style information; according to the face features of the target person, determine the first picture set from the first candidate picture set, each face in the first picture set has the facial features; and/or

According to the first designated area contained in the first filter condition, search in the picture data set, and determine a first candidate picture set, the pictures in the first candidate picture set have the information of the first designated area; according to For the facial features of the target person, the first picture set is determined from the first candidate picture set, and each face in the first picture set has the human face feature.

According to a preferred embodiment of the present invention, the acquiring unit acquiring the second picture set from the first picture set according to the second filter condition includes one or more of the following combinations:

Determining the pictures in the first picture set that meet the second filter condition within a second specified time period as the second picture set, and the pictures in the second picture set have information about the second specified time period, said first specified time period includes said second specified time period; and/or

Determining the pictures in the first picture set that meet the second filter condition in the second specified area as the second picture set, the pictures in the second picture set have the information of the second specified area, the The first specified area includes the second specified area.

According to a preferred embodiment of the present invention, the determining unit is specifically configured to:

Obtain the shooting time and shooting location corresponding to each picture in the second picture set;

sorting the pictures in the second picture set based on the shooting time corresponding to each picture, and determining the activity track of the target person; or

Classify the pictures in the second picture set based on the shooting location corresponding to each picture, and determine the activity track of the target person.

According to a preferred embodiment of the present invention, the acquiring unit is further configured to acquire the last location where the target person appears;

The determining unit is further configured to determine the movement direction of the target person at the final position;

The device also includes:

The prediction unit is configured to predict the activity area of the target person according to the movement direction of the target person.

According to a preferred embodiment of the present invention, the acquiring unit is further configured to acquire in real time the pictures captured by the camera device in the predicted activity area;

The device also includes:

a tracking unit, configured to identify the target person from the snapped pictures, and track the target person;

A sending unit, configured to send the target person's activity trajectory and the predicted activity area corresponding to the target person to at least one user equipment when the target person is a dangerous person.

An electronic device comprising:

a memory storing at least one instruction; and

A processor, executing instructions stored in the memory to implement the person searching method.

A computer-readable storage medium, at least one instruction is stored in the computer-readable storage medium, and the at least one instruction is executed by a processor in an electronic device to implement the person searching method.

As can be seen from the above technical solutions, the present invention obtains the picture of the target person; recognizes the facial features and clothing features of the target person in the picture of the target person; obtains the first filter condition; Features and wearing features, and the first filter condition is to obtain the first picture set from the picture data set; to obtain the second filter condition; to obtain the second picture set from the first picture set according to the second filter condition; to obtain the second picture set according to the said second filter condition The data of the pictures contained in the second picture set is used to determine the activity track of the target person. The present invention can quickly and accurately determine the activity track of the target person through multiple filtering conditions and in combination with the facial features and clothing features of the target person, thereby bringing better user experience to users.

Description of drawings

Fig. 1 is a schematic diagram of an application environment of a preferred embodiment of the person search method of the present invention.

Fig. 2 is a flowchart of a preferred embodiment of the person search method of the present invention.

Fig. 3 is a functional block diagram of a preferred embodiment of the person search device of the present invention.

Fig. 4 is a schematic structural diagram of an electronic device implementing a preferred embodiment of a person search method according to the present invention.

Detailed ways

In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

As shown in FIG. 1 , it is a schematic diagram of an application environment of a preferred embodiment of the person search method of the present invention. The electronic device 1 communicates with the imaging device 2 . The camera 2 is used for taking video images.

As shown in FIG. 2 , it is a flow chart of a preferred embodiment of the person search method of the present invention. According to different requirements, the order of the steps in the flowchart can be changed, and some steps can be omitted.

The person search method is applied to one or more electronic devices 1, and the electronic device 1 is a device capable of automatically performing numerical calculation and/or information processing according to preset or stored instructions, and its hardware includes but It is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

The electronic device 1 can be any electronic product capable of man-machine interaction with the user, for example, a personal computer, a tablet computer, a smart phone, a personal digital assistant (Personal Digital Assistant, PDA), a game console, an interactive Internet TV (Internet Protocol Television, IPTV), smart wearable devices, etc.

The electronic device 1 may also include network equipment and/or user equipment. Wherein, the network device includes, but is not limited to, a single network server, a server group composed of multiple network servers, or a cloud composed of a large number of hosts or network servers based on cloud computing (Cloud Computing).

The network where the electronic device 1 is located includes but is not limited to the Internet, a wide area network, a metropolitan area network, a local area network, a virtual private network (Virtual Private Network, VPN) and the like.

S10, the electronic device 1 acquires a picture of a target person.

In at least one embodiment of the present invention, said electronic device 1 acquires a picture of a target person including, but not limited to, one or more of the following combinations:

(1) The electronic device 1 receives the uploaded picture, and uses the uploaded picture as the picture of the target person.

In at least one embodiment of the present invention, the electronic device 1 may receive a picture uploaded by a user, and use the uploaded picture as the picture of the target person.

In this way, the electronic device 1 can search for the target person according to the requirements provided by the user, making the search more targeted, and usually, in the pictures provided by the user, the characteristics of the target person The display will be clearer, so that when the electronic device 1 uses the picture provided by the user to identify the facial features and clothing features of the person, the identification result will be more accurate and reliable.

(2) The electronic device 1 receives a picture selected from the picture data set, and uses the selected picture as the picture of the target person.

In at least one embodiment of the present invention, when the user cannot provide a picture of the target person, the user can select a picture from the picture data set, the electronic device 1 receives the selected picture, and The selected picture is determined as the picture of the target person.

In this way, even when the user cannot provide a picture of the target person as the basis for identification, the electronic device 1 can also perform facial features and recognition of the target person according to the received picture selected from the picture data set. The recognition of the wearing characteristics, so that the search work of the target person can be carried out smoothly, and also makes the search work of the target person more flexible.

In at least one embodiment of the present invention, the picture data set may be a pre-stored picture data set, or a picture data set captured in real time by the camera 2 communicating with the electronic device 1, The invention is not limited here.

In at least one embodiment of the present invention, in order to enrich data and facilitate more accurate searches, the picture data set may store pictures of people, animals, scenery, etc., which is not limited in the present invention.

S11, the electronic device 1 recognizes the facial features and clothing features of the target person in the picture of the target person.

In at least one embodiment of the present invention, there may be many methods for the electronic device 1 to recognize the facial features of the target person, which are not limited in the present invention. Since the face recognition technology is relatively mature and belongs to the prior art, the present invention will not repeat it here.

In at least one embodiment of the present invention, the electronic device 1 identifying the wearing characteristics of the target person in the picture of the target person includes:

The electronic device 1 determines the clothing area from the picture of the target person, and extracts the features of the clothing in the clothing area. The clothing features include the style, color and color ratio of the clothing. The electronic device 1 will The extracted features are matched with the corresponding features in the pre-trained clothing feature model to determine the wearing features of the target person including the style, color and color ratio information.

