CN110390262A - Video analysis method, apparatus, server and storage medium - Google Patents
Video analysis method, apparatus, server and storage medium Download PDFInfo
- Publication number
- CN110390262A CN110390262A CN201910517477.XA CN201910517477A CN110390262A CN 110390262 A CN110390262 A CN 110390262A CN 201910517477 A CN201910517477 A CN 201910517477A CN 110390262 A CN110390262 A CN 110390262A
- Authority
- CN
- China
- Prior art keywords
- target object
- video
- video image
- image
- business scenario
- 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.)
- Granted
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 74
- 238000003860 storage Methods 0.000 title claims abstract description 21
- 230000002159 abnormal effect Effects 0.000 claims abstract description 86
- 238000001514 detection method Methods 0.000 claims description 63
- 238000000034 method Methods 0.000 claims description 40
- 230000015654 memory Effects 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 12
- 230000002547 anomalous effect Effects 0.000 abstract description 4
- 230000006870 function Effects 0.000 description 20
- 238000012544 monitoring process Methods 0.000 description 11
- 238000013527 convolutional neural network Methods 0.000 description 10
- 238000010801 machine learning Methods 0.000 description 10
- 230000003068 static effect Effects 0.000 description 10
- 238000012360 testing method Methods 0.000 description 7
- 238000013528 artificial neural network Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 206010039203 Road traffic accident Diseases 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 241000406668 Loxodonta cyclotis Species 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 230000007423 decrease Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 241001465754 Metazoa Species 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000005206 flow analysis Methods 0.000 description 2
- 230000000116 mitigating effect Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs
- H04N21/44008—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Library & Information Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Image Analysis (AREA)
Abstract
A kind of video analysis method, comprising: receive the video image of camera acquisition;It detects the target object in the video image and obtains the classification of the target object;It tracks the target object in the video image and obtains the state of the target object;The business scenario for including in the video image is obtained according to the state analysis of the classification of the target object and the target object;Judge whether the business scenario exception occurs;And when the business scenario in the video image occurs abnormal, the key message when business scenario occurs abnormal is recorded.The present invention also provides a kind of video analysis device, server and storage mediums.Occurs key message when anomalous event in available video image, through the invention to handle the anomalous event in time.
Description
Technical field
The present invention relates to image identification technical fields, and in particular to a kind of video analysis method, apparatus, server and storage
Medium.
Background technique
With the continuous development of Video Supervision Technique, the current video monitoring in China is in smart city, digital city, wisdom garden
Each intermediate items such as area, intelligent transportation, ferry monitoring are widely applied.Internet of Things is the basis of smart city, and video monitoring will
It is core.However, needing user to replay monitor video when analyzing the monitor video, checking one by one
Video image, to search the anomalous event in video image.It needs to take a significant amount of time and manpower.
Summary of the invention
In view of the foregoing, it is necessary to propose a kind of video analysis method, apparatus, server and storage medium, Neng Gouji
When obtain key message when there is anomalous event in video image.
The first aspect of the present invention provides a kind of video analysis method, which comprises
Receive the video image of camera acquisition;
It detects the target object in the video image and obtains the classification of the target object;
It tracks the target object in the video image and obtains the state of the target object;
Obtained according to the state analysis of the classification of the target object and the target object include in the video image
Business scenario;
Judge whether the business scenario exception occurs;And
When the business scenario in the video image occurs abnormal, the key when business scenario occurs abnormal is recorded
Information.
Preferably, the target object in the detection video image obtains the classification of the target object and includes:
By decomposing the target object in the video image, the basic category of the target object in the video image is obtained
Property;
The essential attribute that will acquire is compared with the essential attribute that target object in the database is stored in advance;
When the essential attribute of acquisition is consistent with the essential attribute of target object in the database, data are inquired
The essential attribute stored in library table corresponding with target object classification is to obtain the classification of the target object.
Preferably, the target object in the tracking video image obtains the state of the target object and includes:
Determine the target object in current video frame;
Obtain the characteristics of image of image-region and described image region of the target object in preamble video frame, wherein
The preamble video frame is k video frame before current video frame, and k is positive integer;
According to image-region of the target object in preamble video frame, estimation is carried out to the target object,
Determine the target object in the estimation range of current video frame;
Detection range of the target object in current video frame is determined according to the estimation range;
Judge whether the target object appears in the detection range in current video frame;
If the target object appears in the detection range in current video frame, determine the target object in current video
Image-region in frame;
If the target object does not appear in the detection range in current video frame, determine that the target object is abnormal.
Preferably, described to judge whether the business scenario exception occurs and include:
When determining the target object exception, the current video frame is extracted as abnormal image;
It is imported the abnormal image as images to be recognized in trained Exception Model in advance, wherein the exception
Model is used to characterize the corresponding relationship between images to be recognized and abnormal scene;
When Exception Model output abnormal scene corresponding with the images to be recognized, confirm that the business scenario goes out
It is now abnormal.
Preferably, the key message includes the view that abnormal time, place and interception occurs in the business scenario
Picture file when business scenario described in frequency image occurs abnormal.
Preferably, the key message includes the view that abnormal time, place and interception occurs in the business scenario
Picture file when business scenario described in frequency image occurs abnormal.
Preferably, the method also includes:
The key message of record is sent to third party's business platform, wherein third party's business platform includes public security system
System and traffic control system.
Preferably, after the video image for receiving camera acquisition, the method also includes:
The video image is decoded.
The second aspect of the present invention provides a kind of video analysis device, and described device includes:
Receiving module, for receiving the video image of camera acquisition;
Detection module obtains the classification of the target object for detecting the target object in the video image;
Tracking module obtains the state of the target object for tracking the target object in the video image;
Analysis module, for obtaining the view according to the classification of the target object and the state analysis of the target object
The business scenario for including in frequency image;
Judgment module, for judging whether the business scenario exception occurs;And
Processing module, for recording the business scenario and going out when the business scenario in the video image occurs abnormal
Key message when now abnormal.
The third aspect of the present invention provides a kind of server, and the server includes processor and memory, the processing
Device is for realizing the video analysis method when executing the computer program stored in the memory.
The fourth aspect of the present invention provides a kind of computer readable storage medium, deposits on the computer readable storage medium
Computer program is contained, the computer program realizes the video analysis method when being executed by processor.
Video analysis method, apparatus, system and storage medium of the present invention, can analyze video image obtain it is described
The business scenario that video image is included, and judge whether the business scenario exception occurs, when business scenario appearance is different
Chang Shi records the key message when business scenario occurs abnormal.It is corresponding so as to which the key message to be sent to
Third-party platform, to handle the exception in time.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The embodiment of invention for those of ordinary skill in the art without creative efforts, can also basis
The attached drawing of offer obtains other attached drawings.
Fig. 1 is the flow chart for the video analysis method that the embodiment of the present invention one provides.
Fig. 2 is the functional block diagram in video analysis device preferred embodiment of the present invention provided by Embodiment 2 of the present invention.
