CN115410153A - Door opening and closing state judging method and device, electronic terminal and storage medium - Google Patents
Door opening and closing state judging method and device, electronic terminal and storage medium Download PDFInfo
- Publication number
- CN115410153A CN115410153A CN202211049208.3A CN202211049208A CN115410153A CN 115410153 A CN115410153 A CN 115410153A CN 202211049208 A CN202211049208 A CN 202211049208A CN 115410153 A CN115410153 A CN 115410153A
- Authority
- CN
- China
- Prior art keywords
- preset
- door
- image
- determining
- opening
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 80
- 230000002159 abnormal effect Effects 0.000 claims abstract description 35
- 238000004590 computer program Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 16
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 5
- 238000001514 detection method Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000004888 barrier function Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- E—FIXED CONSTRUCTIONS
- E05—LOCKS; KEYS; WINDOW OR DOOR FITTINGS; SAFES
- E05B—LOCKS; ACCESSORIES THEREFOR; HANDCUFFS
- E05B17/00—Accessories in connection with locks
-
- E—FIXED CONSTRUCTIONS
- E05—LOCKS; KEYS; WINDOW OR DOOR FITTINGS; SAFES
- E05B—LOCKS; ACCESSORIES THEREFOR; HANDCUFFS
- E05B41/00—Locks with visible indication as to whether the lock is locked or unlocked
-
- E—FIXED CONSTRUCTIONS
- E05—LOCKS; KEYS; WINDOW OR DOOR FITTINGS; SAFES
- E05B—LOCKS; ACCESSORIES THEREFOR; HANDCUFFS
- E05B45/00—Alarm locks
- E05B45/06—Electric alarm locks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5072—Grid computing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/54—Interprogram communication
- G06F9/546—Message passing systems or structures, e.g. queues
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
- G06V10/225—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition based on a marking or identifier characterising the area
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/94—Hardware or software architectures specially adapted for image or video understanding
- G06V10/95—Hardware or software architectures specially adapted for image or video understanding structured as a network, e.g. client-server architectures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/96—Management of image or video recognition tasks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/50—Indexing scheme relating to G06F9/50
- G06F2209/5018—Thread allocation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/50—Indexing scheme relating to G06F9/50
- G06F2209/502—Proximity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/54—Indexing scheme relating to G06F9/54
- G06F2209/548—Queue
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention discloses a method and a device for judging the opening and closing state of a door, an electronic terminal and a storage medium, wherein the method comprises the following steps: acquiring an image of at least one gate area of a target scene at the current moment, and storing the image into a preset queue; when the number of the images stored in the preset queue reaches the number of the door areas, taking out each image from the preset queue; identifying target characteristic points of preset marks in each image, and determining actual pixel coordinates of each target characteristic point; acquiring preset pixel coordinates of each target feature point, and determining the opening and closing state of the corresponding door area at the current moment according to each actual pixel coordinate and the corresponding preset pixel coordinate; and if the opening state exists in the switch states, performing abnormal opening alarm of the corresponding door area. Not only can avoid a large amount of earlier stage work, can improve the suitability under the different scenes moreover, can also realize supporting the judgement of many switch states at the limited terminal of resource, fall to ground deployment cycle short, with low costs.
Description
Technical Field
The embodiment of the invention relates to a computer vision technology, in particular to a method and a device for judging a door opening and closing state, an electronic terminal and a storage medium.
Background
The accurate judgment of the opening and closing states of the door is an important and basic requirement in most intelligent security scenes.
In the prior art, the door opening and closing state determination method generally includes the following steps: 1. detecting the position of the door through a target detection model, and further identifying the opening and closing states of the door; 2. under the fixed camera, the position of the door does not need to be detected, and the real-time image of the door area only needs to be classified and identified by a classifier according to the opening and closing state; 3. firstly setting a door opening and closing state template in an application scene, matching the template from the image, and then tracking the template to judge the opening and closing state.
The disadvantages of the prior art include at least: if the judgment is carried out based on the first method, the data set of the opening and closing states of the door needs to be collected, data labeling needs to be carried out, a target detection model needs to be trained, and the like, so that the application landing period is long, and the relative cost is high; if the judgment is carried out based on the method two, not only the earlier stage work which is the same as that of the method one exists, but also the camera cannot be guaranteed to be fixed in a real use scene; if the judgment is carried out based on the method III, the scene customization requirement is high, a new template of the door needs to be acquired during deployment each time, in addition, during template tracking, if a target tracking algorithm of a traditional method is adopted, the influence of the external environment is easily caused, if a deep learning method is adopted, larger computing resources are needed, and the landing cost is increased.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method and an apparatus for determining a door opening/closing state, an electronic terminal, and a storage medium, which can avoid a large amount of preliminary work, improve applicability in different scenarios, and enable a resource-limited terminal to support determination of a multi-door opening/closing state, and have a short floor-to-floor deployment cycle and a low cost.
In a first aspect, an embodiment of the present invention provides a method for determining a door opening/closing state, including:
acquiring an image of at least one gate area of a target scene at the current moment, and storing the image into a preset queue;
when the number of the images stored in the preset queue reaches the number of the door areas, taking out each image from the preset queue;
identifying target characteristic points of preset marks in each image, and determining actual pixel coordinates of each target characteristic point;
acquiring preset pixel coordinates of each target feature point, and determining the opening and closing state of the corresponding door area at the current moment according to each actual pixel coordinate and the corresponding preset pixel coordinate;
and if the opening state exists in the switch states, performing abnormal opening alarm of the corresponding door area.