In at least one embodiment of the present invention, the pre-trained clothing feature model can have many categories, specifically, the categories of the pre-trained clothing feature model can include, but not limited to: Korean, Japanese, European style, ethnic style, Mori girl series, small fresh series and so on. It should be noted that the clothing feature model of each category includes feature data of all wearing features such as the style, color, and color ratio of the character.

In this way, the electronic device 1 can first determine the category of the pre-trained clothing feature model to which the picture of the target person belongs, and then match the extracted features with the features in the corresponding category of clothing feature model to obtain the matched features. Since the search scope is narrowed, the process of identifying the wearing features of the target person in the picture of the target person is more efficient.

S12. The electronic device 1 acquires a first filter condition.

In at least one embodiment of the present invention, the scope of the first filtering condition may include, but not limited to: time, location, clothing style, clothing color and clothing color ratio, and the like.

It should be noted that the first filter condition is a filter condition with a relatively large search range, and search results with a wider coverage can be obtained through the first filter condition, so as to avoid search restrictions caused by narrow filter conditions and make the search results Not comprehensive enough.

S13, the electronic device 1 acquires a first picture set from the picture data set according to the facial features and clothing features of the target person and the first filter condition.

In at least one embodiment of the present invention, the electronic device 1 obtains the first picture set from the picture data set according to the facial features and clothing features of the target person and the first filter condition, including, but not limited to the following One or more combinations:

(1) The electronic device 1 searches in the picture data set according to the first specified time period contained in the first filter condition, and determines a first candidate picture set, and the pictures in the first candidate picture set have The first designated time period information; the electronic device 1 determines the first picture set from the first candidate picture set according to the facial features of the target person, and each person in the first picture set The faces all have the described facial features.

In at least one embodiment of the present invention, the first specified time period can be set by the user, specifically, the user can set it according to the actual search needs, or according to the known living habits of the target person Set, or set according to the known search time experience value in the search field, the present invention is not limited.

For example: when the user wants to know the activity trajectory of the target person in the morning, the user can set the first designated time period from 8:00 am to 12:00 am, so that the electronic device 1 first combines the From 8:00 a.m. to 12:00 a.m. for the first designated time period, search in the picture data set and determine the first candidate picture set; The picture set determines the first picture set.

(2) The electronic device 1 searches in the picture data set according to the wearing characteristics of the target person and the first specified clothing color contained in the first filter condition, and determines a first set of candidate pictures, the The pictures in the first candidate picture set have the first designated clothing color information; according to the facial features of the target person, determine the first picture set from the first candidate picture set, and the first picture set in the first picture set Each face has the facial features.

In at least one embodiment of the present invention, the first designated clothing color can be set by the user, or can be set by the electronic device 1 according to the recognized clothing color in the wearing characteristics of the target person. Inventions are not limited.

For example: when the clothing colors in the wearing characteristics of the target person recognized by the electronic device 1 are red and black, the electronic device 1 can set the first specified clothing color to be red and black, so that the The electronic device 1 first combines the wearing characteristics of the target person and the red and black colors of the first designated clothing, searches in the picture data set, and determines the first candidate picture set; The face feature of the target person is used to determine the first set of pictures from the first set of candidate pictures.

(3) The electronic device 1 searches in the picture data set according to the wearing characteristics of the target person and the first specified clothing color ratio included in the first filter condition, and determines a first set of candidate pictures, so The pictures in the first candidate picture set have the first designated clothing color ratio information; according to the facial features of the target person, the first picture set is determined from the first candidate picture set, and the first picture Each face in the set has the facial features.

In at least one embodiment of the present invention, the first designated clothing color ratio can be set by the user, or can be set by the electronic device 1 according to the clothing color ratio in the recognized wearing characteristics of the target person , the present invention is not limited.

For example: when the clothing color ratio in the wearing characteristics of the target person identified by the electronic device 1 is: red: black=1:1, the electronic device 1 can set the ratio of the first specified clothing color to : red: black = 1:1, so that the electronic device 1 first combines the wearing characteristics of the target person and the color ratio of the first specified clothing red: black = 1:1 to search in the image data set, And determine the first set of candidate pictures; the electronic device 1 then determines the first set of pictures from the first set of candidate pictures according to the facial features of the target person.

(4) The electronic device 1 searches in the picture data set according to the wearing characteristics of the target person and the first specified clothing style contained in the first filter condition, and determines a first candidate picture set, the The pictures in the first candidate picture set have the first designated clothing style information; according to the facial features of the target person, determine the first picture set from the first candidate picture set, and the first picture set in the first picture set Each face has the facial features.

In at least one embodiment of the present invention, the first specified clothing style can be set by the user, or can be set by the electronic device 1 according to the clothing style in the recognized wearing characteristics of the target person. Inventions are not limited.

For example: when the clothing style in the wearing characteristics of the target person identified by the electronic device 1 is Korean style, the electronic device 1 can set the first designated clothing style as Korean style, so that the electronic device 1 First, in combination with the wearing characteristics of the target person and the Korean style of the first specified clothing style, search in the picture data set, and determine the first candidate picture set; The feature is to determine the first set of pictures from the first set of candidate pictures.

(5) The electronic device 1 searches in the picture data set according to the first designated area contained in the first filter condition, and determines a first candidate picture set, and the pictures in the first candidate picture set have all The first designated area information; according to the facial features of the target person, determine the first picture set from the first candidate picture set, and each face in the first picture set has the human face feature.

In at least one embodiment of the present invention, the first designated area can be set by the user, specifically, the user can set it according to the actual search needs, or according to the known living habits of the target person , or set according to known experience in the search field, which is not limited in the present invention.

For example: when the electronic device 1 receives that the first designated area set by the user is Street A, the electronic device 1 first searches in the picture data set in combination with the first designated area A street, and determines A first set of candidate pictures: the electronic device 1 then determines the first set of pictures from the first set of candidate pictures according to the facial features of the target person.

In at least one embodiment of the present invention, because the face recognition technology is relatively fine and cumbersome, it takes a lot of time to operate, therefore, in this embodiment, the electronic device 1 first combines the target person's wearing feature and the first filter condition are searched in the picture data set, and after obtaining the first candidate picture set, combined with the facial features of the target person, the first candidate picture set is determined from the first candidate picture set. Photo album. This not only saves search time, but also can quickly search for the target person when the flow of people is large and the environment is complex, thereby improving search efficiency.

In at least one embodiment of the present invention, according to the search result, the first set of pictures may include one or more pictures, which is not limited in the present invention.

S14. The electronic device 1 acquires a second filter condition.