Fig. 3 is the schematic diagram for the server that the embodiment of the present invention three provides.
The present invention that the following detailed description will be further explained with reference to the above drawings.
Specific embodiment
To better understand the objects, features and advantages of the present invention, with reference to the accompanying drawing and specific real
Applying example, the present invention will be described in detail.It should be noted that in the absence of conflict, the embodiment of the present invention and embodiment
In feature can be combined with each other.
In the following description, numerous specific details are set forth in order to facilitate a full understanding of the present invention, described embodiment is only
It is only a part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill
Personnel's every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
Unless otherwise defined, all technical and scientific terms used herein and belong to technical field of the invention
The normally understood meaning of technical staff is identical.Term as used herein in the specification of the present invention is intended merely to description tool
The purpose of the embodiment of body, it is not intended that in the limitation present invention.
Description and claims of this specification and term " first " in above-mentioned attached drawing, " second " and " third " etc. are
For distinguishing different objects, not for description particular order.In addition, term " includes " and their any deformations, it is intended that
Non-exclusive include in covering.Such as the process, method, system, product or equipment for containing a series of steps or units do not have
It is defined in listed step or unit, but optionally further comprising the step of not listing or unit, or optionally further comprising
For the intrinsic other step or units of these process, methods, product or equipment.
The video analysis method of the embodiment of the present invention is applied by least one server and by network and the service
In the hardware environment that the mobile terminal that device is attached is constituted.Network includes but is not limited to: wide area network, Metropolitan Area Network (MAN) or local
Net.The video analysis method of the embodiment of the present invention can be executed by server, can also be executed by mobile terminal;It can be with
It is to be executed jointly by server and mobile terminal.
The server for needing to carry out video analysis method, can directly integrate side of the invention on the server
Video analysis function provided by method, or installation is for realizing the client of method of the invention.For another example, provided by the present invention
Method server can also be operated in the form of Software Development Kit (Software Development Kit, SDK)
Etc. in equipment, the interface of video analysis function, server or other equipment are provided in the form of SDK, the interface that provides are provided
Realize video analysis function.
Embodiment one
Fig. 1 is the flow chart for the video analysis method that the embodiment of the present invention one provides.The flow chart according to different requirements,
In execution sequence can change, certain steps can be omitted.
Step S1 receives the video image of camera acquisition.
In the present embodiment, video image is acquired by camera, the camera is installed in different business fields
Jing Zhong.The business scenario describes the scene for needing to carry out target object detecting and/or video analysis.For example, the industry
Scene of being engaged in be identification traffic accident, congestion, Bus- Speed Monitoring, wagon flow prediction, to lose control of one's vehicle, vehicle driving trace, personnel or voluntarily
Vehicle swarms into, traffic violation, the intelligent transportation business scenario for shedding object etc., and the business scenario can also be that identification personnel enter
Invade, the monitoring of residue, lost-and-found object, license plate analysis, vehicle driving trace, train flow analysis, stream of people's analysis, pyrotechnics or smog etc. intelligence
Intelligent garden business scenario, the business scenario can also be illegal ship, overload, dense population detection, whether wear life jacket, fall
The ferry of water etc. monitors business scenario.
The business scenario can also be unmanned, financial scenario, equipment log in, airport and the monitoring of public domain etc.
Scene.
In the present embodiment, the camera can be the camera of the different model specification of different vendor's factory, institute
Stating video analysis method may be implemented the camera shooting for being uniformly processed and analyzing the different model specification of different vendor's factory
Video image.
Preferably, after the video image for receiving camera acquisition, the video analysis method further include:
The step of video image is decoded.
Specifically, video decoding can be carried out to the video image by graphics processor (GPU), to obtain the view
Every frame image in frequency image.
Step S2 detects the target object in the video image and obtains the classification of the target object.
In the present embodiment, the target object in the video image include personage, animal, the vehicles, building,
Smog etc..
Specifically, the target object in the detection video image obtains the classification of the target object and includes:
(1) target object in the video image is identified;
In the present embodiment, the target object in the video image includes static target object and moving target pair
As.
When the target object in the video image is static target object, the detection method based on template can be passed through
To identify the static target object.It specifically includes: determining the profile of the target object shape in the video image, it will be described
The profile of target object shape carries out characteristic matching with the template file prestored.
For example, can determine the wheel of the target object shape when the target object in the video image is Yishanmen
Exterior feature is a rectangle, and the template file of the rectangle and the door prestored is carried out characteristic matching to identify the target object.Wherein,
The template file of the door is rectangle.
When the target object in the video image is moving target object, Background difference, frame difference method, light can be passed through
At least one of stream method is identified.The Background difference is to carry out background to scene comparatively fixed in video image
Modeling obtains the moving target object by the difference of present image and background model when detection;The frame difference method is by view
Corresponding position pixel is compared to obtain the position of moving target object between consecutive frame in frequency sequence;The optical flow method is
Using the light stream vector characteristic of time change, the moving target object in the video image is detected.
It is understood that the method for static target object and moving target object in above-mentioned detection video image is unlimited
It is enumerated in above-mentioned, any method of putting for being adapted to detect the target object in video image can be applied to this.In addition, this reality
The method for applying static target object and moving target object in the detection video image in example is the prior art, herein
It is no longer discussed in detail herein.
(2) classification of the target object is determined.
For example, can determine the class of the target object when identifying the target object in the video image is automobile
It Wei not the vehicles.As soon as the detection and classification of the target object are a very basic task, purpose in vision technique
It is interested some objects in tracking scene, including conventional target object detection, personnel's detection and vehicle detection etc..
In the present embodiment, the video image can be obtained by decomposing the target object in the video image
In target object essential attribute, wherein the essential attribute includes color, motion profile, shape, structure etc., then in institute
The essential attribute for stating acquisition is compared with the essential attribute that target object in the database is stored in advance, to accurately know
It Chu not target object in the video image.The essential attribute and target object class of target object are stored in the database
Table is not corresponded to.
The classification of the determination target object specifically includes: by decomposing the target object in the video image,
Obtain the essential attribute of the target object in the video image;The essential attribute that will acquire and it is stored in advance in database
In the essential attribute of target object be compared;When the target object in the essential attribute of acquisition and the database
When essential attribute is consistent, the essential attribute table corresponding with target object classification stored in database is inquired to obtain the target pair
The classification of elephant.
Step S3 tracks the target object in the video image and obtains the state of the target object.
After target object detection is completed, need to calculate its motion profile for the target object each detected,
To realize the target object tracked in the video image.In the present embodiment, by tracking in the video image
Target object can determine the state of the target object.
The method of target object in the tracking video image includes:
A) target object in current video frame is determined.
B) characteristics of image of image-region and described image region of the target object in preamble video frame is obtained,
In, the preamble video frame is k video frame before current video frame, and k is positive integer.
C) image-region according to the target object in preamble video frame carries out movement to the target object and estimates
Meter, determines the target object in the estimation range of current video frame.