In a second aspect, an embodiment of the present invention further provides a device for determining a door opening/closing state, including:
the storage module is used for acquiring an image of at least one door area of a target scene at the current moment and storing the image into a preset queue;
the taking-out module is used for taking out each image from the preset queue when the number of the images stored in the preset queue reaches the number of the door areas;
the identification module is used for identifying target feature points of preset identifications in each image and determining actual pixel coordinates of each target feature point;
the state determining module is used for acquiring preset pixel coordinates of each target feature point and determining the opening and closing state of the corresponding door area at the current moment according to each actual pixel coordinate and the corresponding preset pixel coordinate;
and the alarm module is used for performing abnormal opening alarm of the corresponding door area if the opening state exists in the switch states.
In a third aspect, an embodiment of the present invention further provides an electronic terminal, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the method for determining the door opening/closing state according to any embodiment of the present application.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the method for determining a door open/close state provided in any embodiment of the present application.
The embodiment of the invention provides a door opening and closing state determination method, a door opening and closing state determination device, an electronic terminal and a storage medium, wherein the door opening and closing state determination method comprises the following steps: acquiring an image of at least one door area of a target scene at the current moment, and storing the image into a preset queue; when the number of the images stored in the preset queue reaches the number of the door areas, taking out each image from the preset queue; identifying target feature points of preset marks in each image, and determining actual pixel coordinates of each target feature point; acquiring preset pixel coordinates of each target feature point, and determining the opening and closing state of the corresponding door area at the current moment according to each actual pixel coordinate and the corresponding preset pixel coordinate; and if the opening state exists in the switch states, performing abnormal opening alarm of the corresponding door area. The method can avoid a large amount of earlier-stage work, can improve the applicability under different scenes, can realize the judgment of supporting the multi-door switch state at the resource-limited terminal, and has short floor deployment period and low cost.
Drawings
Fig. 1 is a schematic flowchart of a method for determining a door opening/closing state according to an embodiment of the present invention;
fig. 2 is an exemplary diagram of ArUco two-dimensional code in a method for determining a gate switch state according to an embodiment of the present invention;
fig. 3 is a schematic diagram illustrating a door area in an open or closed state according to a method for determining an open/close state of a door provided in an embodiment of the present invention;
fig. 4 is a schematic diagram illustrating another door area in an open or closed state in a method for determining an open/close state of a door according to an embodiment of the present invention;
FIG. 5 is a diagram showing the effect of a method for determining the open/close state of a door according to the prior art;
fig. 6 is a diagram illustrating an effect of an alternative exemplary method for determining the opening/closing state of the door according to an embodiment of the present invention;
fig. 7 is a flowchart of another alternative example of a door opening/closing state determination method according to an embodiment of the present invention;
fig. 8 is a schematic flowchart of a method for determining a door opening/closing state according to a second embodiment of the present invention;
fig. 9 is an exemplary diagram of a two-dimensional code in an image and a two-dimensional code in the image in a method for determining a door opening/closing state according to the second embodiment of the present invention in the real world;
fig. 10 is a flowchart of an alternative example of a door opening/closing state determination method according to the second embodiment of the present invention;
fig. 11 is a schematic structural diagram of a door opening/closing state determining apparatus according to a third embodiment of the present invention;
fig. 12 is a schematic structural diagram of an electronic terminal according to a fourth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention. In the following embodiments, optional features and examples are provided in each embodiment, and various features described in the embodiments may be combined to form a plurality of alternatives, and each numbered embodiment should not be regarded as only one technical solution.
Example one
Fig. 1 is a schematic flowchart of a method for determining a door opening/closing state according to an embodiment of the present invention. The present embodiment is applicable to a case where the determination of the multi-gate switch state is performed based on a resource-limited terminal. The method can be executed by the door opening and closing state determination device provided by the embodiment of the invention, the device can be realized in a software and/or hardware mode, and can be configured in an electronic terminal, for example, in an edge terminal such as a resource-limited server or an embedded development board.
Referring to fig. 1, the method for determining the open/close state of the door provided in this embodiment may include:
s110, obtaining an image of at least one door area of the target scene at the current moment, and storing the image into a preset queue.
The target scene may be understood as a scene having a door area requiring a determination of the door opening/closing state, such as a cold chain movable mortgage warehouse or a financial mortgage warehouse. The gate area may be understood as an area having a gate requiring a determination of the state of the gate opening and closing. The image at the current moment can be understood as the image of the door area at the moment when the door opening and closing state needs to be judged; the mode of acquiring the image at the current moment can be a camera which is deployed near the door area and can clearly shoot the range of the door area; the number of the cameras can be multiple, and the number of the cameras can be determined by the number of the door areas; the cameras are not additional deployments and specific cameras, and may be originally present near the door area. The preset queue may be understood as a preset queue capable of storing the image of the current time of at least one gate area, and the length of the preset queue is determined by the number of the gate areas.
For example, in a target scene, there may be a plurality of gate areas, and in order to support the determination of the multi-gate switch state under the condition of limited resources, an image of at least one gate area of the target scene at the current time may be captured by the camera; images are acquired from the camera simultaneously in a multithreading mode so as to realize the maximum utilization of computing resources; and storing the read images into a preset queue by multiple threads. It should be noted that, when the read images are stored in the preset queue in multiple threads, the camera and the door area information to which the images belong can also be stored.
In practical application, the images of the gate area may be acquired at preset time intervals, or may be acquired in real time.