In at least one embodiment of the present invention, the second filter condition is a narrow filter condition, and the scope of the second filter condition may include, but not limited to: time, location and so on. Specifically, the second filter condition includes a second designated time period and a second designated area, the second designated time period is included in the first designated time period in the first filter condition, and the second designated time period The area is included in the first specified area in the first filter condition.

In this way, after the electronic device 1 has acquired the first picture collection, the electronic device 1 can further narrow down the search range according to the further limitation of the second filter condition, so as to obtain more accurate search results.

S15. The electronic device 1 acquires a second picture set from the first picture set according to the second filter condition.

In at least one embodiment of the present invention, the electronic device 1 acquires the second picture set from the first picture set according to the second filter condition, including, but not limited to, a combination of one or more of the following methods:

(1) The electronic device 1 determines the pictures in the first picture set that meet the second filter condition in the second specified time period as the second picture set, and the pictures in the second picture set have the The second specified time period information, the first specified time period includes the second specified time period.

For example: if the electronic device 1 narrows down the search range and sets the second designated time period from 10:00 am to 11:00 am, then the electronic device 1 sets the first picture set to match the second designated time period The pictures from 10 o'clock to 11 o'clock are determined as the second picture set.

(2) The electronic device 1 determines the pictures in the second specified area in the first picture set that meet the second filter condition as the second picture set, and the pictures in the second picture set have the For the second designated time period information, the first designated area includes the second designated area.

For example: if the electronic device 1 narrows down the search range and sets the second specified area to the number X to Y of street A, then the electronic device 1 will set the first picture set to meet the second specification The pictures from No. X to No. Y of the street in area A are determined as the second picture set.

In at least one embodiment of the present invention, the electronic device 1 can record the time when the camera 2 takes each picture, or when the camera 2 takes each picture, it displays the shooting time on For each picture, the electronic device 1 acquires the shooting time of each picture contained in the first picture set, and determines the pictures whose shooting time meets the second specified time period in the second filter condition as the taken pictures. Describe the second set of pictures.

Through the above implementation, when the user wants to further limit the filter conditions, the electronic device 1 can directly perform time, place, etc. The specific restrictions, not only saves the search time, but also makes the search more targeted, and more in line with the user's search needs.

Of course, in other embodiments, the second filter condition may also include restrictions on clothing color, etc., which is not limited in the present invention. For example: if the clothing color in the first filter condition is red and black, and the clothing color in the second filter condition is red, then the electronic device 1 can directly select the clothing color from the first picture collection The red pictures are added to the second picture set without re-searching from the picture data set, which not only reduces the workload, but also saves search time.

S16. The electronic device 1 determines the activity track of the target person according to the data of the pictures included in the second picture set.

In at least one embodiment of the present invention, the electronic device 1 determining the activity track of the target person according to the data of the pictures contained in the second picture collection includes:

The electronic device 1 acquires the shooting time and shooting location corresponding to each picture in the second picture set, and based on the shooting time corresponding to each picture, sorts the pictures in the second picture set to determine the target person activity track.

In at least one embodiment of the present invention, the electronic device 1 can sort the pictures in the second set of pictures according to the shooting time corresponding to each picture, so that the electronic device 1 can obtain the time order The activity track of the target person, so as to predict the place where the target person may appear in the next time according to the time sequence.

For example: the electronic device 1 can sort the pictures in the second picture collection according to the shooting order in the time period from 9:00 am to 11:00 am, so that the electronic device 1 can determine the target person in chronological order From 9:00 am to 11:00 am, the locations appear in sequence to determine the activity track of the target person.

Alternatively, the electronic device 1 acquires the shooting time and shooting location corresponding to each picture in the second picture set, and classifies the pictures in the second picture set based on the shooting location corresponding to each picture, and determines the Describe the trajectory of the target person's activities.

In at least one embodiment of the present invention, the electronic device 1 can classify the pictures in the second picture collection according to the shooting location corresponding to each picture, so that the electronic device 1 can obtain Based on the activity trajectory of the target person, the location where the target person may appear next is predicted according to the frequency of occurrence of the target person at each location.

For example: the electronic device 1 can divide each picture in the second picture set into A street X number, A street Y number, A street Z number, etc. according to the corresponding shooting location, so that the electronic device 1 can According to the connection lines of A Street No. X, A Street No. Y, A Street No. Z, etc., the activity track of the target person is determined.

Through the above method of determining the activity track of the target person by time or place, the search results can be clearly displayed to the user, which is easy to understand.

In at least one embodiment of the present invention, the electronic device 1 can obtain the shooting time and shooting location corresponding to each picture in the second picture set through the camera 2 communicating with the electronic device 1, understandably Yes, the time and place at which the target person appears can be determined through the shooting time and shooting location corresponding to each picture in the second picture set.

Specifically, the electronic device 1 may record the time when the camera 2 captures each picture in the second set of pictures, or when the camera 2 captures each picture in the second set of pictures , displaying the shooting time on each photo in the second picture set, and so on.

Specifically, the electronic device 1 may record the shooting location when the camera 2 shoots each picture in the second picture set, and determine the shooting location as the location where the target person appears.

In at least one embodiment of the present invention, the method also includes:

The electronic device 1 obtains the last position where the target person appears, determines the movement direction of the target person at the last position, and predicts the target person's movement direction according to the movement direction of the target person. active area.

Specifically, the electronic device 1 may determine the direction of movement of the target person according to the recognized body orientation, leg movement tendency, face orientation, etc. of the target person, or the target person's vehicle direction. The direction of the head of the vehicle determines the moving direction of the target person, which is not limited in the present invention.

For example: when the electronic device 1 acquires that the last location where the target person appears is street A street number X, if the electronic device 1 determines that the movement direction of the target person at street number A is toward street number Y , then the electronic device 1 can predict that the activity area of the target person will be from A Street X to A Street Y.

In this way, the electronic device 1 can accurately grasp the area where the target person may appear by predicting the activity area of the target person, and can make corresponding preparations in advance in the area where the target person may appear, so as to cooperate with the search for the target The person's search purpose. For example: when the target person's search purpose is to capture the target person, preparations for capturing the target person can be made in advance by predicting the activity area of the target person.

In other embodiments, the electronic device 1 may also determine the moving direction of the vehicle of the target person at the last position, and predict the moving direction of the vehicle of the target person according to the moving direction of the vehicle of the target person. Describe the activity area of the target person. For example: when the search purpose of the target person is to track the target person, the electronic device 1 can start the camera 2 in the predicted activity area of the target person, and make preparations for capturing in advance to achieve accurate tracking. Purpose.

In at least one embodiment of the present invention, the method also includes:

The electronic device 1 obtains in real time the picture captured by the camera device 2 in the predicted activity area, identifies the target person from the captured picture, and tracks the target person. When the target person is a dangerous person, Sending the activity track of the target person and the predicted activity area corresponding to the target person to at least one user equipment.

For example: when the target person is a thief, the electronic device 1 may send the thief's activity trajectory and the predicted activity area corresponding to the thief to the server of the police station and the thief on the terminal equipment of the community security personnel involved in the activity track, to remind the relevant personnel to take security precautions in time, and because of the tracking of the target person, it can also assist the relevant personnel to quickly arrest the thief .

In summary, the present invention can obtain a picture of a target person; identify the facial features and clothing features of the target person in the picture of the target person; obtain the first filter condition; Wearing characteristics, and the first filter condition is to obtain the first picture set from the picture data set; to obtain the second filter condition; to obtain the second picture set from the first picture set according to the second filter condition; to obtain the second picture set from the first picture set according to the second filter condition; The data of the pictures included in the second picture set determines the activity track of the target person. Therefore, the present invention can quickly and accurately determine the activity track of the target person through multiple filter conditions, combined with the facial features and clothing features of the target person, and bring better user experience to the user.

As shown in FIG. 3 , it is a functional block diagram of a preferred embodiment of the person search device of the present invention. The person search device 11 includes an acquisition unit 110 , an identification unit 111 , a determination unit 112 , a prediction unit 113 , a tracking unit 114 , and a sending unit 115 . The module/unit referred to in the present invention refers to a series of computer program segments that can be executed by the processor 13 and can complete fixed functions, and are stored in the memory 12 . In this embodiment, the functions of each module/unit will be described in detail in subsequent embodiments.

The acquisition unit 110 acquires a picture of the target person.

In at least one embodiment of the present invention, the acquiring unit 110 acquires the picture of the target person including, but not limited to, a combination of one or more of the following:

(1) The acquiring unit 110 receives the uploaded picture, and uses the uploaded picture as the picture of the target person.

In at least one embodiment of the present invention, the obtaining unit 110 may receive a picture uploaded by a user, and use the uploaded picture as the picture of the target person.

In this way, the electronic device 1 can search for the target person according to the requirements provided by the user, making the search more targeted, and usually, in the pictures provided by the user, the characteristics of the target person The display will be clearer, so that when the electronic device 1 uses the picture provided by the user to identify the facial features and clothing features of the person, the identification result will be more accurate and reliable.

(2) The acquiring unit 110 receives a picture selected from the picture data set, and uses the selected picture as the picture of the target person.

In at least one embodiment of the present invention, when the user cannot provide a picture of the target person, the user can select a picture from the picture data set, and the acquisition unit 110 receives the selected picture, and The selected picture is determined as the picture of the target person.

In this way, even when the user cannot provide a picture of the target person as the basis for identification, the electronic device 1 can also perform facial features and recognition of the target person according to the received picture selected from the picture data set. The recognition of the wearing characteristics, so that the search work of the target person can be carried out smoothly, and also makes the search work of the target person more flexible.

In at least one embodiment of the present invention, the picture data set may be a pre-stored picture data set, or a picture data set captured in real time by the camera 2 communicating with the electronic device 1, The invention is not limited here.

In at least one embodiment of the present invention, in order to enrich data and facilitate more accurate searches, the picture data set may store pictures of people, animals, scenery, etc., which is not limited in the present invention.

The recognition unit 111 recognizes facial features and clothing features of the target person in the picture of the target person.

In at least one embodiment of the present invention, the identification unit 111 may identify the facial features of the target person in many ways, which are not limited in the present invention. Since the face recognition technology is relatively mature and belongs to the prior art, the present invention will not repeat it here.

In at least one embodiment of the present invention, the identification unit 111 identifying the wearing characteristics of the target person in the picture of the target person includes:

The identification unit 111 determines the clothing area from the picture of the target person, and extracts the features of the clothing in the clothing area. The clothing features include the style, color and color ratio of the clothing. The identification unit 111 will The extracted features are matched with the corresponding features in the pre-trained clothing feature model to determine the wearing features of the target person including the style, color and color ratio information.

In at least one embodiment of the present invention, the pre-trained clothing feature model can have many categories, specifically, the categories of the pre-trained clothing feature model can include, but not limited to: Korean, Japanese, European style, ethnic style, Mori girl series, small fresh series and so on. It should be noted that the clothing feature model of each category includes feature data of all wearing features such as the style, color, and color ratio of the character.

In this way, the recognition unit 111 can first determine the category of the pre-trained clothing feature model to which the target person's picture belongs, and then match the extracted features with the features in the corresponding category of clothing feature model to obtain matched features. Since the search scope is narrowed, the process of identifying the wearing features of the target person in the picture of the target person is more efficient.

The acquisition unit 110 acquires the first filter condition.

In at least one embodiment of the present invention, the scope of the first filtering condition may include, but not limited to: time, location, clothing style, clothing color and clothing color ratio, and the like.

It should be noted that the first filter condition is a filter condition with a relatively large search range, and search results with a wider coverage can be obtained through the first filter condition, so as to avoid search restrictions caused by narrow filter conditions and make the search results Not comprehensive enough.

The acquiring unit 110 acquires a first picture set from the picture data set according to the facial features and clothing features of the target person and the first filter condition.

In at least one embodiment of the present invention, the acquisition unit 110 acquires the first picture set from the picture data set according to the facial features and clothing features of the target person and the first filter condition, including, but not limited to the following One or more combinations:

(1) The acquisition unit 110 searches in the picture data set according to the first specified time period included in the first filter condition, and determines a first candidate picture set, the pictures in the first candidate picture set have The first designated time period information; the acquisition unit 110 determines the first set of pictures from the first set of candidate pictures according to the facial features of the target person, and each person in the first set of pictures The faces all have the described facial features.

In at least one embodiment of the present invention, the first specified time period can be set by the user, specifically, the user can set it according to the actual search needs, or according to the known living habits of the target person Set, or set according to the known search time experience value in the search field, the present invention is not limited.

For example: when the user wants to know the activity trajectory of the target person in the morning, the user can set the first specified time period from 8:00 am to 12:00 am. In this way, the acquisition unit 110 first combines the From 8:00 am to 12:00 am in the first designated time period, search in the picture data set, and determine the first candidate picture set. Then, the acquisition unit 110 selects from the first The first picture set is determined from the candidate picture set.

(2) The acquisition unit 110 searches in the picture data set according to the wearing characteristics of the target person and the first specified clothing color contained in the first filter condition, and determines a first candidate picture set, the The pictures in the first candidate picture set have the first designated clothing color information; according to the facial features of the target person, determine the first picture set from the first candidate picture set, and the first picture set in the first picture set Each face has the facial features.

In at least one embodiment of the present invention, the first specified clothing color may be set by the user, or may be set by the acquisition unit 110 according to the clothing color in the recognized wearing characteristics of the target person. Inventions are not limited.

For example: when the clothing colors in the wearing characteristics of the target person recognized by the identification unit 111 are red and black, the acquisition unit 110 may set the first designated clothing colors to be red and black, so that the The acquisition unit 110 first combines the wearing characteristics of the target person and the red and black colors of the first designated clothing, searches in the picture data set, and determines the first candidate picture set; the acquisition unit 110 then according to the The face feature of the target person is used to determine the first set of pictures from the first set of candidate pictures.

(3) The acquisition unit 110 searches in the picture data set according to the wearing characteristics of the target person and the first specified clothing color ratio contained in the first filter condition, and determines the first candidate picture set, so The pictures in the first candidate picture set have the first designated clothing color ratio information; according to the facial features of the target person, the first picture set is determined from the first candidate picture set, and the first picture Each face in the set has the facial features.

In at least one embodiment of the present invention, the first designated clothing color ratio can be set by the user, or can be set by the acquisition unit 110 according to the clothing color ratio in the recognized wearing characteristics of the target person , the present invention is not limited.

For example: when the clothing color ratio in the wearing characteristics of the target person identified by the identification unit 111 is: red: black=1:1, the acquisition unit 110 can set the first specified clothing color ratio to : red: black=1:1, like this, the acquisition unit 110 first combines the wearing characteristics of the target person and the first specified clothing color ratio red: black=1:1 to search in the image data set, And determine a first set of candidate pictures; the acquisition unit 110 then determines the first set of pictures from the first set of candidate pictures according to the facial features of the target person.

(4) The acquisition unit 110 searches in the picture data set according to the wearing characteristics of the target person and the first specified clothing style contained in the first filter condition, and determines a first candidate picture set, the The pictures in the first candidate picture set have the first designated clothing style information; according to the facial features of the target person, determine the first picture set from the first candidate picture set, and the first picture set in the first picture set Each face has the facial features.

In at least one embodiment of the present invention, the first specified clothing style can be set by the user, or can be set by the acquisition unit 110 according to the clothing style in the recognized wearing characteristics of the target person. Inventions are not limited.

For example: when the clothing style in the wearing characteristics of the target person recognized by the identification unit 111 is Korean style, the acquisition unit 110 may set the first designated clothing style as Korean style, so that the acquisition unit 110 First, in combination with the wearing characteristics of the target person and the Korean style of the first specified clothing style, search in the picture data set, and determine the first candidate picture set; The feature is to determine the first set of pictures from the first set of candidate pictures.

(5) The acquiring unit 110 searches in the picture data set according to the first designated area contained in the first filtering condition, and determines a first candidate picture set, and the pictures in the first candidate picture set have all The first designated area information; according to the facial features of the target person, determine the first picture set from the first candidate picture set, and each face in the first picture set has the human face feature.

In at least one embodiment of the present invention, the first designated area can be set by the user, specifically, the user can set it according to the actual search needs, or according to the known living habits of the target person , or set according to known experience in the search field, which is not limited in the present invention.

For example: when the acquisition unit 110 receives that the first designated area set by the user is Street A, the acquisition unit 110 first combines the first designated area A street, searches in the picture data set, and determines A first set of candidate pictures: the acquisition unit 110 then determines the first set of pictures from the first set of candidate pictures according to the facial features of the target person.

In at least one embodiment of the present invention, because the face recognition technology is relatively fine and cumbersome, and it takes a lot of time to operate, therefore, in this embodiment, the acquisition unit 110 first combines the clothing of the target person feature and the first filtering condition are searched in the picture data set, and after obtaining the first candidate picture set, the acquisition unit 110 combines the facial features of the target person to obtain the first candidate picture set The first picture set is determined. This not only saves search time, but also can quickly search for the target person when the flow of people is large and the environment is complex, thereby improving search efficiency.

In at least one embodiment of the present invention, according to the search result, the first picture set may include one or more pictures, which is not limited in the present invention.

The obtaining unit 110 obtains the second filter condition.

In at least one embodiment of the present invention, the second filter condition is a narrow filter condition, and the scope of the second filter condition may include, but not limited to: time, location and so on. Specifically, the second filter condition includes a second designated time period and a second designated area, the second designated time period is included in the first designated time period in the first filter condition, and the second designated time period The area is included in the first specified area in the first filter condition.

In this way, after the acquisition unit 110 has acquired the first picture set, the acquisition unit 110 can further narrow down the search scope according to the further limitation of the second filter condition, so as to obtain more accurate search results.

The obtaining unit 110 obtains a second picture set from the first picture set according to the second filter condition.

In at least one embodiment of the present invention, the acquiring unit 110 acquiring the second picture set from the first picture set according to the second filter condition includes, but is not limited to, a combination of one or more of the following methods:

(1) The acquisition unit 110 determines the pictures in the first picture set that meet the second filter condition within the second specified time period as the second picture set, and the pictures in the second picture set have the The second specified time period information, the first specified time period includes the second specified time period.

For example: if the acquisition unit 110 narrows down the search range and sets the second specified time period as 10:00 am to 11:00 am, then the acquisition unit 110 will set the first picture set to match the second specified time period The pictures from 10 o'clock to 11 o'clock are determined as the second picture set.

(2) The acquisition unit 110 determines the pictures in the second specified area in the first picture set that meet the second filter condition as the second picture set, and the pictures in the second picture set have the For the second designated time period information, the first designated area includes the second designated area.

For example: if the acquisition unit 110 narrows down the search range and sets the second specified area as the number X to Y of street A, then the acquisition unit 110 will set the first picture set that meets the second specification The pictures from No. X to No. Y of the street in area A are determined as the second picture set.

In at least one embodiment of the present invention, the electronic device 1 can record the time when the camera 2 takes each picture, or when the camera 2 takes each picture, it displays the shooting time on For each picture, the electronic device 1 acquires the shooting time of each picture contained in the first picture set, and determines the pictures whose shooting time meets the second specified time period in the second filter condition as the taken pictures. Describe the second set of pictures.

Through the above implementation, when the user wants to further limit the filter conditions, the acquisition unit 110 can directly perform time, place, etc. The specific restrictions, not only saves the search time, but also makes the search more targeted, and more in line with the user's search needs.

Of course, in other embodiments, the second filter condition may also include restrictions on clothing color, etc., which is not limited in the present invention. For example: if the clothing colors in the first filter condition are red and black, and the clothing color in the second filter condition is red, then the acquisition unit 110 can directly select the clothing color from the first picture collection The red pictures are added to the second picture set without re-searching from the picture data set, which not only reduces the workload, but also saves search time.

The determining unit 112 determines the activity track of the target person according to the data of the pictures included in the second picture set.

In at least one embodiment of the present invention, the determining unit 112 determining the activity track of the target person according to the data of the pictures contained in the second picture set includes:

The determining unit 112 acquires the shooting time and shooting location corresponding to each picture in the second picture set, and based on the shooting time corresponding to each picture, sorts the pictures in the second picture set to determine the target person activity track.

In at least one embodiment of the present invention, the determining unit 112 can sort the pictures in the second picture set according to the shooting time corresponding to each picture, so that the determining unit 112 can obtain the time order The activity track of the target person, so as to predict the place where the target person may appear in the next time according to the time sequence.

For example: the determining unit 112 can sort the pictures in the second picture collection according to the shooting order in the time period from 9:00 am to 11:00 am, so that the determining unit 112 can determine the target person in chronological order From 9:00 am to 11:00 am, the locations appear in sequence to determine the activity track of the target person.

Alternatively, the determining unit 112 acquires the shooting time and shooting location corresponding to each picture in the second picture set, and classifies the pictures in the second picture set based on the shooting location corresponding to each picture, and determines the Describe the trajectory of the target person's activities.

In at least one embodiment of the present invention, the determining unit 112 can classify the pictures in the second picture set according to the shooting location corresponding to each picture, so that the determining unit 112 can obtain Based on the activity trajectory of the target person, the location where the target person may appear next is predicted according to the frequency of occurrence of the target person at each location.

For example: the determination unit 112 can divide each picture in the second picture collection into A street X number, A street Y number, A street Z number, etc. according to the corresponding shooting location, so that the determination unit 112 can According to the connection lines of A Street No. X, A Street No. Y, A Street No. Z, etc., the activity track of the target person is determined.

Through the above method of determining the activity track of the target person by time or place, the search results can be clearly displayed to the user, which is easy to understand.

In at least one embodiment of the present invention, the determining unit 112 may obtain the shooting time and shooting location corresponding to each picture in the second picture set through the camera 2 communicating with the electronic device 1, understandably Yes, the time and place at which the target person appears can be determined through the shooting time and shooting location corresponding to each picture in the second picture set.

Specifically, the determining unit 112 may record the time when the camera 2 captures each picture in the second set of pictures, or when the camera 2 captures each picture in the second set of pictures , displaying the shooting time on each photo in the second picture set, and so on.

Specifically, the determining unit 112 may record the shooting location when the camera 2 shoots each picture in the second picture set, and determine the shooting location as the location where the target person appears.

In at least one embodiment of the present invention, the method also includes:

The acquisition unit 110 acquires the last position where the target person appears, the determination unit 112 determines the movement direction of the target person at the last position, and the prediction unit 113 , to predict the activity area of the target person.

Specifically, the electronic device 1 may determine the direction of movement of the target person according to the recognized body orientation, leg movement tendency, face orientation, etc. of the target person, or the target person's vehicle direction. The direction of the head of the vehicle determines the moving direction of the target person, which is not limited in the present invention.

For example: when the acquiring unit 110 acquires that the last location where the target person appears is Street A No. X, if the determination unit 112 determines that the movement direction of the target person at Street A No. X is toward Street A No. Y , then the predicting unit 113 can predict that the activity area of the target person will be from A Street X to A Street Y.

In this way, the prediction unit 113 can accurately grasp the area where the target person may appear by predicting the activity area of the target person, and can make corresponding preparations in advance in the area where the target person may appear to cooperate with the search for the target The person's search purpose. For example: when the target person's search purpose is to capture the target person, preparations for capturing the target person can be made in advance by predicting the activity area of the target person.

In other embodiments, the predicting unit 113 may also determine the moving direction of the vehicle of the target person at the last position, and predict the moving direction of the vehicle of the target person according to the moving direction of the vehicle of the target person. Describe the activity area of the target person. For example: when the search purpose of the target person is to track the target person, the prediction unit 113 can start the camera 2 in the predicted activity area of the target person, and prepare for capturing in advance to achieve accurate tracking. Purpose.

In at least one embodiment of the present invention, the method also includes:

The acquisition unit 110 acquires in real time the pictures captured by the camera device 2 in the predicted activity area, the identification unit 111 identifies the target person from the captured pictures, and the tracking unit 114 tracks the target person, when the When the target person is a dangerous person, the sending unit 115 sends the activity track of the target person and the predicted activity area corresponding to the target person to at least one user equipment.

For example: when the target person is a thief, the sending unit 115 can send the thief's activity trajectory and the predicted activity area corresponding to the thief to the server of the police station and the thief. on the terminal equipment of the community security personnel involved in the activity track, to remind the relevant personnel to take security precautions in time, and because of the tracking of the target person, it can also assist the relevant personnel to quickly arrest the thief .

In summary, the present invention can obtain a picture of a target person; identify the facial features and clothing features of the target person in the picture of the target person; obtain the first filter condition; Wearing characteristics, and the first filter condition is to obtain the first picture set from the picture data set; to obtain the second filter condition; to obtain the second picture set from the first picture set according to the second filter condition; to obtain the second picture set from the first picture set according to the second filter condition; The data of the pictures included in the second picture set determines the activity track of the target person. Therefore, the present invention can quickly and accurately determine the activity track of the target person through multiple filter conditions, combined with the facial features and clothing features of the target person, and bring better user experience to the user.

As shown in FIG. 4 , it is a schematic structural diagram of an electronic device implementing a preferred embodiment of the person search method in the present invention.

The electronic device 1 is a device that can automatically perform numerical calculation and/or information processing according to preset or stored instructions, and its hardware includes but is not limited to a microprocessor, an application specific integrated circuit (Application Specific Integrated Circuit, ASIC) , Programmable gate array (Field-Programmable Gate Array, FPGA), digital processor (Digital Signal Processor, DSP), embedded devices, etc.

The electronic device 1 can also be, but not limited to, any electronic product that can interact with the user through a keyboard, mouse, remote control, touch pad or voice-activated device, such as a personal computer, a tablet computer, a smart phone, etc. , Personal Digital Assistant (PDA), game consoles, Internet Protocol Television (IPTV), smart wearable devices, etc.

The electronic device 1 can also be computing devices such as desktop computers, notebooks, palmtop computers, and cloud servers.

The network where the electronic device 1 is located includes but is not limited to the Internet, a wide area network, a metropolitan area network, a local area network, a virtual private network (Virtual Private Network, VPN) and the like.

In one embodiment of the present invention, the electronic device 1 includes, but is not limited to, a memory 12, a processor 13, and a computer program stored in the memory 12 and operable on the processor 13, such as People search program.

Those skilled in the art can understand that the schematic diagram is only an example of the electronic device 1, and does not constitute a limitation to the electronic device 1, and may include more or less components than those shown in the illustration, or combine certain components, or have different Components, for example, the electronic device 1 may also include input and output devices, network access devices, buses, and the like.

The so-called processor 13 can be a central processing unit (Central Processing Unit, CPU), and can also be other general-purpose processors, a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), Off-the-shelf programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc., the processor 13 is the computing core and control center of the electronic device 1, and uses various interfaces and lines to connect the entire electronic device 1, and execute the operating system of the electronic device 1 and various installed applications, program codes, etc.

The processor 13 executes the operating system of the electronic device 1 and various installed application programs. The processor 13 executes the application program to implement the steps in the embodiments of the person search method described above, such as steps S10 , S11 , S12 , S13 , S14 , S15 , and S16 shown in FIG. 1 .

Alternatively, when the processor 13 executes the computer program, it realizes the functions of each module/unit in the above-mentioned device embodiments, for example: acquiring a picture of the target person; identifying the face of the target person in the picture of the target person Features and wearing features; obtain the first filter condition; obtain the first picture set from the picture data set according to the facial features and wearing features of the target person and the first filter condition; obtain the second filter condition; according to the described The second filter condition is to obtain a second picture set from the first picture set; and determine the activity track of the target person according to the data of the pictures contained in the second picture set.

Exemplarily, the computer program can be divided into one or more modules/units, and the one or more modules/units are stored in the memory 12 and executed by the processor 13 to complete this invention. The one or more modules/units may be a series of computer program instruction segments capable of accomplishing specific functions, and the instruction segments are used to describe the execution process of the computer program in the electronic device 1 . For example, the computer program can be divided into an acquisition unit 110 , an identification unit 111 , a determination unit 112 , a prediction unit 113 , a tracking unit 114 , and a sending unit 115 .

The memory 12 can be used to store the computer programs and/or modules, and the processor 13 runs or executes the computer programs and/or modules stored in the memory 12, and calls the data stored in the memory 12, Various functions of the electronic device 1 are realized. Described memory 12 can mainly comprise storage program area and storage data area, wherein, storage program area can store operating system, the application program (such as sound playback function, image playback function etc.) required by at least one function etc.; Storage data area can be Store data (such as audio data, phone book, etc.) created according to the use of the mobile phone. In addition, the memory 12 can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, flash memory card (Flash Card), at least one magnetic disk storage device, flash memory device, or other volatile solid state storage devices.

The memory 12 may be an external memory and/or an internal memory of the electronic device 1 . Further, the memory 12 may be a circuit with a storage function that has no physical form in an integrated circuit, such as RAM (Random-Access Memory, random access memory), FIFO (First In First Out,) and the like. Alternatively, the storage 12 may also be a physical storage, such as a memory stick, a TF card (Trans-flash Card) and the like.

If the integrated modules/units of the electronic device 1 are realized in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the present invention realizes all or part of the processes in the methods of the above embodiments, and can also be completed by instructing related hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer When the program is executed by the processor, the steps in the above-mentioned various method embodiments can be realized.

Wherein, the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM, Read-Only Memory) , Random Access Memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, computer-readable media Excludes electrical carrier signals and telecommunication signals.

Referring to FIG. 2 , the memory 12 in the electronic device 1 stores a plurality of instructions to implement a person search method, and the processor 13 can execute the plurality of instructions to realize: acquiring a picture of a target person; The facial features and clothing features of the target person in the picture of the target person; obtain the first filter condition; obtain the first filter condition from the picture data set according to the facial features and clothing features of the target person and the first filter condition A set of pictures; acquiring a second filter condition; acquiring a second set of pictures from the first set of pictures according to the second filter condition; determining the activity trajectory of the target person according to the data of the pictures contained in the second set of pictures .

According to a preferred embodiment of the present invention, the processor 13 also executes a plurality of instructions including:

Determine the clothing area from the picture of the target person, and extract the features of the clothing in the clothing area. The features of the clothing include the style, color and color ratio of the clothing, and combine the extracted features with the pre-trained clothing feature model. Match the corresponding features of the target person to determine the wearing features of the target person including the style, color and color ratio information.

According to a preferred embodiment of the present invention, the processor 13 also executes a plurality of instructions including:

According to the first designated time period contained in the first filter condition, search in the picture data set and determine a first candidate picture set, the pictures in the first candidate picture set have the information of the first designated time period ; According to the facial features of the target person, determine the first picture set from the first candidate picture set, and each face in the first picture set has the facial features; and/or

According to the wearing characteristics of the target person and the first designated clothing color included in the first filter condition, search in the picture data set, and determine a first candidate picture set, the pictures in the first candidate picture set have The first designated clothing color information; according to the facial features of the target person, determine the first picture set from the first candidate picture set, each face in the first picture set has the facial features; and/or

According to the wearing characteristics of the target person and the first designated clothing color ratio contained in the first filter condition, search in the picture data set, and determine the first candidate picture set, the pictures in the first candidate picture set Having the first specified clothing color ratio information; according to the facial features of the target person, determining the first picture set from the first candidate picture set, each face in the first picture set has the facial features; and/or

According to the wearing characteristics of the target person and the first designated clothing style included in the first filter condition, search in the picture data set, and determine a first candidate picture set, the pictures in the first candidate picture set have The first designated clothing style information; according to the facial features of the target person, determine the first picture set from the first candidate picture set, each face in the first picture set has the facial features; and/or

According to the first designated area contained in the first filter condition, search in the picture data set, and determine a first candidate picture set, the pictures in the first candidate picture set have the information of the first designated area; according to For the facial features of the target person, the first picture set is determined from the first candidate picture set, and each face in the first picture set has the human face feature.

According to a preferred embodiment of the present invention, the processor 13 also executes a plurality of instructions including:

Determining the pictures in the first picture set that meet the second filter condition within a second specified time period as the second picture set, and the pictures in the second picture set have information about the second specified time period, said first specified time period includes said second specified time period; and/or

Determining the pictures in the first picture set that meet the second filter condition in the second specified area as the second picture set, the pictures in the second picture set have the information of the second specified area, the The first specified area includes the second specified area.

According to a preferred embodiment of the present invention, the processor 13 also executes a plurality of instructions including:

Obtain the shooting time and shooting location corresponding to each picture in the second picture set;

sorting the pictures in the second picture set based on the shooting time corresponding to each picture, and determining the activity track of the target person; or

Classify the pictures in the second picture set based on the shooting location corresponding to each picture, and determine the activity track of the target person.

According to a preferred embodiment of the present invention, the processor 13 also executes a plurality of instructions including:

Obtain the last location where the target person appears;

determining a direction of movement of the target person at the final location;

According to the movement direction of the target person, the activity area of the target person is predicted.

According to a preferred embodiment of the present invention, the processor 13 also executes a plurality of instructions including:

Real-time acquisition of pictures captured by the camera device in the predicted activity area;

identifying the target person from the captured picture, and tracking the target person;

When the target person is a dangerous person, sending the activity track of the target person and the predicted activity area corresponding to the target person to at least one user equipment.

Specifically, for the specific implementation method of the above instruction by the processor 13, reference may be made to the description of the relevant steps in the embodiment corresponding to FIG. 2 , which will not be repeated here.

In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, or each unit may physically exist separately, or two or more units may be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware, or in the form of hardware plus software function modules.

It will be apparent to those skilled in the art that the invention is not limited to the details of the above-described exemplary embodiments, but that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention.

Accordingly, the embodiments should be regarded in all points of view as exemplary and not restrictive, the scope of the invention being defined by the appended claims rather than the foregoing description, and it is therefore intended that the scope of the invention be defined by the appended claims rather than by the foregoing description. All changes within the meaning and range of equivalents of the elements are embraced in the present invention. Any reference sign in a claim should not be construed as limiting the claim concerned.

In addition, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or devices stated in the system claims may also be realized by one unit or device through software or hardware. Secondary terms are used to denote names without implying any particular order.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention without limitation. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be Modifications or equivalent replacements can be made without departing from the spirit and scope of the technical solutions of the present invention.

Claims (10)

1. A kind of 1. people search method, it is characterised in that the described method includes：

   Obtain the picture of target person；

   Identify the face characteristic of target person described in the picture of the target person and wear feature；

   Obtain the first filter condition；

   According to the face characteristic of the target person and feature is worn, and first filter condition is concentrated from image data and obtained First pictures；

   Obtain the second filter condition；

   Second picture collection is obtained from first pictures according to second filter condition；

   The data for including picture according to the second picture collection determine the event trace of the target person.
2. 2. people search method as claimed in claim 1, it is characterised in that institute in the picture of the identification target person Stating the feature of wearing of target person includes：

   Clothes region is determined from the picture of the target person, the feature of clothes in the clothes region is extracted, institute Stating the feature of clothes includes style, color and the color-ratio of clothes, by the feature of extraction and garment feature mould trained in advance Individual features in type are matched, and include the style, color and color-ratio information with determine the target person Wear feature.
3. 3. people search method as claimed in claim 1, it is characterised in that the face characteristic according to the target person And feature is worn, and first filter condition concentrates the first pictures of acquisition to include following one or more from image data Combination：

   According to the first specified time section included in first filter condition, concentrate and search in the image data, and determine First candidate's pictures, the picture in the first candidate pictures have the first specified time segment information；According to described The face characteristic of target person, determines first pictures, in first pictures from the first candidate pictures Every face be respectively provided with the face characteristic；And/or

   According to the target person wear included in feature and first filter condition first specify clothing color, in institute State image data and concentrate search, and determine first candidate's pictures, the picture in the first candidate pictures has described the One specifies clothing color information；According to the face characteristic of the target person, determined from the first candidate pictures described First pictures, every face in first pictures are respectively provided with the face characteristic；And/or

   According to the target person wear included in feature and first filter condition first specify clothing color ratio, Concentrate and search in the image data, and determine first candidate's pictures, the picture in the first candidate pictures has institute State first and specify clothing color percent information；According to the face characteristic of the target person, from the first candidate pictures Determine first pictures, every face in first pictures is respectively provided with the face characteristic；And/or

   According to the target person wear included in feature and first filter condition first specify clothes fashion, in institute State image data and concentrate search, and determine first candidate's pictures, the picture in the first candidate pictures has described the One specifies clothes fashion information；According to the face characteristic of the target person, determined from the first candidate pictures described First pictures, every face in first pictures are respectively provided with the face characteristic；And/or

   Region is specified according to first included in first filter condition, concentrates and searches in the image data, and determines the One candidate's pictures, the picture in the first candidate pictures have described first to specify area information；According to the target The face characteristic of personage, determines first pictures from the first candidate pictures, every in first pictures Open face and be respectively provided with the face characteristic.
4. 4. people search method as claimed in claim 1, it is characterised in that it is described according to second filter condition from described Second picture collection is obtained in first pictures includes following one or more kinds of combination：

   The picture met in first pictures in second filter condition in the second specified time section is determined as described Second picture collection, the picture that the second picture is concentrated have the second specified time segment information, first specified time Section includes second specified time section；And/or

   Second will be met in second filter condition in first pictures specifies the picture in region to be determined as described the Two pictures, the picture that the second picture is concentrated have described second to specify area information, and described first specifies region to include Described second specifies region.
5. 5. people search method as claimed in claim 1, it is characterised in that described that figure is included according to the second picture collection The data of piece determine that the event trace of the target person includes：

   The second picture is obtained to concentrate per the corresponding shooting time of pictures and spot for photography；

   Based on the corresponding shooting time of every pictures, the picture of the second picture collection is ranked up, determines the target person The event trace of thing；Or

   Based on the corresponding spot for photography of every pictures, classify to the picture of the second picture collection, determine the target person The event trace of thing.
6. 6. people search method as claimed in claim 5, it is characterised in that the method further includes：

   Obtain the rearmost position that the target person occurs；

   Determine the direction of motion of target person target person at the rearmost position；

   According to the direction of motion of the target person, the zone of action of the target person is predicted.
7. 7. people search method as claimed in claim 6, it is characterised in that the method further includes：

   The picture that the camera device in the zone of action of prediction is captured is obtained in real time；

   The target person is identified from the picture of the candid photograph, and tracks the target person；

   When the target person is dangerous person, by the event trace of the target person and the corresponding institute of the target person The zone of action for stating prediction is sent at least one user equipment.
8. 8. a kind of people search device, it is characterised in that described device includes：

   Acquiring unit, for obtaining the picture of target person；

   Recognition unit, for identifying the face characteristic of target person described in the picture of the target person and wearing feature；

   The acquiring unit, is additionally operable to obtain the first filter condition；

   The acquiring unit, is additionally operable to according to the face characteristic of the target person and wears feature, and first filtering rod Part is concentrated from image data and obtains the first pictures；

   The acquiring unit, is additionally operable to obtain the second filter condition；

   The acquiring unit, is additionally operable to obtain second picture collection from first pictures according to second filter condition；

   Determination unit, the data for including picture according to the second picture collection determine the active rail of the target person Mark.
9. 9. a kind of electronic equipment, it is characterised in that the electronic equipment includes：

   Memory, stores at least one instruction；And

   Processor, performs the instruction that is stored in the memory to realize personage as claimed in any of claims 1 to 7 in one of claims Searching method.
10. A kind of 10. computer-readable recording medium, it is characterised in that：At least one is stored with the computer-readable recording medium A instruction, at least one instruction are performed by the processor in electronic equipment to realize such as any one in claim 1 to 7 The people search method.