D) detection range of the target object in current video frame is determined according to the estimation range.
E) judge whether the target object appears in the detection range in current video frame, if the target object does not have
The detection range in current video frame is appeared in, determines the abnormal state of the target object;If the target object appears in
Detection range in current video frame determines image-region of the target object in current video frame, i.e., the described target pair
The state of elephant is normal.
Refer to k video frame before current video frame due to preamble video frame, by this preceding k video frame come to current
Video frame is estimated and contrasting detection, and calculation amount is smaller, and is able to solve target object in video and loses or hide once in a while
The problem of gear, detection accuracy are higher.
Step S4 obtains the video image according to the state analysis of the classification of the target object and the target object
In include business scenario.
In the present embodiment, the classification that can obtain target object according to testing result, can be true according to tracking result
The state of the fixed target object, so as to analyze to obtain the business scenario for including in the video image.
For example, the classification that can obtain the target object according to testing result is automobile, the automobile is not appeared in
Detection range in current video frame can then determine the abnormal state of the automobile, and such as automobile is in congestion status, then
It can be seen that the business scenario for including in the video image is intelligent transportation business scenario.
The classification that the target object can for another example be obtained according to testing result is pedestrian, and the pedestrian, which does not appear in, to be worked as
Detection range in preceding video frame can then determine the abnormal state of the pedestrian.It is if the pedestrian falls down, then it can be seen that described
The business scenario for including in video image is intelligent transportation business scenario.
The classification that the target object can for another example be obtained according to testing result is door, and the door, which does not appear in, works as forward sight
The abnormal state of the door then can be confirmed in detection range in frequency, and being such as kept open can determine whether in the video image
Including business scenario be intelligent security business scenario.
Step S5, judges whether the business scenario in the video image exception occurs.Industry in the video image
When scene of being engaged in occurs abnormal, S6 is entered step;When the business scenario in the video image does not occur abnormal, terminate stream
Journey.
In the present embodiment, institute can determine whether by the state analysis of the classification of the target object and the target object
State whether the business scenario in video image exception occurs.For example, working as forward sight by judging whether the target object appears in
Detection range in frequency frame determines the target if the target object does not appear in the detection range in current video frame
Also there is exception in the abnormal state of object, i.e., the corresponding business scenario of described target object.
It in other embodiments, can be by the way that the video image be inputted trained Exception Model, and root in advance
Judge whether the business scenario in the video image is abnormal according to the Exception Model.Specifically, when determining the target object
When abnormal, the current video frame is extracted as abnormal image;Instruction in advance is imported using the abnormal image as images to be recognized
In the Exception Model perfected, wherein the Exception Model is used to characterize the corresponding relationship between images to be recognized and abnormal scene;
When Exception Model output abnormal scene corresponding with the images to be recognized, confirm that abnormal institute occurs in the business scenario
Stating Exception Model includes the corresponding Exception Model of different business scenarios.For example, when the business scenario is intelligent transportation business
When scene, the corresponding Exception Model of the intelligent transportation business scenario includes traffic accident model, traffic congestion model and illegal
Violation model etc.;When the business scenario is wisdom garden business scenario, the corresponding exception of wisdom garden business scenario
Model includes that carry-on articles leave model, personnel invade model etc.;When the business scenario is that ferry monitors business scenario, institute
Stating the corresponding Exception Model of ferry monitoring business scenario includes overload model, overboard model, illegal model ship etc..
For example, when traffic congestion occurs in current video frame in the video image, the current video frame is extracted
It is imported in trained traffic congestion model in advance as abnormal image, and using the abnormal image as images to be recognized, when
When the traffic congestion model exports traffic congestion scene corresponding with the images to be recognized, confirm that the video image is corresponding
Intelligent transportation business scenario in occur it is abnormal;When the traffic congestion model do not export it is corresponding with the images to be recognized
When traffic congestion scene, confirm normal in the corresponding intelligent transportation business scenario of the video image.
Above-mentioned Exception Model is the machine learning model according to picture sample collection training.The picture sample includes abnormal industry
Business scene picture sample and regular traffic scene picture sample.The machine learning model is that can carry out the artificial of image recognition
Intelligent algorithm model, comprising: convolutional neural networks MODEL C NN, Recognition with Recurrent Neural Network module RNN and deep neural network model
DNN.Wherein, convolutional neural networks MODEL C NN is a kind of multilayer neural network, problem of image recognition that can be huge by data volume
Continuous dimensionality reduction can be finally trained to, and therefore, the machine learning model in the embodiment of the present application can be CNN model.
In the evolution of CNN network structure, there are many CNN networks, including LeNet, AlexNet, VGGNet,
GoogleNet and ResNet.Wherein, ResNet network proposes a kind of residual error learning framework for mitigating network training burden, this
Kind of network is deeper than the network substantially level being previously used, and solves other neural networks as network is deepened, accuracy rate
The problem of decline.In the present embodiment, the machine learning model can be the ResNet in convolution log on MODEL C NN
Model.It should be noted that be merely illustrative of herein, the machine learning model that other can carry out image recognition is equally applicable
In the application, herein without repeating.
Step S6 records the business scenario and exception occurs when the business scenario in the video image occurs abnormal
When key message.
In the present embodiment, the key message includes that the business scenario abnormal time, place and interception occurs
The video image described in picture file etc. of business scenario when occurring abnormal.
Further, the video analysis method further includes that the key message of record is sent to third party's business platform.
Third party's business platform includes public security system, traffic control system etc..By the way that the key message of the record is sent to
Third party's business platform can help third party's business platform to obtain pass when occurring abnormal in business scenario in time
Key information, to handle the exception in time.
Further, the video analysis method further include: show the key message when business scenario occurs abnormal.
Specifically, shown in the display screen the abnormal picture of the business scenario, the time, point etc. information.
In conclusion video analysis method provided by the invention, the video image including receiving camera acquisition;Detection institute
It states the target object in video image and obtains the classification of the target object;The target object tracked in the video image obtains
The state of the target object;The video is obtained according to the state analysis of the classification of the target object and the target object
The business scenario for including in image;Judge whether the business scenario exception occurs;And when the business field in the video image
When scape occurs abnormal, the key message when business scenario occurs abnormal is recorded.The video image pair can be analyzed in real time
Whether the business scenario answered there is exception, and when confirming that the business scenario occurs abnormal, records the business scenario and occurs
Key message when abnormal.It is described to handle in time so as to which the key message is sent to corresponding third-party platform
It is abnormal.
Embodiment two
Fig. 2 is the functional block diagram in video analysis device preferred embodiment of the present invention.
In some embodiments, the video analysis device 20 is run in server.The video analysis device 20 can
To include multiple functional modules as composed by program code segments.The program of each program segment in the video analysis device 20
Code can store in memory, and as performed by least one processor, with execution (being detailed in Fig. 1 and its associated description) view
Frequency analysis function.
In the present embodiment, function of the video analysis device 20 according to performed by it can be divided into multiple functions
Module.The functional module may include: receiving module 201, detection module 202, tracking module 203, analysis module 204, sentence
Disconnected module 205 and processing module 206.The so-called module of the present invention refer to one kind can performed by least one processor and
The series of computation machine program segment of fixed function can be completed, storage is in memory.In some embodiments, about each mould
The function of block will be described in detail in subsequent embodiment.
The receiving module 201 is used to receive the video image of camera acquisition.
In the present embodiment, video image is acquired by camera, the camera is installed in different business fields
Jing Zhong.The business scenario describes the scene for needing to carry out target object detecting and/or video analysis.For example, the industry
Scene of being engaged in be identification traffic accident, congestion, Bus- Speed Monitoring, wagon flow prediction, to lose control of one's vehicle, vehicle driving trace, personnel or voluntarily
Vehicle swarms into, traffic violation, the intelligent transportation business scenario for shedding object etc., and the business scenario can also be that identification personnel enter
Invade, the monitoring of residue, lost-and-found object, license plate analysis, vehicle driving trace, train flow analysis, stream of people's analysis, pyrotechnics or smog etc. intelligence
Intelligent garden business scenario, the business scenario can also be illegal ship, overload, dense population detection, whether wear life jacket, fall
The ferry of water etc. monitors business scenario.
In the present embodiment, it is communicated to connect between the camera and the server by wired or wireless network.
The video image of acquisition is sent to the server by wired or wireless network by the camera.
The business scenario can also be unmanned, financial scenario, equipment log in, airport and the monitoring of public domain etc.
Scene.
In the present embodiment, the camera can be the camera of the different model specification of different vendor's factory, institute
Stating video analysis method may be implemented the camera shooting for being uniformly processed and analyzing the different model specification of different vendor's factory
Video image.
Preferably, after the video image for receiving camera acquisition, the video analysis device 20 can be with:
The video image is decoded.
Specifically, video decoding can be carried out to the video image by graphics processor (GPU), to obtain the view
Every frame image in frequency image.
The target object that the detection module 202 is used to detect in the video image obtains the class of the target object
Not.
In the present embodiment, the target object in the video image include personage, animal, the vehicles, building,
Smog etc..
Specifically, the target object in the detection video image obtains the classification of the target object and includes:
(1) target object in the video image is identified;
In the present embodiment, the target object in the video image includes static target object and moving target pair
As.
When the target object in the video image is static target object, the detection method based on template can be passed through
To identify the static target object.It specifically includes: determining the profile of the target object shape in the video image, it will be described
The profile of target object shape carries out characteristic matching with the template file prestored.
When the target object in the video image is moving target object, Background difference, frame difference method, light can be passed through
At least one of stream method is identified.The Background difference is to carry out background to scene comparatively fixed in video image
Modeling obtains the moving target object by the difference of present image and background model when detection;The frame difference method is by view
Corresponding position pixel is compared to obtain the position of moving target object between consecutive frame in frequency sequence;The optical flow method is
Using the light stream vector characteristic of time change, the moving target object in the video image is detected.
In the present embodiment, the method for the static target object in above-mentioned detection video image and moving target object is not
Be limited to it is above-mentioned enumerate, any method of putting for being adapted to detect the target object in video image can be applied to this.In addition, this
The method of the static target object and moving target object in the detection video image in embodiment is the prior art, this
Text is no longer discussed in detail herein.
(2) classification of the target object is determined.
For example, can determine the class of the target object when identifying the target object in the video image is automobile
It Wei not the vehicles.As soon as the detection and classification of the target object are a very basic task, purpose in vision technique
It is interested some objects in tracking scene, including conventional target object detection, personnel's detection and vehicle detection etc..
In the present embodiment, the video image can be obtained by decomposing the target object in the video image
In target object essential attribute, wherein the essential attribute includes color, motion profile, shape, structure etc., then in institute
The essential attribute for stating acquisition is compared with the essential attribute that target object in the database is stored in advance, to accurately know
It Chu not target object in the video image.The essential attribute and target object class of target object are stored in the database
Table is not corresponded to.
The classification of the determination target object specifically includes: by decomposing the target object in the video image,
Obtain the essential attribute of the target object in the video image;The essential attribute that will acquire and it is stored in advance in database
In the essential attribute of target object be compared;When the target object in the essential attribute of acquisition and the database
When essential attribute is consistent, the essential attribute table corresponding with target object classification stored in database is inquired to obtain the target pair
The classification of elephant.
The target object that the tracking module 203 is used to track in the video image obtains the shape of the target object
State.
After target object detection is completed, need to calculate its motion profile for the target object each detected,
To realize the target object tracked in the video image.In the present embodiment, by tracking in the video image
Target object can determine the state of the target object.
The method of target object in the tracking video image includes:
A) target object in current video frame is determined.
B) characteristics of image of image-region and described image region of the target object in preamble video frame is obtained,
In, the preamble video frame is k video frame before current video frame, and k is positive integer.
C) image-region according to the target object in preamble video frame carries out movement to the target object and estimates
Meter, determines the target object in the estimation range of current video frame.
D) detection range of the target object in current video frame is determined according to the estimation range.
E) judge whether the target object appears in the detection range in current video frame, if the target object does not have
The detection range in current video frame is appeared in, determines the abnormal state of the target object;If the target object appears in
Detection range in current video frame determines image-region of the target object in current video frame.
Refer to k video frame before current video frame due to preamble video frame, by this preceding k video frame come to current
Video frame is estimated and contrasting detection, and calculation amount is smaller, and is able to solve target object in video and loses or hide once in a while
The problem of gear, detection accuracy are higher.
The analysis module 204 according to the classification of the target object and the state analysis of the target object for obtaining
The business scenario for including in the video image.
In the present embodiment, the classification that can obtain target object according to testing result, can be true according to tracking result
The state of the fixed target object, so as to analyze to obtain the business scenario for including in the video image.
For example, can obtain the target object according to testing result is automobile, the automobile, which does not appear in, works as forward sight
Detection range in frequency frame can then determine the abnormal state of the automobile, such as the automobile be in congestion status, then it can be seen that
The business scenario for including in the video image is intelligent transportation business scenario.
The classification that the target object can for another example be obtained according to testing result is pedestrian, and the pedestrian, which does not appear in, to be worked as
Detection range in preceding video frame can then determine the abnormal state of the pedestrian.It is if the pedestrian falls down, then it can be seen that described
The business scenario for including in video image is intelligent transportation business scenario.
The judgment module 205 is for judging whether the business scenario in the video image exception occurs.When the view
When business scenario in frequency image occurs abnormal, the key message when business scenario occurs abnormal is recorded.
In the present embodiment, institute can determine whether by the state analysis of the classification of the target object and the target object
State whether the business scenario in video image exception occurs.For example, working as forward sight by judging whether the target object appears in
Detection range in frequency frame determines the target if the target object does not appear in the detection range in current video frame
Also there is exception in the abnormal state of object, i.e., the corresponding business scenario of described target object.
It in other embodiments, can be by the way that the video image be inputted trained Exception Model, and root in advance
Judge whether the business scenario in the video image is abnormal according to the Exception Model.Specifically, when determining the target object
When abnormal, the current video frame is extracted as abnormal image;Instruction in advance is imported using the abnormal image as images to be recognized
In the Exception Model perfected, wherein the Exception Model is used to characterize the corresponding relationship between images to be recognized and abnormal scene;
When Exception Model output abnormal scene corresponding with the images to be recognized, confirm that abnormal institute occurs in the business scenario
Stating Exception Model includes the corresponding Exception Model of different business scenarios.For example, when the business scenario is intelligent transportation business
When scene, the corresponding Exception Model of the intelligent transportation business scenario includes traffic accident model, traffic congestion model and illegal
Violation model etc.;When the business scenario is wisdom garden business scenario, the corresponding exception of wisdom garden business scenario
Model includes that carry-on articles leave model, personnel invade model etc.;When the business scenario is that ferry monitors business scenario, institute
Stating the corresponding Exception Model of ferry monitoring business scenario includes overload model, overboard model, illegal model ship etc..
For example, when traffic congestion occurs in current video frame in the video image, the current video frame is extracted
It is imported in trained traffic congestion model in advance as abnormal image, and using the abnormal image as images to be recognized, when
When the traffic congestion model exports traffic congestion scene corresponding with the images to be recognized, confirm that the video image is corresponding
Intelligent transportation business scenario in occur it is abnormal;When the traffic congestion model do not export it is corresponding with the images to be recognized
When traffic congestion scene, confirm normal in the corresponding intelligent transportation business scenario of the video image.
Above-mentioned Exception Model is the machine learning model according to picture sample collection training.The picture sample includes abnormal industry
Business scene picture sample and regular traffic scene picture sample.The machine learning model is that can carry out the artificial of image recognition
Intelligent algorithm model, comprising: convolutional neural networks MODEL C NN, Recognition with Recurrent Neural Network module RNN and deep neural network model
DNN.Wherein, convolutional neural networks MODEL C NN is a kind of multilayer neural network, problem of image recognition that can be huge by data volume
Continuous dimensionality reduction can be finally trained to, and therefore, the machine learning model in the embodiment of the present application can be CNN model.
In the evolution of CNN network structure, there are many CNN networks, including LeNet, AlexNet, VGGNet,
GoogleNet and ResNet.Wherein, ResNet network proposes a kind of residual error learning framework for mitigating network training burden, this
Kind of network is deeper than the network substantially level being previously used, and solves other neural networks as network is deepened, accuracy rate
The problem of decline.In the present embodiment, the machine learning model can be the ResNet in convolution log on MODEL C NN
Model.It should be noted that be merely illustrative of herein, the machine learning model that other can carry out image recognition is equally applicable
In the application, herein without repeating.
The processing module 206 is used to record the business when the business scenario in the video image occurs abnormal
Key message when scene occurs abnormal.
In the present embodiment, the key message includes that the business scenario abnormal time, place and interception occurs
The video image described in picture file etc. of business scenario when occurring abnormal.
Further, the video analysis method further includes that the key message of record is sent to third party's business platform.
Third party's business platform includes public security system, traffic control system etc..By the way that the key message of the record is sent to
Third party's business platform can help third party's business platform to obtain pass when occurring abnormal in business scenario in time
Key information, to handle the exception in time.
Further, the video analysis method further include: show the key message when business scenario occurs abnormal.
Specifically, show that institute in the video image of abnormal time, place and interception occurs in the business scenario in display screen
State the picture file etc. when business scenario occurs abnormal.
In conclusion video analysis device 20 provided by the invention, including receiving module 201, detection module 202, tracking
Module 203, analysis module 204, judgment module 205 and processing module 206.The receiving module 201 is adopted for receiving camera
The video image of collection;The target object that the detection module 202 is used to detect in the video image obtains the target object
Classification;The target object that the tracking module 203 is used to track in the video image obtains the state of the target object;
The analysis module 204 is used to obtain the video according to the classification of the target object and the state analysis of the target object
The business scenario for including in image;The judgment module 205 is for judging whether the business scenario exception occurs;And the place
Reason module 206 is used for when the business scenario in the video image occurs abnormal, when recording the business scenario appearance exception
Key message.It can analyze whether the corresponding business scenario of the video image exception occurs in real time, and confirm the industry
When scene of being engaged in occurs abnormal, the key message when business scenario occurs abnormal is recorded.So as to by the key message
It is sent to corresponding third-party platform, to handle the exception in time.
The above-mentioned integrated unit realized in the form of software function module, can store and computer-readable deposit at one
In storage media.Above-mentioned software function module is stored in a storage medium, including some instructions are used so that a computer
It is each that equipment (can be personal computer, double screen equipment or the network equipment etc.) or processor (processor) execute the present invention
The part of a embodiment the method.
Embodiment three
Fig. 3 is the schematic diagram for the server that the embodiment of the present invention three provides.
The server 3 includes: database 31, memory 32, at least one processor 33, is stored in the memory 32
In and the computer program 34 and at least one communication bus 35 that can be run at least one described processor 33.
At least one described processor 33 realizes above-mentioned video analysis embodiment of the method when executing the computer program 34
In step.
Illustratively, the computer program 34 can be divided into one or more module/units, it is one or
Multiple module/units are stored in the memory 32, and are executed by least one described processor 33, to complete this hair
It is bright.One or more of module/units can be the series of computation machine program instruction section that can complete specific function, this refers to
Enable section for describing implementation procedure of the computer program 34 in the server 3.
The server 3 is that one kind can be automatic to carry out numerical value calculating and/or letter according to the instruction for being previously set or storing
The equipment of processing is ceased, hardware includes but is not limited to microprocessor, specific integrated circuit (application program lication
Specific Integrated Circuit, ASIC), programmable gate array (Field-Programmable Gate
Array, FPGA), digital processing unit (Digital Signal Processor, DSP), embedded device etc..Art technology
Personnel are appreciated that the schematic diagram 3 is only the example of server 3, do not constitute the restriction to server 3, may include
Than illustrating more or fewer components, certain components or different components are perhaps combined, such as the server 3 can be with
Including input-output equipment, network access equipment, bus etc..
The database (Database) 31 is to carry out the foundation of tissue, storage and management data according to data structure described
Warehouse on server 3.Database is generally divided into hierarchical database, network database and three kinds of relational database.In
In present embodiment, the database 31 is for storing described video image etc..
At least one described processor 33 can be central processing unit (Central Processing Unit, CPU),
It can also be other general processors, digital signal processor (Digital Signal Processor, DSP), dedicated integrated
Circuit (Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..The processor 33 can be microprocessor or the processor 33 is also possible to any conventional processor
Deng the processor 33 is the control centre of the server 3, utilizes each of various interfaces and the entire server 3 of connection
A part.
The memory 32 can be used for storing the computer program 34 and/or module/unit, and the processor 33 passes through
Operation executes the computer program and/or module/unit being stored in the memory 32, and calls and be stored in memory
Data in 32 realize the various functions of the server 3.The memory 32 can mainly include storing program area and storage number
According to area, wherein storing program area can application program needed for storage program area, at least one function (for example sound plays function
Energy, image player function etc.) etc.;Storage data area, which can be stored, uses created data (such as audio number according to server 3
According to, phone directory etc.) etc..In addition, memory 32 may include high-speed random access memory, it can also include non-volatile memories
Device, such as hard disk, memory, plug-in type hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure
Digital, SD) card, flash card (Flash Card), at least one disk memory, flush memory device or other volatibility are solid
State memory device.
Program code is stored in the memory 32, and at least one described processor 33 can call the memory 32
The program code of middle storage is to execute relevant function.For example, modules described in Fig. 2 (receiving module 201, detection mould
Block 202, tracking module 203, analysis module 204, judgment module 205 and processing module 206) it is stored in the memory 32
Program code, and as performed by least one described processor 33, to realize the function of the modules to reach view
Frequency analysis purpose.
The receiving module 201 is used to receive the video image of camera acquisition;
The target object that the detection module 202 is used to detect in the video image obtains the class of the target object
Not;
The target object that the tracking module 203 is used to track in the video image obtains the shape of the target object
State;
The analysis module 204 according to the classification of the target object and the state analysis of the target object for obtaining
The business scenario for including in the video image;
The judgment module 205 is for judging whether the business scenario exception occurs;And
The processing module 206 is used to record the business when the business scenario in the video image occurs abnormal
Key message when scene occurs abnormal.
If the integrated module/unit of the server 3 is realized in the form of SFU software functional unit and as independent production
Product when selling or using, can store in a computer readable storage medium.Based on this understanding, the present invention realizes
All or part of the process in above-described embodiment method can also instruct relevant hardware to complete by computer program,
The computer program can be stored in a computer readable storage medium, the computer program when being executed by processor,
The step of above-mentioned each embodiment of the method can be achieved.Wherein, the computer program includes computer program code, the calculating
Machine program code can be source code form, object identification code form, executable file or certain intermediate forms etc..The computer
Readable medium may include: any entity or device, recording medium, USB flash disk, the movement that can carry the computer program code
Hard disk, magnetic disk, CD, computer storage, read-only memory (ROM, Read-Only Memory), random access memory
(RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium etc..It needs to illustrate
It is that the content that the computer-readable medium includes can be fitted according to the requirement made laws in jurisdiction with patent practice
When increase and decrease, such as in certain jurisdictions, according to legislation and patent practice, computer-readable medium does not include electric carrier wave letter
Number and telecommunication signal.
Although being not shown, the server 3 can also include the power supply (such as battery) powered to all parts, preferably
, power supply can be logically contiguous by power-supply management system and at least one described processor 33, to pass through power management system
System realizes the functions such as management charging, electric discharge and power managed.Power supply can also include one or more direct current or friendship
Galvanic electricity source, recharging system, power failure detection circuit, power adapter or inverter, power supply status indicator etc. are any
Component.The server 3 can also include bluetooth module, Wi-Fi module etc., and details are not described herein.
It should be appreciated that the embodiment is only purposes of discussion, do not limited by this structure in patent claim.
In several embodiments provided by the present invention, it should be understood that disclosed electronic equipment and method, Ke Yitong
Other modes are crossed to realize.For example, electronic equipment embodiment described above is only schematical, for example, the unit
Division, only a kind of logical function partition, there may be another division manner in actual implementation.
It, can also be in addition, each functional unit in each embodiment of the present invention can integrate in same treatment unit
It is that each unit physically exists alone, can also be integrated in same unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of hardware adds software function module.
It is obvious to a person skilled in the art that invention is not limited to the details of the above exemplary embodiments, Er Qie
In the case where without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, and the scope of the present invention is by appended power
Benefit requires rather than above description limits, it is intended that all by what is fallen within the meaning and scope of the equivalent elements of the claims
Variation is included in the present invention.Any reference signs in the claims should not be construed as limiting the involved claims.This
Outside, it is clear that one word of " comprising " is not excluded for other units or, odd number is not excluded for plural number.The multiple units stated in system claims
Or device can also be implemented through software or hardware by a unit or device.The first, the second equal words are used to indicate name
Claim, and does not indicate any particular order.
Finally it should be noted that the above examples are only used to illustrate the technical scheme of the present invention and are not limiting, although reference
Preferred embodiment describes the invention in detail, those skilled in the art should understand that, it can be to of the invention
Technical solution is modified or equivalent replacement, without departing from the spirit of the technical scheme of the invention range.
Claims (10)
1. a kind of video analysis method, which is characterized in that the described method includes:
Receive the video image of camera acquisition;
It detects the target object in the video image and obtains the classification of the target object;
It tracks the target object in the video image and obtains the state of the target object;
The industry for including in the video image is obtained according to the state analysis of the classification of the target object and the target object
Business scene;
Judge whether the business scenario exception occurs;And
When the business scenario in the video image occurs abnormal, the crucial letter when business scenario occurs abnormal is recorded
Breath.
2. video analysis method as described in claim 1, which is characterized in that the target pair in the detection video image
Classification as obtaining the target object includes:
By decomposing the target object in the video image, the essential attribute of the target object in the video image is obtained;
The essential attribute that will acquire is compared with the essential attribute that target object in the database is stored in advance;
When the essential attribute of acquisition is consistent with the essential attribute of target object in the database, inquire in database
The essential attribute of storage table corresponding with target object classification is to obtain the classification of the target object.
3. video analysis method as described in claim 1, which is characterized in that the target pair in the tracking video image
State as obtaining the target object includes:
Determine the target object in current video frame;
Obtain the characteristics of image of image-region and described image region of the target object in preamble video frame, wherein described
Preamble video frame is k video frame before current video frame, and k is positive integer;
According to image-region of the target object in preamble video frame, estimation is carried out to the target object, is determined
The target object is in the estimation range of current video frame;
Detection range of the target object in current video frame is determined according to the estimation range;
Judge whether the target object appears in the detection range in current video frame;
If the target object appears in the detection range in current video frame, determine the target object in current video frame
Image-region;
If the target object does not appear in the detection range in current video frame, determine that the target object is abnormal.
4. video analysis method as claimed in claim 3, which is characterized in that described to judge whether the business scenario occurs different
Often include:
When determining the target object exception, the current video frame is extracted as abnormal image;
It is imported the abnormal image as images to be recognized in trained Exception Model in advance, wherein the Exception Model
For characterizing the corresponding relationship between images to be recognized and abnormal scene;
When Exception Model output abnormal scene corresponding with the images to be recognized, it is different to confirm that the business scenario occurs
Often.
5. video analysis method as described in claim 1, which is characterized in that the key message includes that the business scenario goes out
Picture file when now business scenario described in the video image of abnormal time, place and interception occurs abnormal.
6. video analysis method as claimed in claim 5, which is characterized in that the method also includes:
The key message of record is sent to third party's business platform, wherein third party's business platform include public security system and
Traffic control system.
7. video analysis method as described in claim 1, which is characterized in that after the video image for receiving camera acquisition,
The method also includes:
The video image is decoded.
8. a kind of video analysis device, which is characterized in that described device includes:
Receiving module, for receiving the video image of camera acquisition;
Detection module obtains the classification of the target object for detecting the target object in the video image;
Tracking module obtains the state of the target object for tracking the target object in the video image;
Analysis module, for obtaining the video figure according to the classification of the target object and the state analysis of the target object
The business scenario for including as in;
Judgment module, for judging whether the business scenario exception occurs;And
Processing module, it is different for when the business scenario in the video image occurs abnormal, recording the business scenario appearance
Key message when often.
9. a kind of server, which is characterized in that the server includes processor and memory, and the processor is for executing institute
Video analysis method as claimed in any of claims 1 to 7 in one of claims is realized when stating the computer program stored in memory.
10. a kind of computer readable storage medium, computer program, feature are stored on the computer readable storage medium
It is, the computer program realizes video analysis side as claimed in any of claims 1 to 7 in one of claims when being executed by processor
Method.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910517477.XA CN110390262B (en) | 2019-06-14 | 2019-06-14 | Video analysis method, device, server and storage medium |
PCT/CN2019/103373 WO2020248386A1 (en) | 2019-06-14 | 2019-08-29 | Video analysis method and apparatus, computer device and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910517477.XA CN110390262B (en) | 2019-06-14 | 2019-06-14 | Video analysis method, device, server and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110390262A true CN110390262A (en) | 2019-10-29 |
CN110390262B CN110390262B (en) | 2023-06-30 |
Family
ID=68285438
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910517477.XA Active CN110390262B (en) | 2019-06-14 | 2019-06-14 | Video analysis method, device, server and storage medium |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN110390262B (en) |
WO (1) | WO2020248386A1 (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111339894A (en) * | 2020-02-20 | 2020-06-26 | 支付宝(杭州)信息技术有限公司 | Data processing and risk identification method, device, equipment and medium |
CN111652043A (en) * | 2020-04-15 | 2020-09-11 | 北京三快在线科技有限公司 | Object state identification method and device, image acquisition equipment and storage medium |
CN111680610A (en) * | 2020-06-03 | 2020-09-18 | 合肥中科类脑智能技术有限公司 | Construction scene abnormity monitoring method and device |
CN111783591A (en) * | 2020-06-23 | 2020-10-16 | 北京百度网讯科技有限公司 | Anomaly detection method, device, equipment and storage medium |
CN111832492A (en) * | 2020-07-16 | 2020-10-27 | 平安科技(深圳)有限公司 | Method and device for distinguishing static traffic abnormality, computer equipment and storage medium |
CN112804489A (en) * | 2020-12-31 | 2021-05-14 | 重庆文理学院 | Internet + -based intelligent construction site management system and method |
WO2021208875A1 (en) * | 2020-04-17 | 2021-10-21 | 华为技术有限公司 | Visual detection method and visual detection apparatus |
CN114792368A (en) * | 2022-04-28 | 2022-07-26 | 上海兴容信息技术有限公司 | Method and system for intelligently judging store compliance |
CN115834621A (en) * | 2022-11-16 | 2023-03-21 | 山东新一代信息产业技术研究院有限公司 | Accident quick-place device and method based on artificial intelligence |
WO2023103819A1 (en) * | 2021-12-08 | 2023-06-15 | 北京拙河科技有限公司 | Video monitoring system and method based on hundred-megapixel data and video anomaly analysis system and method based on hundred-megapixel data |
CN116708899A (en) * | 2022-06-30 | 2023-09-05 | 北京生数科技有限公司 | Video processing method, device and storage medium applied to virtual image synthesis |
RU2818487C1 (en) * | 2023-10-01 | 2024-05-02 | Общество С Ограниченной Ответственностью "Проф-Ит" (Ооо "Проф-Ит") | Local video analytics device |
Families Citing this family (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112633126A (en) * | 2020-12-18 | 2021-04-09 | 联通物联网有限责任公司 | Video processing method and device |
CN112711994A (en) * | 2020-12-21 | 2021-04-27 | 航天信息股份有限公司 | Method and system for detecting illegal operation behaviors based on scene recognition |
CN112634329B (en) * | 2020-12-26 | 2024-02-13 | 西安电子科技大学 | Scene target activity prediction method and device based on space-time and or graph |
CN112749636B (en) * | 2020-12-29 | 2023-10-31 | 精英数智科技股份有限公司 | Monitoring method, device and system for water drainage detection of coal mine and storage medium |
CN112991280B (en) * | 2021-03-03 | 2024-05-28 | 望知科技(深圳)有限公司 | Visual detection method, visual detection system and electronic equipment |
CN113065456A (en) * | 2021-03-30 | 2021-07-02 | 上海商汤智能科技有限公司 | Information prompting method and device, electronic equipment and computer storage medium |
CN113378005B (en) * | 2021-06-03 | 2023-06-02 | 北京百度网讯科技有限公司 | Event processing method, device, electronic equipment and storage medium |
CN113361468A (en) * | 2021-06-30 | 2021-09-07 | 北京百度网讯科技有限公司 | Business quality inspection method, device, equipment and storage medium |
CN113422935B (en) * | 2021-07-06 | 2022-09-30 | 城云科技(中国)有限公司 | Video stream processing method, device and system |
CN114205565B (en) * | 2022-02-15 | 2022-07-29 | 云丁网络技术(北京)有限公司 | Monitoring video distribution method and system |
CN113705370B (en) * | 2021-08-09 | 2023-06-30 | 百度在线网络技术(北京)有限公司 | Method and device for detecting illegal behaviors of live broadcasting room, electronic equipment and storage medium |
CN113807257A (en) * | 2021-09-17 | 2021-12-17 | 深圳市商汤科技有限公司 | Method, device and equipment for generating algorithm application element and computer readable storage medium |
CN113992890A (en) * | 2021-10-22 | 2022-01-28 | 北京明略昭辉科技有限公司 | Monitoring method, monitoring device, storage medium and electronic equipment |
CN114378862B (en) * | 2022-03-02 | 2024-05-10 | 北京云迹科技股份有限公司 | Cloud platform-based automatic robot abnormality repairing method and device and robot |
CN114682520A (en) * | 2022-04-12 | 2022-07-01 | 浪潮软件集团有限公司 | Substandard product sorting device based on domestic CPU and artificial intelligence accelerator card |
CN116953416B (en) * | 2023-09-19 | 2023-12-08 | 英迪格(天津)电气有限公司 | Monitoring system for running state of railway power transformation and distribution device |
CN117079079B (en) * | 2023-09-27 | 2024-03-15 | 中电科新型智慧城市研究院有限公司 | Training method of video anomaly detection model, video anomaly detection method and system |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090087024A1 (en) * | 2007-09-27 | 2009-04-02 | John Eric Eaton | Context processor for video analysis system |
CN107194318A (en) * | 2017-04-24 | 2017-09-22 | 北京航空航天大学 | The scene recognition method of target detection auxiliary |
CN108830204A (en) * | 2018-06-01 | 2018-11-16 | 中国科学技术大学 | The method for detecting abnormality in the monitor video of target |
CN109598885A (en) * | 2018-12-21 | 2019-04-09 | 广东中安金狮科创有限公司 | Monitoring system and its alarm method |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107346415A (en) * | 2017-06-08 | 2017-11-14 | 小草数语(北京)科技有限公司 | Method of video image processing, device and monitoring device |
US10546197B2 (en) * | 2017-09-26 | 2020-01-28 | Ambient AI, Inc. | Systems and methods for intelligent and interpretive analysis of video image data using machine learning |
CN109063667B (en) * | 2018-08-14 | 2021-02-19 | 视云融聚(广州)科技有限公司 | Scene-based video identification mode optimization and pushing method |
-
2019
- 2019-06-14 CN CN201910517477.XA patent/CN110390262B/en active Active
- 2019-08-29 WO PCT/CN2019/103373 patent/WO2020248386A1/en active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090087024A1 (en) * | 2007-09-27 | 2009-04-02 | John Eric Eaton | Context processor for video analysis system |
CN107194318A (en) * | 2017-04-24 | 2017-09-22 | 北京航空航天大学 | The scene recognition method of target detection auxiliary |
CN108830204A (en) * | 2018-06-01 | 2018-11-16 | 中国科学技术大学 | The method for detecting abnormality in the monitor video of target |
CN109598885A (en) * | 2018-12-21 | 2019-04-09 | 广东中安金狮科创有限公司 | Monitoring system and its alarm method |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111339894A (en) * | 2020-02-20 | 2020-06-26 | 支付宝(杭州)信息技术有限公司 | Data processing and risk identification method, device, equipment and medium |
CN111652043A (en) * | 2020-04-15 | 2020-09-11 | 北京三快在线科技有限公司 | Object state identification method and device, image acquisition equipment and storage medium |
WO2021208875A1 (en) * | 2020-04-17 | 2021-10-21 | 华为技术有限公司 | Visual detection method and visual detection apparatus |
CN111680610A (en) * | 2020-06-03 | 2020-09-18 | 合肥中科类脑智能技术有限公司 | Construction scene abnormity monitoring method and device |
CN111783591A (en) * | 2020-06-23 | 2020-10-16 | 北京百度网讯科技有限公司 | Anomaly detection method, device, equipment and storage medium |
CN111783591B (en) * | 2020-06-23 | 2024-04-26 | 北京百度网讯科技有限公司 | Abnormality detection method, abnormality detection device, abnormality detection apparatus, and recording medium |
CN111832492A (en) * | 2020-07-16 | 2020-10-27 | 平安科技(深圳)有限公司 | Method and device for distinguishing static traffic abnormality, computer equipment and storage medium |
CN111832492B (en) * | 2020-07-16 | 2024-06-04 | 平安科技(深圳)有限公司 | Static traffic abnormality judging method and device, computer equipment and storage medium |
CN112804489A (en) * | 2020-12-31 | 2021-05-14 | 重庆文理学院 | Internet + -based intelligent construction site management system and method |
WO2023103819A1 (en) * | 2021-12-08 | 2023-06-15 | 北京拙河科技有限公司 | Video monitoring system and method based on hundred-megapixel data and video anomaly analysis system and method based on hundred-megapixel data |
CN114792368A (en) * | 2022-04-28 | 2022-07-26 | 上海兴容信息技术有限公司 | Method and system for intelligently judging store compliance |
CN116708899A (en) * | 2022-06-30 | 2023-09-05 | 北京生数科技有限公司 | Video processing method, device and storage medium applied to virtual image synthesis |
CN116708899B (en) * | 2022-06-30 | 2024-01-23 | 北京生数科技有限公司 | Video processing method, device and storage medium applied to virtual image synthesis |
CN115834621A (en) * | 2022-11-16 | 2023-03-21 | 山东新一代信息产业技术研究院有限公司 | Accident quick-place device and method based on artificial intelligence |
RU2818487C1 (en) * | 2023-10-01 | 2024-05-02 | Общество С Ограниченной Ответственностью "Проф-Ит" (Ооо "Проф-Ит") | Local video analytics device |
Also Published As
Publication number | Publication date |
---|---|
WO2020248386A1 (en) | 2020-12-17 |
CN110390262B (en) | 2023-06-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110390262A (en) | Video analysis method, apparatus, server and storage medium | |
CN110309735A (en) | Exception detecting method, device, server and storage medium | |
WO2019153193A1 (en) | Taxi operation monitoring method, device, storage medium, and system | |
CN111199257A (en) | Fault diagnosis method and device for high-speed rail driving equipment | |
CN105931068A (en) | Cardholder consumption figure generation method and device | |
CN111814775B (en) | Target object abnormal behavior identification method, device, terminal and storage medium | |
CN102902960B (en) | Leave-behind object detection method based on Gaussian modelling and target contour | |
CN110532888A (en) | A kind of monitoring method, apparatus and system | |
CN102254394A (en) | Antitheft monitoring method for poles and towers in power transmission line based on video difference analysis | |
CN110263623B (en) | Train climbing monitoring method, device, terminal and storage medium | |
CN111274886A (en) | Deep learning-based pedestrian red light violation analysis method and system | |
CN113287120A (en) | Vehicle driving environment abnormity monitoring method and device, electronic equipment and storage medium | |
CN110263622A (en) | Train fire monitoring method, apparatus, terminal and storage medium | |
CN113253709A (en) | Health diagnosis method and device suitable for rail transit vehicle | |
Heydarian et al. | Automated benchmarking and monitoring of an earthmoving operation's carbon footprint using video cameras and a greenhouse gas estimation model | |
CN111126167A (en) | Method and system for quickly identifying series activities of multiple specific persons | |
CN111027510A (en) | Behavior detection method and device and storage medium | |
CN110458260A (en) | A kind of method, apparatus and computer memory device for supervising school bus | |
CN115132368A (en) | Infectious disease prevention and control monitoring method and system based on big data platform | |
Huang et al. | A bus crowdedness sensing system using deep-learning based object detection | |
CN112633163A (en) | Detection method for realizing illegal operation vehicle detection based on machine learning algorithm | |
Corrado et al. | Smart passenger center: Real-time optimization of urban public transport | |
CN116992267B (en) | Regional population gender identification method and system based on signaling data | |
Siaminamini et al. | Generating a risk profile for car insurance policyholders: A deep learning conceptual model | |
CN112906518B (en) | Riding abnormal person identification method and system based on SVM model |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |