CN107016061A - Video monitoring document handling method and device - Google Patents
Video monitoring document handling method and device Download PDFInfo
- Publication number
- CN107016061A CN107016061A CN201710152804.7A CN201710152804A CN107016061A CN 107016061 A CN107016061 A CN 107016061A CN 201710152804 A CN201710152804 A CN 201710152804A CN 107016061 A CN107016061 A CN 107016061A
- Authority
- CN
- China
- Prior art keywords
- video
- sample
- frame
- target
- information
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/7837—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using objects detected or recognised in the video content
- G06F16/784—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using objects detected or recognised in the video content the detected or recognised objects being people
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/7837—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using objects detected or recognised in the video content
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Library & Information Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of video monitoring document handling method and device, the problem of memory space at least to solve existing video monitoring file occupancy is too big.Methods described includes：The data flow of wagon flow video monitoring file is sampled according to default sample frequency, multiple Sample video frames are obtained；Extract the Sample video frame with goal-selling；According to sampling order, in the Sample video frame of extraction, it is determined that Sample video frame that is neighbouring and repeating, rejects the Sample video frame of the repetition；The parameter preset information of the target is never extracted in repeated sample frame of video；According to the identification information of the corresponding not repeated sample frame of video of each target, the parameter information extracted and the wagon flow video monitoring file, the target information of each target is generated according to default storage organization.
Description
Technical field
The present invention relates to monitoring field, more particularly to a kind of video monitoring document handling method and device.
Background technology
Video Supervision Technique is widely used, and spreads all over the various aspects such as traffic, public safety.Pass through regarding that video monitoring is obtained
The convenient inquiry of frequency file, evidence obtaining etc., foundation is provided for post-survey.
Prior art is general to search foundation by the mode of watching from video file, and inquiry mode compares limitation, and needs
Expend longer query time.Simultaneously because video file storage excessively takes memory space, so video file needs reservation one
It is just to be deleted after the section time, so as to reduce the pot-life of video file.
The content of the invention
In order to overcome the defect of above-mentioned prior art, the technical problem to be solved in the present invention is to provide a kind of video monitoring text
Part processing method and processing device, the problem of memory space at least to solve existing video monitoring file occupancy is too big.
In order to solve the above technical problems, a kind of video monitoring document handling method in the present invention, including：
The data flow of wagon flow video monitoring file is sampled according to default sample frequency, multiple Sample videos are obtained
Frame；
The Sample video frame with goal-selling is extracted, the target includes car and/or people；
According to sampling order, in the Sample video frame of extraction, it is determined that Sample video frame that is neighbouring and repeating, rejects institute
State the Sample video frame of repetition；
The parameter preset information of the target is never extracted in repeated sample frame of video；
According to the corresponding not repeated sample frame of video of each target, the parameter information extracted and wagon flow video monitoring text
The identification information of part, the target information of each target is generated according to default storage organization.
Alternatively, it is described according to sampling order, in the Sample video frame of extraction, it is determined that sample that is neighbouring and repeating is regarded
Frequency frame, including：
Initial Sample video frame is set, the initial Sample video frame is set to not repeated sample frame of video；
According to the sampling order, the similarity of each sample frame of video and the initial Sample video frame is contrasted successively；
When the phase knowledge and magnanimity for contrasting n-th of Sample video frame and the initial Sample video frame are more than or equal to predetermined threshold value
When, the Sample video frame between the initial Sample video frame and n-th of Sample video frame is defined as described adjacent to simultaneously
And the Sample video frame repeated；Wherein n is the integer more than or equal to 1.
Specifically, the similarity that each sample frame of video and the initial Sample video frame are contrasted successively, including：
Extract the default sample characteristics of the initial Sample video frame；
Contrast sample's frame of video is treated for any, the default sample characteristics for treating contrast sample's frame of video is extracted；
Using the absolute difference of two default sample characteristics of extraction as the initial Sample video frame and this treat pair
Than the similarity of Sample video frame.
Alternatively, when the target is vehicle, the target information includes the corresponding not repeated sample frame of video of target
Information, the identification information of the wagon flow video monitoring file, license board information and the car plate in the wagon flow video monitoring
The temporal information for occurring in file and/or disappearing；
When the target is behaved, the target information includes the information of the corresponding not repeated sample frame of video of target, institute
Identification information, face information and the face for stating wagon flow video monitoring file occur in the wagon flow video monitoring file
And/or the temporal information disappeared.
Specifically, according to the corresponding not repeated sample frame of video of each target, the parameter information extracted and the wagon flow
The identification information of video monitoring file is generated according to default storage organization after the target information of each target, and methods described is also wrapped
Include：
Store the target information of each target；
Receive search information；
The search target corresponding with the search information from the target information of each target of storage；
The information of not repeated sample frame of video according to corresponding to the target searched, exports the not repeated sample of the target
Frame of video.
In order to solve the above technical problems, a kind of video monitoring document handling apparatus in the present invention, including：
Sampling module, for being sampled according to default sample frequency to video monitoring stream, obtains multiple Sample videos
Frame；
Object extraction module, for extracting the Sample video frame with goal-selling, the target includes car and/or people；
Deduplication module, for according to sampling order, in the Sample video frame of extraction, it is determined that sample that is neighbouring and repeating
Frame of video；
Parameter extraction module, the parameter preset information for extracting the target in never repeated sample frame of video；
Generation module, for according to the corresponding not repeated sample frame of video of each target, the parameter information and described extracted
The identification information of wagon flow video monitoring file, the target information of each target is generated according to default storage organization.
Alternatively, the deduplication module, specifically for setting initial Sample video frame, the initial Sample video frame is set
It is set to not repeated sample frame of video；
According to the sampling order, the similarity of each sample frame of video and the initial Sample video frame is contrasted successively；
When the phase knowledge and magnanimity for contrasting n-th of Sample video frame and the initial Sample video frame are more than or equal to predetermined threshold value
When, the Sample video frame between the initial Sample video frame and n-th of Sample video frame is defined as described adjacent to simultaneously
And the Sample video frame repeated；Wherein n is the integer more than or equal to 1.
Specifically, the similarity that each sample frame of video and the initial Sample video frame are contrasted successively, including：
Extract the default sample characteristics of the initial Sample video frame；
Contrast sample's frame of video is treated for any, the default sample characteristics for treating contrast sample's frame of video is extracted；
Using the absolute difference of two default sample characteristics of extraction as the initial Sample video frame and this treat pair
Than the similarity of Sample video frame.
Alternatively, when the target is vehicle, the target information includes the corresponding not repeated sample frame of video of target
Information, the identification information of the wagon flow video monitoring file, license board information and the car plate in the wagon flow video monitoring
The temporal information for occurring in file and/or disappearing；
When the target is behaved, the target information includes the information of the corresponding not repeated sample frame of video of target, institute
Identification information, face information and the face for stating wagon flow video monitoring file occur in the wagon flow video monitoring file
And/or the temporal information disappeared.
Specifically, described device also includes read module；
The read module, the target information for storing each target；
Receive search information；
Target information search target corresponding with the search information from each target of storage；
The information of not repeated sample frame of video according to corresponding to the target searched, exports the not repeated sample of the target
Frame of video.
The present invention has the beneficial effect that：
Method and apparatus are by extracting the Sample video frame with goal-selling in the present invention；According to sampling order, carrying
In the Sample video frame taken, it is determined that Sample video frame that is neighbouring and repeating, rejects the Sample video frame of the repetition；Never weigh
The parameter preset information of the target is extracted in this frame of video of duplicate sample；According to the corresponding not repeated sample frame of video of each target,
The identification information of the parameter information of extraction and the wagon flow video monitoring file, each target is generated according to default storage organization
Target information, so as to be effectively retained the valuable information in video file, and effectively reduces video monitoring file
Shared memory space.
Brief description of the drawings
Fig. 1 is a kind of flow chart of video monitoring document handling method in the embodiment of the present invention；
Fig. 2 is the flow chart of contiguous frames duplicate removal processing in the embodiment of the present invention；
Fig. 3 is the schematic diagram of structured storage in the embodiment of the present invention；
Fig. 4 is a kind of structural representation of video monitoring file storage device in the embodiment of the present invention.
Embodiment
In order to solve problem of the prior art, the invention provides a kind of video monitoring document handling method and device, with
Lower combination accompanying drawing and embodiment, the present invention will be described in further detail.It should be appreciated that specific implementation described herein
Example does not limit the present invention only to explain the present invention.
As shown in figure 1, a kind of video monitoring document handling method in the embodiment of the present invention, including：
S101, samples to the data flow of wagon flow video monitoring file according to default sample frequency, obtains multiple samples
This frame of video；
S102, extracts the Sample video frame with goal-selling, and the target includes car and/or people；
S103, according to sampling order, in the Sample video frame of extraction, it is determined that Sample video frame that is neighbouring and repeating,
Reject the Sample video frame of the repetition；
S104, never extracts the parameter preset information of the target in repeated sample frame of video；
S105, according to the corresponding not repeated sample frame of video of each target, the parameter information and the wagon flow video that extract
The identification information of file is monitored, the target information of each target is generated according to default storage organization.
The embodiment of the present invention passes through by extracting the Sample video frame with goal-selling；According to sampling order, extracting
Sample video frame in, it is determined that Sample video frame that is neighbouring and repeating, rejects the Sample video frame of the repetition；Never repeat
The parameter preset information of the target is extracted in Sample video frame；According to the corresponding not repeated sample frame of video of each target, carry
The parameter information and the identification information of the wagon flow video monitoring file taken, the mesh of each target is generated according to default storage organization
Information is marked, so as to be effectively retained the valuable information in video file, and video monitoring file institute is effectively reduced
The memory space of occupancy.
Wherein, when implementing, important valuable information is not lost in order to realize, sample frequency can be set to
High frequency sample rate.High frequency could be arranged to be not less than 0.05 second and no more than 0.2 second, such as 0.1 second using rate.
Principle is as follows：When video file number of pictures per second is more than 24 frame, slack problem would not occur in video.But
It is that for monitoring, 24 frame per second obviously contains the information much repeated, so what kind of sampling frequency to be very using
Bad control, sampling frequency is too high, and the information repeated is more, and the pressure of system processing is bigger；Sampling frequency is too low, can
It can lose some information.
By setting high frequency sample rate in the embodiment of the present invention, so as to not lose data, it will not produce again a large amount of
Junk data.
Furtherly, carried out tentatively for the adjacent sample (i.e. adjacent sample frame of video) got after high frequency sampling
Contrast, if similarity is more than a certain threshold value, is ignored as this part sample.For an extreme example, monitored when midnight
Content may 7,8 hours only store a sample representation all without there is big difference, at this time just can be with.So as to not have
Have on the valuable Information base of loss, reduce the memory space of occupancy.
On the basis of above-described embodiment, it is further proposed that the variant embodiment of above-described embodiment, needs explanation herein
It is, in order that description is brief, the only description and the difference of above-described embodiment in each variant embodiment.
In one embodiment of the invention, it is described according to sampling order, in the Sample video frame of extraction, it is determined that neighbouring
And the Sample video frame repeated, including：
S1031, sets initial Sample video frame, the initial Sample video frame is set into not repeated sample frame of video；
S1032, according to the sampling order, contrasts each sample frame of video similar to the initial Sample video frame successively
Degree；
S1033, when the phase knowledge and magnanimity for contrasting n-th of Sample video frame and the initial Sample video frame are more than or equal in advance
If during threshold value, the Sample video frame between the initial Sample video frame and n-th of Sample video frame is defined as described
Sample video frame that is neighbouring and repeating；Wherein n is the integer more than or equal to 1.
S1034, will be described when (n+1)th random sample this frame of video is not the Sample video frame of last sampling
(n+1)th Sample video frame is set to next initial Sample video frame, then re-executes S1031.
The embodiment of the present invention is by according to sampling order, in the Sample video frame of extraction, it is determined that neighbouring and repetition
The specific implementation of Sample video frame, can effectively remove the useless Sample video frame of heavier repetition, so as to further
The valuable information in video file is effectively retained, and effectively reduces the memory space shared by video monitoring file.
Furtherly, the similarity that each sample frame of video and the initial Sample video frame are contrasted successively, including：
Extract the default sample characteristics of the initial Sample video frame；
Contrast sample's frame of video is treated for any, the default sample characteristics for treating contrast sample's frame of video is extracted；
Using the absolute difference of two default sample characteristics of extraction as the initial Sample video frame and this treat pair
Than the similarity of Sample video frame.
Wherein sample characteristics can use existing mode, and such as sample characteristics can be institute in each Sample video frame
There is the average gray value of all pixels in the gray value sum or each Sample video frame of pixel；Therefore do not make herein
It is specific to limit.
With reference to accompanying drawing 2, the embodiment of the present invention is sketched.
As shown in Fig. 2 the 1st step：Pending video file is read from storage medium.
2nd step：Video file is read, video flowing is converted to, then by video stream to " fixed frequency sampling " unit
Sampled.
3rd step：Sampled according to certain frequency, for this application, sample frequency is 0.1 second.
4th step：The result cache of sampling is got up, for follow-up processing.
6th step：After sampling terminates, " processing of frame duplicate removal " unit is notified to carry out duplicate removal processing.
7th step：" processing of frame duplicate removal " unit reads fixed sample result from caching and analyzed.
9th step：Pre-processed for crude sampling result, remove noise and impurity
10th step：A long type " sample code " (i.e. sample characteristics) is calculated for each sample.
11st step：" sample code " is more similar closer to explanation sample, sets a sampling standard, and sample difference is more than this
Threshold value can be just retained.
11st step：Analysis result is saved in structure storage element.
In yet another embodiment of the present invention, when the target is vehicle, the target information includes target correspondence
Not repeated sample frame of video information, the identification information of the wagon flow video monitoring file, license board information and the car plate
The temporal information for occurring and/or disappearing in the wagon flow video monitoring file；
When the target is behaved, the target information includes the information of the corresponding not repeated sample frame of video of target, institute
Identification information, face information and the face for stating wagon flow video monitoring file occur in the wagon flow video monitoring file
And/or the temporal information disappeared.
The embodiment of the present invention monitors the multi-dimensional object information in file by structured storage, so as to according to these
Target information, is that each target is produced for analyzing the data sheet of the target characteristics of motion, so as to realize the embodiment of the present invention
The video information of middle structured storage is applied in traffic, and in each scene such as safety check, reliable foundation is provided for policymaker.
And this structured storage establishes video file to wagon flow, the stream of people, maximum to the mapping relations of primitive information
The content information of the reservation video of limit, but need seldom memory capacity.So as to further be effectively retained video text
Valuable information in part, and effectively reduce the memory space shared by video monitoring file.
In the embodiment of the present invention at least there is following advantage in structured storage：
A. the disk storage space of video file is greatlyd save after being preserved using structured way, can be preserved more
More long information of many, time.
B. using after structured storage, although the memory space of occupancy greatly reduces, but the major part of reduction is weight
Multiple redundancy, effective information is preserved well.
C. use after structured storage, more facilitate the quick-searching of information, such as can be according to a certain people or car
The feature of board carries out the search in full storehouse.
In embodiments of the present invention, the information of the corresponding not repeated sample frame of video of target can be not repeated sample video
The primitive information (can be image data or frame data) of frame or the not sample characteristics of repeated sample frame of video.
The identification information of the wagon flow video monitoring file can be that wagon flow video monitoring file (can be referred to as in the present invention
For monitoring file or video file) video file coding.
Certainly serial number, such as serial number can be set to each target in embodiments of the present invention.
If the information of the corresponding not repeated sample frame of video of target is the sample characteristics of not repeated sample frame of video, this hair
Bright embodiment can also include：
Store the primitive information of not repeated sample frame of video；
Set up the corresponding relation of the not sample characteristics of repeated sample frame of video and the primitive information.
Furtherly, according to the corresponding not repeated sample frame of video of each target, the parameter information and the car that extract
The identification information of stream video monitoring file is generated according to default storage organization after the target information of each target, and methods described is also
Including：
Store the target information of each target；
Receive search information；
The search target corresponding with the search information from the target information of each target of storage；
The information of not repeated sample frame of video according to corresponding to the target searched, exports the not repeated sample of the target
Frame of video.
Wherein, the acquisition modes of the data flow of wagon flow video monitoring file, including：
Read wagon flow video monitoring file；
It is data flow by the video monitoring file translations；
It is that vehicle and people illustrate the embodiment of the present invention using target.
As shown in figure 3, " video file "：The source information of video file is recorded, in order to (wait to locate with original video files
Manage video file) correspondence.
" information of vehicles "：It has recorded the information of vehicle in some video file.
" face information (also referred to as facial information) "：It has recorded the information of the people occurred in video file.
" primitive information "：It has recorded the information of least unit image, such as the vehicle of some license plate number, or a certain spy
Levy " face " of code.
Present invention further propose that a kind of video monitoring document handling apparatus, including：
Sampling module 110, for being sampled according to default sample frequency to video monitoring stream, obtains multiple samples and regards
Frequency frame；
Object extraction module 120, for extract with goal-selling Sample video frame, the target include car and/or
People；
Deduplication module 130, for according to sampling order, in the Sample video frame of extraction, it is determined that neighbouring and repetition
Sample video frame；
Parameter extraction module 140, the parameter preset information for extracting the target in never repeated sample frame of video；
Generation module 150, for according to the corresponding not repeated sample frame of video of each target, the parameter information extracted and institute
The identification information of wagon flow video monitoring file is stated, the target information of each target is generated according to default storage organization.
The embodiment of the present invention passes through by extracting the Sample video frame with goal-selling；According to sampling order, extracting
Sample video frame in, it is determined that Sample video frame that is neighbouring and repeating, rejects the Sample video frame of the repetition；Never repeat
The parameter preset information of the target is extracted in Sample video frame；According to the corresponding not repeated sample frame of video of each target, carry
The parameter information and the identification information of the wagon flow video monitoring file taken, the mesh of each target is generated according to default storage organization
Information is marked, so as to be effectively retained the valuable information in video file, and video monitoring file institute is effectively reduced
The memory space of occupancy.
In one embodiment of the invention, the deduplication module 130, will specifically for setting initial Sample video frame
The initial Sample video frame is set to not repeated sample frame of video；
According to the sampling order, the similarity of each sample frame of video and the initial Sample video frame is contrasted successively；
When the phase knowledge and magnanimity for contrasting n-th of Sample video frame and the initial Sample video frame are more than or equal to predetermined threshold value
When, the Sample video frame between the initial Sample video frame and n-th of Sample video frame is defined as described adjacent to simultaneously
And the Sample video frame repeated；Wherein n is the integer more than or equal to 1.
Furtherly, the similarity that each sample frame of video and the initial Sample video frame are contrasted successively, including：
Extract the default sample characteristics of the initial Sample video frame；
Contrast sample's frame of video is treated for any, the default sample characteristics for treating contrast sample's frame of video is extracted；
Using the absolute difference of two default sample characteristics of extraction as the initial Sample video frame and this treat pair
Than the similarity of Sample video frame.
In another embodiment of the present invention, when the target is vehicle, the target information includes target correspondence
Not repeated sample frame of video information, the identification information of the wagon flow video monitoring file, license board information and the car plate
The temporal information for occurring and/or disappearing in the wagon flow video monitoring file；
When the target is behaved, the target information includes the information of the corresponding not repeated sample frame of video of target, institute
Identification information, face information and the face for stating wagon flow video monitoring file occur in the wagon flow video monitoring file
And/or the temporal information disappeared.
Furtherly, described device also includes read module；
The read module, the target information for storing each target；
Receive search information；
Target information search target corresponding with the search information from each target of storage；
The information of not repeated sample frame of video according to corresponding to the target searched, exports the not repeated sample of the target
Frame of video.
The embodiment of the present invention monitors the multi-dimensional object information in file by structured storage, so as to according to these
Target information, is that each target is produced for analyzing the data sheet of the target characteristics of motion, so as to realize the embodiment of the present invention
The video information of middle structured storage is applied in traffic, and in each scene such as safety check, reliable foundation is provided for policymaker.
And this structured storage establishes video file to wagon flow, the stream of people, maximum to the mapping relations of primitive information
The content information of the reservation video of limit, but need seldom memory capacity.So as to further be effectively retained video text
Valuable information in part, and effectively reduce the memory space shared by video monitoring file.
In the embodiment of the present invention at least there is following advantage in structured storage：
A. the disk storage space of video file is greatlyd save after being preserved using structured way, can be preserved more
More long information of many, time.
B. using after structured storage, although the memory space of occupancy greatly reduces, but the major part of reduction is weight
Multiple redundancy, effective information is preserved well.
C. use after structured storage, more facilitate the quick-searching of information, such as can be according to a certain people or car
The feature of board carries out the search in full storehouse.
The method described with reference to example disclosed herein, can be embodied directly in hardware, the software mould by computing device
Block or the two combination.For example, the one of one or more of functional block diagram functional block diagram shown in accompanying drawing and/or functional block diagram
Individual and/or multiple combinations, both can correspond to each software module of computer program flow, can also correspond to each hardware
Module.These software modules, can correspond respectively to each step shown in accompanying drawing.These hardware modules are for example using existing
These software modules are solidified and realized by field programmable gate array (FPGA).
Software module can be located at RAM memory, flash memory, ROM memory, eprom memory, eeprom memory, post
Storage, hard disk, mobile hard disk, the storage medium of CD-ROM or any other form known in the art.One kind can be deposited
Storage media lotus root is connected to processor, so as to enable a processor to from the read information, and can be write to the storage medium
Information；Or the storage medium can be the part of processor.Processor and storage medium can be located at special integrated electricity
Lu Zhong.The software module can be stored in a memory in the mobile terminal, can also be stored in the storage of pluggable mobile terminal
In card.If for example, mobile terminal uses the MEGA-SIM cards of larger capacity or the flash memory device of Large Copacity, the software
Module is storable in the flash memory device of the MEGA-SIM cards or Large Copacity.
For one or more combinations of one or more of functional block diagram described in accompanying drawing and/or functional block diagram,
It can be implemented as the general processor, digital signal processor (DSP), special integrated electricity for performing function described herein
Road (ASIC), field programmable gate array (FPGA) or other PLDs, discrete gate or transistor logic,
Discrete hardware components or it is any appropriately combined.For one or more of functional block diagram described in accompanying drawing and/or work(
One or more combinations of energy block diagram, are also implemented as the combination of computer equipment, for example, the combination of DSP and microprocessor,
Multi-microprocessor, communicate with DSP the one or more microprocessors combined or any other this configuration.
Although This application describes the particular example of the present invention, those skilled in the art can not depart from the present invention generally
Variant of the invention is designed on the basis of thought.
Those skilled in the art are under the inspiration that the technology of the present invention is conceived, on the basis of present invention is not departed from, also
Various improvement can be made to the present invention, this still falls within the scope and spirit of the invention.
Claims (10)
1. a kind of video monitoring document handling method, it is characterised in that methods described includes：
The data flow of wagon flow video monitoring file is sampled according to default sample frequency, multiple Sample video frames are obtained；
The Sample video frame with goal-selling is extracted, the target includes car and/or people；
According to sampling order, in the Sample video frame of extraction, it is determined that Sample video frame that is neighbouring and repeating, is rejected described heavy
Multiple Sample video frame；
The parameter preset information of the target is never extracted in repeated sample frame of video；
According to the corresponding not repeated sample frame of video of each target, the parameter information extracted and the wagon flow video monitoring file
Identification information, the target information of each target is generated according to default storage organization.
2. the method as described in claim 1, it is characterised in that described according to sampling order, in the Sample video frame of extraction,
It is determined that Sample video frame that is neighbouring and repeating, including：
Initial Sample video frame is set, the initial Sample video frame is set to not repeated sample frame of video；
According to the sampling order, the similarity of each sample frame of video and the initial Sample video frame is contrasted successively；
When the phase knowledge and magnanimity for contrasting n-th of Sample video frame and the initial Sample video frame are more than or equal to predetermined threshold value,
By the Sample video frame between the initial Sample video frame and n-th of Sample video frame, be defined as it is described neighbouring and
The Sample video frame repeated；Wherein n is the integer more than or equal to 1.
3. method as claimed in claim 2, it is characterised in that described to contrast each sample frame of video and the initial sample successively
The similarity of frame of video, including：
Extract the default sample characteristics of the initial Sample video frame；
Contrast sample's frame of video is treated for any, the default sample characteristics for treating contrast sample's frame of video is extracted；
The absolute difference of two default sample characteristics of extraction is treated into control sample as the initial Sample video frame with this
The similarity of this frame of video.
4. the method as described in any one in claim 1-3, it is characterised in that when the target is vehicle, the mesh
Marking information includes the information of the corresponding not repeated sample frame of video of target, identification information, the car of the wagon flow video monitoring file
The temporal information that board information and the car plate occur and/or disappeared in the wagon flow video monitoring file；
When the target is behaved, the target information includes the information of the corresponding not repeated sample frame of video of target, the car
Stream video monitoring file identification information, face information and the face occur in the wagon flow video monitoring file and/
Or the temporal information disappeared.
5. method as claimed in claim 4, it is characterised in that according to the corresponding not repeated sample frame of video of each target,
The identification information of the parameter information of extraction and the wagon flow video monitoring file generates each target according to default storage organization
After target information, methods described also includes：
Store the target information of each target；
Receive search information；
The search target corresponding with the search information from the target information of each target of storage；
The information of not repeated sample frame of video according to corresponding to the target searched, exports the not repeated sample video of the target
Frame.
6. a kind of video monitoring document handling apparatus, it is characterised in that described device includes：
Sampling module, for being sampled according to default sample frequency to video monitoring stream, obtains multiple Sample video frames；
Object extraction module, for extracting the Sample video frame with goal-selling, the target includes car and/or people；
Deduplication module, for according to sampling order, in the Sample video frame of extraction, it is determined that Sample video that is neighbouring and repeating
Frame；
Parameter extraction module, the parameter preset information for extracting the target in never repeated sample frame of video；
Generation module, for according to the corresponding not repeated sample frame of video of each target, the parameter information extracted and the wagon flow
The identification information of video monitoring file, the target information of each target is generated according to default storage organization.
7. device as claimed in claim 6, it is characterised in that the deduplication module, specifically for setting initial Sample video
Frame, not repeated sample frame of video is set to by the initial Sample video frame；
According to the sampling order, the similarity of each sample frame of video and the initial Sample video frame is contrasted successively；
When the phase knowledge and magnanimity for contrasting n-th of Sample video frame and the initial Sample video frame are more than or equal to predetermined threshold value,
Sample video frame between the initial Sample video frame and n-th of Sample video frame is defined as described neighbouring and again
Multiple Sample video frame；Wherein n is the integer more than or equal to 1.
8. device as claimed in claim 7, it is characterised in that described to contrast each sample frame of video and the initial sample successively
The similarity of frame of video, including：
Extract the default sample characteristics of the initial Sample video frame；
Contrast sample's frame of video is treated for any, the default sample characteristics for treating contrast sample's frame of video is extracted；
The absolute difference of two default sample characteristics of extraction is treated into control sample as the initial Sample video frame with this
The similarity of this frame of video.
9. the device as described in any one in claim 6-8, it is characterised in that when the target is vehicle, the mesh
Marking information includes the information of the corresponding not repeated sample frame of video of target, identification information, the car of the wagon flow video monitoring file
The temporal information that board information and the car plate occur and/or disappeared in the wagon flow video monitoring file；
When the target is behaved, the target information includes the information of the corresponding not repeated sample frame of video of target, the car
Stream video monitoring file identification information, face information and the face occur in the wagon flow video monitoring file and/
Or the temporal information disappeared.
10. device as claimed in claim 9, it is characterised in that described device also includes read module；
The read module, the target information for storing each target；
Receive search information；
Target information search target corresponding with the search information from each target of storage；
The information of not repeated sample frame of video according to corresponding to the target searched, exports the not repeated sample video of the target
Frame.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710152804.7A CN107016061A (en) | 2017-03-15 | 2017-03-15 | Video monitoring document handling method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710152804.7A CN107016061A (en) | 2017-03-15 | 2017-03-15 | Video monitoring document handling method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107016061A true CN107016061A (en) | 2017-08-04 |
Family
ID=59440583
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710152804.7A Pending CN107016061A (en) | 2017-03-15 | 2017-03-15 | Video monitoring document handling method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107016061A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110135517A (en) * | 2019-05-24 | 2019-08-16 | 北京百度网讯科技有限公司 | For obtaining the method and device of vehicle similarity |
| CN110516651A (en) * | 2019-09-02 | 2019-11-29 | 卓尔智联(武汉)研究院有限公司 | A kind of video data handling procedure, device and storage medium |
| CN110969093A (en) * | 2019-11-05 | 2020-04-07 | 武汉菲旺软件技术有限责任公司 | District security protection video evidence obtaining method, device, equipment and medium based on block chain |
| CN111601108A (en) * | 2020-05-26 | 2020-08-28 | 李云祥 | Monitoring video processing method and device and video monitoring terminal |
| CN112422772A (en) * | 2020-10-23 | 2021-02-26 | 深圳市优必选科技股份有限公司 | Image acquisition method, image acquisition device, terminal device and readable storage medium |
| CN112995558A (en) * | 2019-12-17 | 2021-06-18 | Tcl新技术（惠州）有限公司 | Video file storage method and device and storage medium |
| CN114339299A (en) * | 2021-12-27 | 2022-04-12 | 司法鉴定科学研究院 | Video evidence obtaining method for automobile driving recorder |
| CN115190329A (en) * | 2022-06-29 | 2022-10-14 | 杭州拓深科技有限公司 | Plug flow optimization method of data sample filtering comparison method for real-time video stream |
| WO2023109284A1 (en) * | 2021-12-17 | 2023-06-22 | 深圳Tcl新技术有限公司 | Video preview method and apparatus, and electronic device and computer-readable storage medium |
| CN116916049A (en) * | 2023-09-12 | 2023-10-20 | 北京青水环境科技有限公司 | Video data online acquisition and storage system based on cloud computing technology |
| CN119135851A (en) * | 2024-11-14 | 2024-12-13 | 苏州元脑智能科技有限公司 | Surveillance video log recording method, device, medium and computer program product |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101252686A (en) * | 2008-03-20 | 2008-08-27 | 上海交通大学 | Method and system for lossless encoding and decoding in video frames based on interleaved prediction |
| US20140108615A1 (en) * | 2012-10-16 | 2014-04-17 | Norifumi Takaya | Method and apparatus for managing a catalog of media content |
| CN104093021A (en) * | 2014-07-15 | 2014-10-08 | 上海工程技术大学 | A surveillance video compression method |
| CN104853161A (en) * | 2015-05-11 | 2015-08-19 | 董宜平 | Video surveillance system of trajectory |
| CN106448160A (en) * | 2016-09-22 | 2017-02-22 | 江苏理工学院 | Target person tracking method combining vehicle running track and monitoring video data |
-
2017
- 2017-03-15 CN CN201710152804.7A patent/CN107016061A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101252686A (en) * | 2008-03-20 | 2008-08-27 | 上海交通大学 | Method and system for lossless encoding and decoding in video frames based on interleaved prediction |
| US20140108615A1 (en) * | 2012-10-16 | 2014-04-17 | Norifumi Takaya | Method and apparatus for managing a catalog of media content |
| CN104093021A (en) * | 2014-07-15 | 2014-10-08 | 上海工程技术大学 | A surveillance video compression method |
| CN104853161A (en) * | 2015-05-11 | 2015-08-19 | 董宜平 | Video surveillance system of trajectory |
| CN106448160A (en) * | 2016-09-22 | 2017-02-22 | 江苏理工学院 | Target person tracking method combining vehicle running track and monitoring video data |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110135517A (en) * | 2019-05-24 | 2019-08-16 | 北京百度网讯科技有限公司 | For obtaining the method and device of vehicle similarity |
| CN110516651A (en) * | 2019-09-02 | 2019-11-29 | 卓尔智联(武汉)研究院有限公司 | A kind of video data handling procedure, device and storage medium |
| CN110969093A (en) * | 2019-11-05 | 2020-04-07 | 武汉菲旺软件技术有限责任公司 | District security protection video evidence obtaining method, device, equipment and medium based on block chain |
| CN110969093B (en) * | 2019-11-05 | 2024-02-13 | 武汉菲旺软件技术有限责任公司 | Block chain-based community security video evidence obtaining method, device, equipment and medium |
| CN112995558A (en) * | 2019-12-17 | 2021-06-18 | Tcl新技术（惠州）有限公司 | Video file storage method and device and storage medium |
| CN111601108A (en) * | 2020-05-26 | 2020-08-28 | 李云祥 | Monitoring video processing method and device and video monitoring terminal |
| CN112422772B (en) * | 2020-10-23 | 2023-12-01 | 深圳市优必选科技股份有限公司 | Image acquisition method, image acquisition device, terminal device and readable storage medium |
| CN112422772A (en) * | 2020-10-23 | 2021-02-26 | 深圳市优必选科技股份有限公司 | Image acquisition method, image acquisition device, terminal device and readable storage medium |
| WO2023109284A1 (en) * | 2021-12-17 | 2023-06-22 | 深圳Tcl新技术有限公司 | Video preview method and apparatus, and electronic device and computer-readable storage medium |
| CN114339299A (en) * | 2021-12-27 | 2022-04-12 | 司法鉴定科学研究院 | Video evidence obtaining method for automobile driving recorder |
| CN115190329A (en) * | 2022-06-29 | 2022-10-14 | 杭州拓深科技有限公司 | Plug flow optimization method of data sample filtering comparison method for real-time video stream |
| CN116916049A (en) * | 2023-09-12 | 2023-10-20 | 北京青水环境科技有限公司 | Video data online acquisition and storage system based on cloud computing technology |
| CN116916049B (en) * | 2023-09-12 | 2023-12-08 | 北京青水环境科技有限公司 | Video data online acquisition and storage system based on cloud computing technology |
| CN119135851A (en) * | 2024-11-14 | 2024-12-13 | 苏州元脑智能科技有限公司 | Surveillance video log recording method, device, medium and computer program product |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107016061A (en) | Video monitoring document handling method and device | |
| CN109697424A (en) | A kind of high-speed railway impurity intrusion detection device and method based on FPGA and deep learning | |
| CN111898416A (en) | Video stream processing method and device, computer equipment and storage medium | |
| CN106534344A (en) | Cloud platform video processing system and application method thereof | |
| CN112819000A (en) | Streetscape image semantic segmentation system, streetscape image semantic segmentation method, electronic equipment and computer readable medium | |
| CN101059838A (en) | Human face recognition system and recognition method | |
| CN111523527B (en) | Special transport vehicle monitoring method and device, medium and electronic equipment | |
| CN102411677A (en) | Pre-processing method for data collection based on floating car | |
| CN110110325A (en) | It is a kind of to repeat case lookup method and device, computer readable storage medium | |
| CN103049263A (en) | Document classification method based on similarity | |
| CN115223228A (en) | Face key point detection method based on mixed domain attention mechanism | |
| CN106708876B (en) | Similar video retrieval method and system based on Lucene | |
| CN108921147A (en) | A kind of black smoke vehicle recognition methods based on dynamic texture and transform domain space-time characteristic | |
| CN115114805B (en) | Information interaction pair discrete simulation method of autonomous traffic system architecture | |
| CN113609952B (en) | Depth fake video frequency domain detection method based on dense convolutional neural network | |
| CN112948639B (en) | Unified storage management method and system for data of highway middling station | |
| CN105072444A (en) | A HEVC video secondary compression detection method under different quantization parameters | |
| CN106934041A (en) | image file management method and device | |
| CN114710474A (en) | Data stream processing and classifying method based on Internet of things | |
| CN109002863B (en) | Image processing method based on compact convolutional neural network | |
| CN108062395A (en) | A kind of track traffic big data analysis method and system | |
| CN114187550A (en) | An identification method of pantograph-catenary core components based on improved YOLO V3 network | |
| CN114267084A (en) | Video recognition method, device, electronic device and storage medium | |
| CN116561372B (en) | Personnel gear gathering method and device based on multiple algorithm engines and readable storage medium | |
| CN117412115A (en) | Video processing method and device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170804 |
|
| RJ01 | Rejection of invention patent application after publication |