It can be understood that after all the images in the preset queue are processed, a new image can be stored in the preset queue to ensure that all the images in the preset queue are the images corresponding to at least one next door region at the same time.
And S120, taking out each image from the preset queue when the number of the images stored in the preset queue reaches the number of the door areas.
When the number of the images stored in the preset queue reaches the number of the door areas, the fact that all the images of the door areas requiring door opening and closing state judgment at the current moment are stored in the preset queue is shown. At this point, the retrieval of each image from the preset queue may be initiated to determine the open/close status of each door zone at the current time.
And S130, identifying target characteristic points of preset marks in each image, and determining actual pixel coordinates of each target characteristic point.
The preset identifier may be a pre-deployed identifier with a feature point, for example, a trademark pattern existing in the door area itself, paper posted with a two-dimensional code, or a two-dimensional code painted on the door area. The target feature point can be understood as an easily recognized feature point on the preset mark. The actual pixel coordinates can be understood as pixel position coordinates of pixel points corresponding to the target feature points in the image coordinate system.
Specifically, target feature points of preset marks in each image can be identified, and position coordinates of the target feature points in an image coordinate system are determined as actual pixel coordinates of each target feature point.
Optionally, the preset identifier includes at least one two-dimensional code; and each two-dimensional code has a binding relationship with the information of the corresponding door area.
The two-dimensional code is a pattern which is distributed on a plane (in a two-dimensional direction) according to a certain rule by using a certain specific geometric figure, is alternate in black and white and records data symbol information; the two-dimensional code has stable detection property, strong applicability in different scenes, short land deployment period and greatly reduced application cost; it should be noted that the two-dimensional code not only can be used as a preset identifier, but also can carry certain information.
Fig. 2 is an exemplary diagram of an ArUco two-dimensional code in a method for determining a door switch state according to an embodiment of the present invention. For example, referring to fig. 2, an ArUco two-dimensional code may be deployed in advance for each door region as a preset identifier, four corner points of the ArUco two-dimensional code are used as target feature points, and the ArUco two-dimensional code is bound with information of the corresponding door region; the method can identify four corner points of the Aruco two-dimensional codes in each image, and determine actual pixel coordinates of the four corner points corresponding to the Aruco two-dimensional codes respectively; when the actual pixel coordinates of each target feature point are determined, the door area information bound by the ArUco two-dimensional code can be identified, for example, the position of the door area, the number corresponding to the door area, the building name corresponding to the door area, the importance degree of the door area, and the like can be identified.
The detection of the Aruco two-dimensional code is integrated in an OpenCV algorithm, and compared with other reference objects serving as preset marks, the detection method has the advantages of being fast and convenient. It should be noted that when identifying the door region information bound by the ArUco two-dimensional code, the bound door region information may be directly identified according to the ArUco two-dimensional code, or a number corresponding to the ArUco two-dimensional code may be identified first, and then the door region information corresponding to the number may be obtained according to a mapping relationship between the number and the door region information.
S140, acquiring preset pixel coordinates of each target feature point, and determining the opening and closing state of the corresponding door area at the current moment according to each actual pixel coordinate and the corresponding preset pixel coordinate.
The preset pixel coordinates can be understood as pixel position coordinates of the target feature point in the image coordinate system when the door area is in the normal closed state.
In the embodiment of the invention, the preset pixel coordinates of each target feature point can be obtained, and the opening and closing state of the corresponding door area at the current moment can be determined according to the position relation between each actual pixel coordinate and the corresponding preset pixel coordinate. The open/close state can be understood as an open/close state of the door region. Fig. 3 is a schematic diagram illustrating a door area in an open or closed state in a method for determining a door opening/closing state according to an embodiment of the present invention, and fig. 4 is a schematic diagram illustrating another door area in an open or closed state in a method for determining a door opening/closing state according to an embodiment of the present invention. In fig. 3, the actual pixel coordinate corresponding to the left door area is not changed compared to the preset pixel coordinate, which indicates that the left door area is in a closed state; the actual pixel coordinate corresponding to the door area on the right side moves upwards by a larger distance compared with the position of the preset pixel coordinate, and the door area on the left side is in an open state. In fig. 4, the actual pixel coordinate corresponding to the left door area is not changed compared with the preset pixel coordinate, which indicates that the left door area is in a closed state; the actual pixel coordinate corresponding to the door area on the right side moves a larger distance to the left than the position of the preset pixel coordinate, and the door area on the left side is in an open state.
And S150, if the opening state exists in the switch states, performing abnormal opening alarm of the corresponding door area.
The abnormal opening alarm can be understood as an alarm when the corresponding door area is in an abnormal opening state, and the alarm mode can be a sound alarm, a light alarm or an alarm message sent to a preset terminal, and the alarm mode is not exhaustive.
It should be noted that, in at least one door zone of the target scene, if at least one door zone is in an open state, it indicates that the door switch state in the target scene is abnormal, and an abnormal opening alarm is performed on the door zone in the open state.
In practical application, the abnormal opening alarm can be performed when the door area is in an open state, for example, in a scene of state identification of an emergency fire door in a financial pledge warehouse, the emergency fire door in the scene should be normally closed, and when the emergency fire door is in an open state, the abnormal opening alarm is performed so as to facilitate manual intervention supervision. The abnormal opening alarm can also be avoided when the door area is legally opened, for example, the worker legally adopts the cooperation of key opening and face recognition to ensure that the abnormal opening alarm is not carried out when the door area is in the opened state.
In practical application, if the opening and closing state of the corresponding door area at the current moment is determined, the door area information is identified according to the preset identification, and abnormal opening alarm can be performed according to the door area information identified by the preset identification and/or the camera and the door area information stored when the image is stored in the preset queue. The setting can construct more service scenes for judging the door area state and provide more service requirements for judging the door area state.
It should also be noted that, in practical applications, in order to avoid a large amount of preliminary work without requiring a Graphics Processing Unit (GPU) to calculate resources, and to improve applicability in different scenarios, the method according to the embodiment of the present invention may be deployed at an edge terminal with limited resources, and the determination of the door open/close state is enabled in a multithreading manner. The edge terminal may be a resource-limited server or an embedded development board, and is not limited in this respect.
The method for judging the opening and closing states of the door, provided by the embodiment of the invention, comprises the steps of obtaining an image of at least one door area of a target scene at the current moment, and storing the image into a preset queue; when the number of the images stored in the preset queue reaches the number of the door areas, taking out each image from the preset queue; identifying target feature points of preset marks in each image, and determining actual pixel coordinates of each target feature point; acquiring preset pixel coordinates of each target feature point, and determining the opening and closing state of the corresponding door area at the current moment according to each actual pixel coordinate and the corresponding preset pixel coordinate; and if the opening state exists in the switch states, performing abnormal opening alarm of the corresponding door area.
For example, fig. 5 is an effect diagram of a method for determining the open/close state of a door in the related art. Fig. 6 is a diagram illustrating an effect of an alternative exemplary method for determining a door open/close state according to an embodiment of the present invention. Referring to fig. 5, the method for determining the open/close state of the door based on template matching and the conventional tracking algorithm in the prior art is very easily affected by the external environment, and the matching target is lost when the color of the door is close to that of the wall, so that the normal open/close state of the door cannot be determined. Referring to fig. 6, according to the technical scheme of the embodiment of the invention, a model is not required to be used for door state judgment, so that the early-stage work of model training can be omitted; the preset identifier can be fixed in the door area, so that the scene stability can be ensured; different preset pixel coordinates are set according to different scenes, so that the scene universality can be improved; the required computing resources are few, and the switching state judgment of multiple doors can be realized based on the resource-limited terminal. The technical scheme of the embodiment of the invention can solve the problems in the prior art, not only can avoid a large amount of earlier work, but also can improve the applicability under different scenes, can realize the judgment of supporting the multi-door switch state at the resource-limited terminal, and has short floor deployment period and low cost.
An optional technical solution, a method for determining a door opening/closing state, further includes: the time when the first image is stored in the preset queue is used as a first time; and if the number of the images stored in the preset queue does not reach the number of the door areas after the first preset time length from the first moment, emptying the preset queue and acquiring the image of at least one door area of the target scene at the next moment.
The first time is the time when the first image is stored in the preset queue. The first preset time duration may be understood as a preset time duration for determining whether to empty the preset queue.
It should be noted that, in the embodiment of the present invention, since the determination is performed based on the opening and closing state of the target scene door, and there is a corresponding relationship between the number of the door areas of the target scene and the length of the preset queue, if the number of the images in the preset queue does not reach the number of the door areas within a certain time, it is described that the image acquisition of each door area of the target scene at the current time is abnormal.
In order to prevent a determination error of the door open/close state due to the abnormality, and to realize a determination algorithm of a single door open/close state, the open/close states of a plurality of door areas may be determined, and an image of each door area at the present time may be selected to be discarded.
Fig. 7 is a flowchart of another alternative example of a door opening and closing state determination method according to an embodiment of the present invention. Referring to fig. 7, images of n gate areas of a target scene at the current time are obtained according to n cameras, the read images are stored in a preset queue in a multithread mode, information of the cameras and the gate areas to which the images belong is stored, the number of the images stored in the preset queue is obtained, when the number of the images stored in the preset queue reaches the number n of the gate areas, the images can be taken out of the preset queue, and the on-off state of the gate is judged to obtain the on-off states of the n gates corresponding to the n cameras. In addition, if the number of the images stored in the preset queue does not reach n when the first preset time length is elapsed from the moment of storing the first image, the preset queue can be emptied, and the image of at least one door area of the target scene at the next moment is obtained.
In the embodiment of the present invention, since the image may be obtained in real time, and the calculation process of determining the door opening/closing state according to the image at each time takes a short time, for example, one frame of image may be processed in 0.02S, the interval between the current time and the next time is also extremely short, and discarding the image at one time does not have a great influence on the determination of the door opening/closing state.
In practical application, due to the fact that at least one camera is damaged or other reasons, images of a part of door regions cannot be acquired for a long time, therefore, the preset times for continuously emptying the preset queue can be preset, and after the times for continuously emptying the preset queue exceed the preset times, abnormal alarm is given to the image acquisition of the corresponding door region.
In the embodiment of the invention, the number of the images stored in the preset queue does not reach the number of the door areas, so that the preset queue emptying method has the advantages of preventing door opening and closing state judgment errors caused by abnormal image acquisition at the current moment, and realizing that a single door opening and closing state judgment algorithm can judge the opening and closing states of a plurality of door areas.
Another optional technical solution is that the method for determining the door opening/closing state further includes: if the preset mark in each image has an unrecognized target feature point, pushing a shielding warning of a corresponding door area; and if the warning time length of the shielding warning reaches a second preset time length, performing abnormal shielding warning of the corresponding door area.
The unrecognized target feature points can be understood as feature points on an obstacle which is shielded by the preset identifier. An occlusion warning may be understood as an alarm in case the preset identifier is occluded. The warning duration may be understood as the duration of existence of a preset target feature point for identifying existence of an unrecognized target feature point, and may also be understood as the duration of occlusion warning. The second preset time period can be understood as the preset warning time period required for carrying out abnormal shielding warning of the corresponding door area. The abnormal shielding alarm can be understood as an alarm that the long-term shielding of the preset identifier may cause the abnormal judgment of the opening and closing state of the door.
It should be noted that there may be piled up debris that may obstruct the predetermined indication, or that the predetermined indication in the door area may be obstructed by obstacles that may move over time, such as birds or passerby. Therefore, in order to ensure that the opening and closing state of the door can be normally judged, the preset marks in each image have unrecognized target feature points, if the unrecognized target feature points exist, it is indicated that other obstacles possibly shield the preset marks in the door area, and then shielding warning of the corresponding door area is pushed; and if the warning time for shielding the warning reaches a second preset time, which indicates that the preset identification is shielded by the obstacle which can not move by oneself for a long time, performing abnormal shielding alarm in the corresponding door area.
It can be understood that when the preset identifier in each image has an unrecognized target feature point, the preset identifier may be shielded by a short-term shielding obstacle such as a bird or a passing passerby, and a low-level shielding warning may be performed; when the warning duration of the shielding warning reaches a second preset duration, the situation that the door opening and closing state cannot be judged normally possibly is shown, the barrier needs to be removed, and high-level abnormal shielding warning can be carried out.
In the embodiment of the invention, the shielding warning or abnormal shielding alarm of the corresponding door area is pushed, so that the problem that the opening and closing state of the door cannot be normally judged due to the shielding of the preset identification by the barrier can be avoided.
Example two
The determination method of the door open/close state provided in the present embodiment can be combined with each alternative in the determination method of the door open/close state provided in the above-described embodiments. The method for determining the open-close state of the raw door provided in this embodiment describes in detail the determination of the open-close state of the corresponding door area at the current time according to each actual pixel coordinate and the corresponding preset pixel coordinate. Calculating the pixel distance between each actual pixel coordinate and the corresponding preset pixel coordinate; and if the pixel distance is greater than the preset threshold value, determining that the corresponding door area is in an open state at the current moment. The opening and closing state of the corresponding door area at the current moment can be determined more accurately.
Fig. 8 is a schematic flowchart of a method for determining a door opening/closing state according to a second embodiment of the present invention. Referring to fig. 8, the method for determining the open/close state of the door provided in this embodiment may include:
s210, obtaining an image of at least one door area of the target scene at the current moment, and storing the image into a preset queue.
S220, when the number of the images stored in the preset queue reaches the number of the door areas, taking out each image from the preset queue.
And S230, identifying target characteristic points of preset marks in each image, and determining actual pixel coordinates of each target characteristic point.
S240, acquiring preset pixel coordinates of each target feature point, and calculating pixel distances between each actual pixel coordinate and the corresponding preset pixel coordinate.
The pixel distance can be understood as the distance between the actual pixel coordinate and the corresponding preset pixel coordinate; the method for calculating the pixel distance may be euclidean distance calculation, manhattan distance calculation, chebyshev distance calculation, mahalanobis distance calculation, or the like, and is not particularly limited herein.
It can be understood that, since the preset pixel coordinate is a coordinate of the target feature point in the door area in the normally closed state, if there is a large deviation in the position distance between the actual pixel coordinate and the corresponding preset pixel coordinate, it indicates that the door area corresponding to the actual pixel coordinate is not in the normally closed state at the current moment. Therefore, if the door opening and closing state needs to be judged, the pixel distance between each actual pixel coordinate and the corresponding preset pixel coordinate can be calculated.
For example, the preset pixel coordinates of each target feature point in the image coordinate system when the door area is in the normally closed state may be predetermined, and the actual pixel coordinates of each target feature point in the image coordinate system corresponding to the target feature point at the current moment may be determined when the door is in the open-close state; calculating a pixel distance between each actual pixel coordinate and the corresponding preset pixel coordinate, where the formula for calculating the pixel distance may be:
where ρ is the actual pixel coordinate (x) 2 ，y 2 ) With preset pixel coordinates (x) 1 ，y 1 ) Pixel distance in between.
In practical application, the preset distance between the preset pixel coordinate and the origin of the image coordinate system can be predetermined, the actual distance between the actual pixel coordinate and the origin of the image coordinate system is determined when the door opening and closing state is judged, the difference value between the preset distance and the actual distance is calculated as the pixel distance, and the formula for calculating the pixel distance can be as follows:
wherein | X | is the actual pixel coordinate (X) 2 ，y 2 ) And a predetermined pixel coordinate (x) 1 ，y 1 ) Pixel distance in between.
And S250, if the pixel distance is larger than a preset threshold value, determining that the corresponding door area is in an opening state at the current moment.
The preset threshold may be a threshold corresponding to a preset pixel distance.
It is to be noted that, possibly due to the existence of an error, the switching state of the door area at the present time may not be the on state when the pixel distance is small, and therefore a preset threshold may be set to avoid an error in the determination of the door switching state.
And S260, if the opening state exists in the switch states, performing abnormal opening alarm of the corresponding door area.
According to the method for judging the opening and closing state of the door, provided by the embodiment of the invention, the pixel distance between each actual pixel coordinate and the corresponding preset pixel coordinate is calculated; and if the pixel distance is greater than the preset threshold value, determining that the corresponding door area is in an open state at the current moment. The opening and closing state of the corresponding door area at the current moment can be determined more accurately.
An optional technical solution is that, if each preset identifier includes at least one target feature point, after a pixel distance between each actual pixel coordinate and a corresponding preset pixel coordinate is calculated, the method for determining the opening and closing state of the door further includes: and determining a final pixel distance corresponding to each preset identifier according to the pixel distance between the actual pixel coordinate of each target feature point in the same preset identifier and the preset pixel coordinate.
The final pixel distance may be a pixel distance obtained by combining the actual pixel coordinates of each target feature point in the same preset identifier with the pixel distance between the preset pixel coordinates.
It should be noted that each preset identifier may have a plurality of target feature points, for example, a two-dimensional code has four corner points, and due to the existence of errors, the pixel distances corresponding to the target feature points on the same preset identifier are not necessarily the same. Therefore, the final pixel distance corresponding to each preset identifier can be determined according to the pixel distance between the actual pixel coordinate and the preset pixel coordinate of each target feature point in the same preset identifier, and the state of the corresponding door area at the current moment can be determined according to the final pixel distance. The method for determining the final pixel distance may be to average, maximum, minimum, or median the pixel distances between the actual pixel coordinates and the preset pixel coordinates of the target feature points in the same preset identifier, and is not limited specifically herein.
In practical application, the same gate region may also correspond to multiple preset identifiers, and the final pixel distance corresponding to the gate region is determined according to multiple target feature points corresponding to the multiple preset identifiers.
The advantage of setting the final pixel distance is that the problem that the pixel distances corresponding to the target feature points on the same preset identifier are not necessarily the same can be solved, and the error of the judgment of the door opening and closing state is reduced.
In another optional technical solution, the step of determining the preset threshold includes: and determining a preset threshold according to the mapping relation between the image space coordinate and the world space coordinate.
It should be noted that, due to the difference in the device type, device model, or installation position of the shooting device such as a camera for shooting images of different door regions, the value of the preset threshold value is changed accordingly, otherwise, the problem of low accuracy in determining the opening and closing state of the door is caused. In order to improve applicability under different scenes, in the embodiment of the present invention, a camera for capturing an image may be calibrated in advance, an image coordinate system corresponding to the image captured by the camera is mapped with a world coordinate system, and a preset threshold value is determined according to a mapping relationship between an image space coordinate and a world space coordinate.
Fig. 9 is an exemplary diagram of a two-dimensional code in an image and a two-dimensional code in the image in a method for determining a door opening/closing state according to the second embodiment of the present invention in the real world. For example, referring to fig. 9, the size of the two-dimensional code in the image is 148 pixels, and the width of the two-dimensional code in the image in the real world is 80cm, so that the distance ratio relationship between the image coordinate system and the world coordinate system is 1.85 pixels/cm, and at this time, the size of the Pixel distance in the real world in the normal closing state of the door region in the real world can be configured according to requirements, that is, the Pixel distance can be automatically converted into the preset threshold corresponding to the image, thereby avoiding the situation of blindly setting the preset threshold.
In the embodiment of the invention, the advantage of determining the preset threshold value according to the mapping relationship between the image space coordinate and the world space coordinate is that the applicability under different scenes can be improved.
Fig. 10 is a flowchart of an alternative example of a method for determining a door opening/closing state according to the second embodiment of the present invention. In order to better understand the technical solutions of the embodiments of the present invention, an alternative example is provided herein. For example, referring to fig. 10, images of three gate areas of a target scene at the current time are obtained, and the images are stored in a preset queue and taken out for image preprocessing; performing a judging function of a service configuration door opening switch state, and deploying a two-dimensional code on a door area; detecting the angular points of the two-dimensional code, and judging whether the angular points cannot be detected or not; if the corner point cannot be detected, judging whether the shielding warning duration of the corresponding door area is greater than a second preset threshold value or not, if not, pushing the shielding warning of the corresponding door area, and if so, performing abnormal shielding warning of the corresponding door area; and if the corner point is detected, judging that the final pixel distance is larger than a preset threshold value, if so, performing abnormal opening alarm of the corresponding door area, and if not, all the door areas are in a normal closing state.
In addition, the method for determining the open/close state of the door provided by the present embodiment is the same as the method for determining the open/close state of the door provided by the above embodiment, and the technical details that are not described in detail in the present embodiment can be referred to the above embodiment, and the same technical features have the same beneficial effects in the present embodiment and the above embodiment.
EXAMPLE III
Fig. 11 is a schematic structural diagram of a door opening/closing state determination device according to a third embodiment of the present invention. The present embodiment is applicable to a case where the determination of the multi-gate switch state is performed based on a resource-limited terminal.
Referring to fig. 11, the door open/close state determining apparatus according to the present invention may include:
a storing module 310, configured to obtain an image of at least one gate area of a target scene at a current time, and store the image in a preset queue;
a fetching module 320, configured to fetch each image from the preset queue when the number of images stored in the preset queue reaches the number of the gate areas;
the identification module 330 is configured to identify target feature points with preset identifiers in each image, and determine actual pixel coordinates of each target feature point;
the state determining module 340 is configured to obtain preset pixel coordinates of each target feature point, and determine an open/close state of a corresponding door area at the current time according to each actual pixel coordinate and the corresponding preset pixel coordinate;
and an alarm module 350, configured to perform an abnormal opening alarm of the corresponding door area if an opening state exists in the switch states.
Optionally, the logging module may further be configured to:
the time when the first image is stored in the preset queue is used as a first time;
and if the number of the images stored in the preset queue does not reach the number of the door areas after the first preset time length from the first moment, emptying the preset queue and acquiring the image of at least one door area of the target scene at the next moment.
Optionally, if the preset identifier in each image has a target feature point that is not recognized by the recognition module, the alarm module may be configured to:
pushing shielding warning of a corresponding door area;
and if the warning time length of the shielding warning reaches a second preset time length, performing abnormal shielding warning of the corresponding door area.
Optionally, the state determination module may include:
the pixel distance calculating unit is used for calculating the pixel distance between each actual pixel coordinate and the corresponding preset pixel coordinate;
and the opening state determining unit is used for determining that the corresponding door area is in an opening state at the current moment if the pixel distance is greater than the preset threshold value.
On the basis of the foregoing scheme, optionally, if each preset identifier includes at least one target feature point, the state determining module may further include:
and the final pixel distance determining unit is used for determining the final pixel distance corresponding to each preset identifier according to the pixel distance between the actual pixel coordinate of each target feature point in the same preset identifier and the preset pixel coordinate after calculating the pixel distance between each actual pixel coordinate and the corresponding preset pixel coordinate.
Optionally, the door open/close state determining device may further include:
and the preset threshold value determining module is used for determining the preset threshold value according to the mapping relation between the image space coordinate and the world space coordinate.
On the basis of the scheme, optionally, the preset identifier comprises at least one two-dimensional code; and each two-dimensional code has a binding relationship with the information of the corresponding door area.
According to the door opening and closing state judging device provided by the embodiment of the invention, the image of at least one door area of a target scene at the current moment is obtained through the storing module, and the image is stored in the preset queue; when the number of the images stored in the preset queue reaches the number of the door areas, taking out each image from the preset queue through a taking-out module; identifying target characteristic points of preset identifications in each image through an identification module, and determining actual pixel coordinates of each target characteristic point; acquiring preset pixel coordinates of each target feature point through a state determination module, and determining the opening and closing state of a corresponding door area at the current moment according to each actual pixel coordinate and the corresponding preset pixel coordinate; and if the opening state exists in each switch state through the alarm module, performing abnormal opening alarm of the corresponding door area. The method can avoid a large amount of earlier-stage work, can improve the applicability under different scenes, can realize the judgment of supporting the multi-door switch state at the resource-limited terminal, and has short floor deployment period and low cost.
The door opening and closing state determining device provided by the embodiment of the invention can execute the door opening and closing state determining method provided by the embodiment of the invention, and has the corresponding functional modules and beneficial effects of the executing method. For details of the technology that is not described in detail, reference may be made to the method for determining the opening and closing state of the door provided in the embodiments of the present invention.
Example four
Fig. 12 is a schematic structural diagram of an electronic terminal according to a fourth embodiment of the present invention. As shown in fig. 12, the terminal may include a processor 410, a memory 420, an input device 430, and an output device 440; the number of the processors 410 in the terminal may be one or more, and one processor 410 is taken as an example in fig. 4; the processor 410, the memory 420, the input device 430 and the output device 440 in the terminal/may be connected by a bus or other means, and the connection by the bus is exemplified in fig. 12.
The memory 420 serves as a computer-readable storage medium for storing software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the door opening and closing state determination method in the embodiment of the present invention (e.g., a storing module, a retrieving module, an identifying module, a state determining module, and an alarm module in the door opening and closing state determination device). The processor 410 executes various functional applications and data processing of the device/terminal/server by executing software programs, instructions, and modules stored in the memory 420, thereby implementing the above-described method for determining the door open/close state.
The memory 420 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 420 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, the memory 420 can further include memory located remotely from the processor 410, which can be connected to the terminal over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 430 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the terminal. The output device 440 may include a display device such as a display screen.
EXAMPLE five
An embodiment of the present invention further provides a storage medium containing computer-executable instructions, where the computer-executable instructions are executed by a computer processor to perform a method for determining a state of a door switch, and the method includes:
acquiring an image of at least one gate area of a target scene at the current moment, and storing the image into a preset queue; when the number of the images stored in the preset queue reaches the number of the door areas, taking out each image from the preset queue; identifying target feature points of preset marks in each image, and determining actual pixel coordinates of each target feature point;
acquiring preset pixel coordinates of each target feature point, and determining the opening and closing state of a corresponding door area at the current moment according to each actual pixel coordinate and the corresponding preset pixel coordinate; and if the opening state exists in the switch states, performing abnormal opening alarm of the corresponding door area.
Of course, the storage medium provided by the embodiment of the present invention contains computer-executable instructions, and the computer-executable instructions are not limited to the above method operations, and may also perform related operations in the method for determining the door opening and closing state provided by any embodiment of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention or portions thereof contributing to the prior art may be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods of the embodiments of the present invention.
It should be noted that, in the embodiment of the above search apparatus, each included unit and module are merely divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments illustrated herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A method for determining a door opening/closing state, comprising:
acquiring an image of at least one door area of a target scene at the current moment, and storing the image into a preset queue;
when the number of the images stored in the preset queue reaches the number of the door areas, taking out each image from the preset queue;
identifying target characteristic points of preset identifications in the images, and determining actual pixel coordinates of the target characteristic points;
acquiring preset pixel coordinates of each target feature point, and determining the opening and closing state of a corresponding door area at the current moment according to each actual pixel coordinate and the corresponding preset pixel coordinate;
and if the opening state exists in the opening and closing states, performing abnormal opening alarm corresponding to the door region.
2. The method of claim 1, further comprising:
the moment when the first image is stored in the preset queue is used as a first moment;
and if the number of the images stored in the preset queue does not reach the number of the door areas after a first preset time length from the first moment, emptying the preset queue and acquiring the image of at least one door area of the target scene at the next moment.
3. The method of claim 1, further comprising:
if the preset identification in each image has unrecognized target feature points, pushing a shielding warning of a corresponding door area;
and if the warning time length of the shielding warning reaches a second preset time length, performing abnormal shielding warning of the corresponding door area.
4. The method of claim 1, wherein determining the opening and closing state of the corresponding gate region at the current time based on each of the actual pixel coordinates and the corresponding predetermined pixel coordinates comprises:
calculating the pixel distance between each actual pixel coordinate and the corresponding preset pixel coordinate;
and if the pixel distance is greater than a preset threshold value, determining that the corresponding door area is in an open state at the current moment.
5. The method according to claim 4, wherein if each of the preset identifiers includes at least one target feature point, after the calculating the pixel distance between each of the actual pixel coordinates and the corresponding preset pixel coordinate, the method further comprises:
and determining a final pixel distance corresponding to each preset identifier according to the pixel distance between the actual pixel coordinate of each target feature point in the same preset identifier and the preset pixel coordinate.
6. The method according to claim 4, wherein the step of determining the preset threshold comprises:
and determining a preset threshold according to the mapping relation between the image space coordinate and the world space coordinate.
7. The method according to any one of claims 1-6, wherein the preset identifier comprises at least one two-dimensional code; and each two-dimensional code has a binding relationship with the information of the corresponding door area.
8. A door opening/closing state determining device, comprising:
the storage module is used for acquiring an image of at least one door area of a target scene at the current moment and storing the image into a preset queue;
the taking-out module is used for taking out each image from the preset queue when the number of the images stored in the preset queue reaches the number of the door areas;
the identification module is used for identifying target characteristic points of preset identifications in the images and determining actual pixel coordinates of the target characteristic points;
the state determining module is used for acquiring preset pixel coordinates of each target feature point and determining the opening and closing state of the corresponding door area at the current moment according to each actual pixel coordinate and the corresponding preset pixel coordinate;
and the alarm module is used for performing abnormal opening alarm of the corresponding door area if the opening state exists in each switch state.
9. An electronic terminal comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method for determining a door open/close state as claimed in any one of claims 1 to 7 when executing the program.
10. A computer-readable storage medium, on which a computer program is stored, the program, when being executed by a processor, implementing the door opening/closing state determination method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211049208.3A CN115410153A (en) | 2022-08-30 | 2022-08-30 | Door opening and closing state judging method and device, electronic terminal and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211049208.3A CN115410153A (en) | 2022-08-30 | 2022-08-30 | Door opening and closing state judging method and device, electronic terminal and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115410153A true CN115410153A (en) | 2022-11-29 |
Family
ID=84163196
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211049208.3A Pending CN115410153A (en) | 2022-08-30 | 2022-08-30 | Door opening and closing state judging method and device, electronic terminal and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115410153A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116051897A (en) * | 2023-01-28 | 2023-05-02 | 合肥中科类脑智能技术有限公司 | Door opening and closing state detection method and device, edge processing equipment and storage medium |
-
2022
- 2022-08-30 CN CN202211049208.3A patent/CN115410153A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116051897A (en) * | 2023-01-28 | 2023-05-02 | 合肥中科类脑智能技术有限公司 | Door opening and closing state detection method and device, edge processing equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3806064B1 (en) | Method and apparatus for detecting parking space usage condition, electronic device, and storage medium | |
| WO2022105243A1 (en) | Event detection method, apparatus, electronic device, and storage medium | |
| CN114119676B (en) | Target detection tracking identification method and system based on multi-feature information fusion | |
| US9652863B2 (en) | Multi-mode video event indexing | |
| EP2798578B1 (en) | Clustering-based object classification | |
| CN109035304B (en) | Target tracking method, medium, computing device and apparatus | |
| CN111325769B (en) | Target object detection method and device | |
| CN108052859A (en) | A kind of anomaly detection method, system and device based on cluster Optical-flow Feature | |
| CN108053427A (en) | A kind of modified multi-object tracking method, system and device based on KCF and Kalman | |
| CN112733690A (en) | High-altitude parabolic detection method and device and electronic equipment | |
| CN110647818A (en) | Identification method and device for shielding target object | |
| JP7638398B2 (en) | Behavior detection method, electronic device and computer-readable storage medium | |
| CN115049954B (en) | Target identification method, device, electronic equipment and medium | |
| CN111797726A (en) | Flame detection method and device, electronic equipment and storage medium | |
| CN107786848A (en) | The method, apparatus of moving object detection and action recognition, terminal and storage medium | |
| CN114821441B (en) | A deep learning-based method for identifying moving targets at airports combined with ADS-B information | |
| CN116778673A (en) | Water area safety monitoring method, system, terminal and storage medium | |
| CN113505643A (en) | Violation target detection method and related device | |
| CN115410153A (en) | Door opening and closing state judging method and device, electronic terminal and storage medium | |
| CN102789645A (en) | Multi-objective fast tracking method for perimeter precaution | |
| CN111402185A (en) | Image detection method and device | |
| JP2021007055A (en) | Discriminator learning device, discriminator learning method, and computer program | |
| CN118134882A (en) | Foreign matter intrusion detection method, device, equipment and medium | |
| Zhang et al. | [Retracted] Fast Target Detection Algorithm Based on CFAR and Target Variance Characteristics | |
| CN114022509A (en) | Target tracking method and related equipment based on surveillance video of multiple animals |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |