CN110149355A - A kind of distributed image analysis system - Google Patents
A kind of distributed image analysis system Download PDFInfo
- Publication number
- CN110149355A CN110149355A CN201810150471.9A CN201810150471A CN110149355A CN 110149355 A CN110149355 A CN 110149355A CN 201810150471 A CN201810150471 A CN 201810150471A CN 110149355 A CN110149355 A CN 110149355A
- Authority
- CN
- China
- Prior art keywords
- analysing computer
- image analysing
- image
- analysis
- computer device
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/162—Detection; Localisation; Normalisation using pixel segmentation or colour matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B19/00—Alarms responsive to two or more different undesired or abnormal conditions, e.g. burglary and fire, abnormal temperature and abnormal rate of flow
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- 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, rendering scenes according to MPEG-4 scene graphs
- H04N21/44008—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream
Abstract
The invention discloses a kind of distributed image analysis systems, include: multiple image analysing computer devices and a cluster management device to analyze video streaming;Wherein, for one image analysing computer device when one video streaming of execution is analyzed but can not individually complete video streaming analysis, the image analysing computer device is by the cluster management device so that other image analysing computer devices are analyzed to execute at least part of work of video streaming analysis with completing the video streaming.
Description
Technical field
The present invention relates to image analysis system, especially a kind of distributed image analysis system.
Background technique
Existing image analysing computer device usually designs for particular analysis function, and is limited to image analysing computer needs
The hardware limitation of a large amount of operation efficiencies, existing image analysing computer device can not analyze the complicated image string for needing a large amount of operation efficiencies
Stream, otherwise the cost of existing image analysing computer device can be too high.And existing recording apparatus, still it is absorbed in the storage of image and returns
It adjusts, even if there is additional image analysing computer function, also lacks system support, it is difficult to effectively application.
Therefore, industry, which needs one, can analyze the distributed image for needing the complicated video streaming of a large amount of operation efficiencies
Analysis system.
Summary of the invention
A purpose of the invention is to provide a kind of distributed image analysis system, can make multiple image analysing computer device phases
It mutually supports, to make full use of the resource of multiple image analysing computer device to be to reduce come the analysis work for completing complicated video streaming
System cost.The analysis for the complicated video streaming that the present invention is sayed refers to that single image analysing computer device of the invention can not be unaided
Video streaming analysis.
A purpose of the invention is to provide a kind of distributed image analysis system, wherein when an image analysing computer device is being held
When one video streaming of row is analyzed but can not analyze a complicated image, which hands over the analysis work of the complexity image
It is executed by a cloud Analysis Service device, then is transmitted back to the analysis result of the complexity image by the cloud Analysis Service device
The image analysing computer device is to complete video streaming analysis.The analysis for the complicated image that the present invention is sayed refers to single shadow of the invention
As analytical equipment can not unaided image analysing computer.
A kind of distributed image analysis system, the distributed image analysing computer system are proposed in one embodiment of the invention
System includes: multiple image analysing computer devices, to analyze video streaming;And a cluster management device, it is connected to multiple image
Analytical equipment;Wherein, when an image analysing computer device of multiple image analysing computer devices is analyzed in one video streaming of execution but can not be single
When solely completing video streaming analysis, which passes through the cluster management device so that other image analysing computer devices
And/or the cluster management device is incited somebody to action to execute at least part of work that the video streaming is analyzed, then by cluster management device
The implementing result of at least part of work is back to the image analysing computer device, and the image analysing computer device is again by this at least one
The implementing result system of the work divided is whole to complete video streaming analysis.
In one embodiment, which is connected to a cloud Analysis Service device, at least part of work
Make to include an image analysing computer, multiple image analysing computer device does not have the ability for executing the image analysing computer, the cluster management device
The cloud Analysis Service device is transferred to execute the work of the image analysing computer, then by the cloud Analysis Service device by the image
The result of analysis is sent to the image analysing computer device to complete video streaming analysis.
In one embodiment, which is passed the result of the image analysing computer by the cluster management device
It send to the image analysing computer device.
In one embodiment, which is directly sent to the image analysing computer for the result of the image analysing computer
Device is without passing through the cluster management device.
In one embodiment, when which detects event generation, which is transferred into the cloud
Analysis Service device judges that the image has the probability score of an abnormality, then by the cloud Analysis Service device that this is several
Rate score is transmitted back to the image analysing computer device.
In one embodiment, it is the preliminary analysis by the image which, which detects the event, when this
The event is detected when preliminary analysis meets a trigger condition.
In one embodiment, which receives the information of an arrangement for detecting to detect the event.
In one embodiment, it includes a dangerous goods or a fiery scape which, which is the image,.
In one embodiment, which is the movement of object.
In one embodiment, which is a temperature detection device.
A kind of distributed image analysis system, the distributed image analysing computer system are proposed in one embodiment of the invention
System includes: multiple image analysing computer devices, to analyze video streaming;And a cluster management device, it is connected to multiple image
Analytical equipment, wherein the cluster management device is connected to a cloud Analysis Service device;Wherein, when multiple image analysing computer devices
One image analysing computer device is when executing video streaming analysis but can not individually complete video streaming analysis, image analysing computer dress
It sets through the cluster management device so that other image analysing computer devices and/or the cloud Analysis Service device execute the image
At least part of work of crossfire analysis, then returned the implementing result of at least part of work by cluster management device
To the image analysing computer device, the image analysing computer device is whole to complete the shadow by the implementing result system of at least part of work again
As crossfire is analyzed.
A kind of distributed image analysis system, the distributed image analysing computer system are proposed in one embodiment of the invention
System includes: an image analysing computer device, and wherein the image analysing computer device is connected to a cloud Analysis Service device;Wherein, when the shadow
As analytical equipment is executing video streaming analysis but when can not execute an image analysing computer, the image analysing computer device is by the image point
The work of analysis transfers to the cloud Analysis Service device to execute, then by the cloud Analysis Service device by the result of the image analysing computer
It is transmitted back to the image analysing computer device, the image analysing computer device is whole to complete the video streaming point by the result system of the image analysing computer again
Analysis.
In one embodiment, when which detects event generation, which is transferred into the cloud
Analysis Service device judges that the image has the probability score of an abnormality, then by the cloud Analysis Service device that this is several
Rate score is transmitted back to the image analysing computer device.
In one embodiment, it is the preliminary analysis by the image which, which detects the event, when this
The event is detected when preliminary analysis meets a trigger condition.
In one embodiment, which receives the information of an arrangement for detecting to detect the event.
In one embodiment, it includes a dangerous goods or a fiery scape which, which is the image,.
In one embodiment, which is the movement of object.
In one embodiment, which is a temperature detection device.
Detailed description of the invention
Fig. 1 is the schematic diagram of the image analysis system in one embodiment of the invention.
Fig. 2 is the schematic diagram of the image analysis system in one embodiment of the invention.
Fig. 3 is the schematic diagram of the image analysis system in one embodiment of the invention.
Fig. 4 is the schematic diagram of the image analysis system in one embodiment of the invention.
Description of symbols: the distributed image analysis system of 100A-;The distributed image analysis system of 100B-;
The distributed image analysis system of 100C-;The distributed image analysis system of 100D-;101- cluster management device;102- image
Analytical equipment;The cloud 103- Analysis Service device;104- camera;105- arrangement for detecting.
Specific embodiment
For the present invention aforementioned and other technology contents, feature and effect refer to the preferable reality of schema in following cooperation
It applies in the detailed description of example, can clearly present.However it is to be noted that following embodiment is not intended to limit the invention.
A kind of distributed image analysis system 100A is proposed in one embodiment of the invention.Referring to Fig. 1, the image
Analysis system 100A includes: multiple image analysing computer devices 102, to analyze video streaming;And a cluster management device 101,
It is connected to multiple image analysing computer device 102, wherein when an image analysing computer device of multiple image analysing computer devices 102 is executing
When one video streaming is analyzed but can not individually complete video streaming analysis, which passes through the cluster management device
101 so that other image analysing computer devices 102 and/or the cluster management device 101 are analyzed at least to execute the video streaming
The work of a part, then the implementing result of at least part of work is back to the image by the cluster management device 101
Analytical equipment, the image analysing computer device are whole to complete the video streaming point by the implementing result system of at least part of work again
Analysis.It note that the present invention is not only restricted to the mode that the image analysing computer device receives video streaming, such as image analysing computer device 102
Can be connected by internet camera or the direct locality connection camera of image analysing computer device 102 or other
Suitable mode is so that image analysing computer device 102 obtains the video streaming that the camera is absorbed.
In one embodiment, which has the ability of image analysing computer, and the cluster management device is executable should
At least part of work.
In one embodiment, which does not have the ability of image analysing computer.
In one embodiment, the resource of the image analysing computer device includes an at least central processing unit (CPU).
In one embodiment, the resource of the image analysing computer device includes an at least central processing unit (CPU) and an at least figure
As processor (GPU) or an image processing hardware accelerator.
In one embodiment, the resource of the image analysing computer device includes an at least central processing unit (CPU) and an at least figure
As processing hardware accelerator.
In one embodiment, which distributes to other image analysing computers for at least part of work and fills
It sets, which is transmitted back to the cluster management device, the cluster management by other image analysing computer devices
At least part of working result is transmitted back to the image analysing computer device again by device, the image analysing computer device unite again it is whole this at least
The working result of a part is to complete video streaming analysis.
In one embodiment, which distributes to other image analysing computers for at least part of work and fills
It sets, which is transmitted back to the image analysing computer device, the image analysing computer by other image analysing computer devices
Device unites the whole at least part of working result again to complete video streaming analysis.
A kind of distributed image analysis system 100B is proposed in one embodiment of the invention.Referring to Fig. 2, the image
Analysis system 100B includes: multiple image analysing computer devices 102, to analyze video streaming;And a cluster management device 101,
It is connected to multiple image analysing computer device 102, which is connected to a cloud Analysis Service device 103,
In, when the image analysing computer device in multiple image analysing computer devices 102 is executing video streaming analysis but can not individually complete
When the video streaming is analyzed, the image analysing computer device pass through the cluster management device 101 so that other image analysing computer device and/
Or the cloud Analysis Service device 103 executes at least part of work of video streaming analysis, then by the cluster management
The implementing result of at least part of work is back to the image analysing computer device by device 101, which again will
The implementing result system of at least part of work is whole to complete video streaming analysis.
In one embodiment, at least part of work of video streaming analysis includes the cloud Analysis Service device
103 one first work, the cluster management device 101 are given first work to the cloud Analysis Service device 103 and are executed,
First implementing result to work is back to the image analysing computer device by cluster management device 101 again or the cloud is analyzed
First implementing result to work is back to the image analysing computer device without by the cluster management device by service unit 103
101.In one embodiment, at least part of work of video streaming analysis includes to give the cloud Analysis Service device
103 be performed one first work and give other image analysing computer devices be performed one second work, the cluster management
Device 101 is given first work to the cloud Analysis Service device 103 and is executed, the cluster management device 101 by this second
Work gives other image analysing computer devices to execute, then by the cluster management device 101 by the cloud Analysis Service device 103
Implementing result of first work and implementing result of second work of other image analysing computer devices be back to the image
Analytical equipment.In one embodiment, which can be back to this for first implementing result to work
Image analysing computer device is without by cluster management device 101, other image analysing computer devices can be by second execution to work
As a result the image analysing computer device is back to without by the cluster management device 101.
In one embodiment, some real-time input output analysis of needs can be individually performed in the processing capacity of image analysing computer device itself
As a result real-time imaging crossfire analysis, such as: human face recognition, the parking lot number plate recognition etc. of very important people (VIP).
In one embodiment, some real-time outputs point of not needing can be performed in the processing capacity of local image analysing computer device itself
Analyse the semireal time video streaming analysis of result, that is to say, that the result of video streaming analysis allows the delay of certain time.If this
The operational capability of ground image analysing computer device is inadequate, work can be transferred to other shadows by cluster management device by part work
Cluster management device or local image analysing computer device are passed back as analytical equipment, then by result, such as: real-time imaging includes a large amount of
Crowd, face feature extraction to be done and analysis, do not have Real-time Alarm demand, and analysis data are the condition search for semireal time.This
When can do the reception of crossfire by an image analysing computer device and human face detection catches face, then will by cluster management device
The face information captured is dispersed to other image analysing computer devices and makees face characteristic acquisition and analysis, finally result united whole.
If local image analysing computer device can not provide all analysis ability, part work can be handed over work by cluster management device
Cluster management device or local image analysing computer device are passed back after the completion of the Analysis Service of cloud, then by result, such as: real-time imaging
For complex scene, predicting abnormality analysis and semireal time alarm to be done, since big data learns and analyze to need a large amount of fortune of elasticity
Resource is calculated, and based in resource set, local image analysing computer device does not have the ability for analyzing this complex scene, needs by cloud point
Analysis service unit does operation to analyze this complex scene.Local image analysing computer device does the reception of video streaming at this time, and looks for
Representative scene out, then the scene picture of table is transferred into cloud Analysis Service device analysis, most by cluster management device
Result is passed back afterwards.
In one embodiment, image analysing computer device can be used and keep in the video streaming to get off to execute off line image analysing computer,
Or use movie file, with output not ask real-time analysis as a result, operating mechanism with semireal time video streaming above-mentioned
Analysis, it is not required that the reaction time, scheduling priority is low.
In one embodiment, image analysing computer device can be used real-time imaging crossfire, keep in the video streaming or shadow to get off
Piece file is analyzed, and prolonged analysis result is taken statistics, and to obtain certain trend or prediction, while analysis result being sent to
Cloud service device counts.
In one embodiment, referring to Fig. 3, the image analysing computer device 102 in distributed image analysis system 100C can
To connect a camera 104, so that image analysing computer device 102 obtains the video streaming that the camera 104 is absorbed.One
In embodiment, image analysing computer device 102 can connect an arrangement for detecting 105 also to sense the variation of environment.In one embodiment,
When the image analysing computer device detects event generation, the cloud Analysis Service is transferred to fill the work of the image analysing computer of a scene
103 are set to execute, to judge that the scene has the probability score of an abnormality, as the scene include a dangerous goods or this
Scape has the probability score of fire, then the scene is had to the probability score of abnormality by the cloud Analysis Service device 103, such as
The scene includes that a dangerous goods or the scene have the probability score of fire to be transmitted back to the image analysing computer device, to generate alarm.
In one embodiment, an image analysing computer device of the invention can connect arrangement for detecting to sense the variation of environment,
When meeting trigger condition, such as: door is turned on, window is broken, alarm bell is pressed, temperature anomaly etc., is just carried out further
Image analysing computer to reach effective image analysing computer, while can reduce wrong report, can also save analysis efficiency.Such as scene is one
Server room, arrangement for detecting are temperature-sensing device, which monitors the service by the temperature-sensing device
When device computer room temperature, it is found that the server room temperature anomaly increases, the image analysing computer device can be triggered at this time and done further
Image analysing computer such as captures the scene photo of the server room at present, a cloud Analysis Service device is transferred to judge the service
The probability score of fire occurs for device computer room, which returns the probability point that fire occurs for the server room again
Number is to the image analysing computer device, to generate alarm.
In one embodiment, image analysing computer device can execute preliminary scene image analysis, when meeting trigger condition, example
Such as: detect it is mobile, detect it is humanoid, detect face, detect invasion, just carry out further scene image analysis,
To reach effective image analysing computer, while wrong report can be reduced, can also save analysis efficiency.Such as scene is Bank Hall, shadow
As analytical equipment analysis finds to have new personage to enter, further image analysing computer is triggered at this time, captures the personage and surrounding photo,
Cloud Analysis Service device is transferred to judge that this image includes the probability score of dangerous goods, cloud Analysis Service device returns again
Image includes the probability score of dangerous goods to image analysing computer device, to generate alarm.
A kind of distributed image analysis system is proposed in one embodiment of the invention.Referring to Fig. 4, the image analysing computer
System 100D includes: an image analysing computer device 102, and wherein the image analysing computer device 102 is connected to a cloud Analysis Service device
103;Wherein, when the image analysing computer device 102 is executing video streaming analysis but when can not analyze a scene, the image analysing computer
The work of the image analysing computer of the scene is transferred to the cloud Analysis Service device 103 to analyze to execute, then by the cloud by device 102
The result of the image analysing computer of the scene is transmitted back to the image analysing computer device 102 by service unit 103, the image analysing computer device 102
It is again that the result system of the image analysing computer of the scene is whole to complete video streaming analysis.
In one embodiment, when which detects event generation, the image analysing computer of the scene is transferred to
The cloud Analysis Service device come judge the scene have an abnormality as having fire comprising a dangerous goods or the scene
Probability score, then the probability score by the cloud Analysis Service device by the scene with abnormality, such as comprising a danger
Product or the scene have the probability score of fire to be transmitted back to the image analysing computer device.
In one embodiment, image analysing computer device can execute preliminary scene image analysis, when meeting trigger condition, example
Such as: detect it is mobile, detect it is humanoid, detect face, detect invasion, just carry out further scene image analysis,
To reach effective image analysing computer, it is possible to reduce wrong report can also save analysis efficiency, such as scene is Bank Hall, image point
Analysis apparatus analysis finds have new personage to enter, and triggers further image analysing computer at this time, captures the personage and surrounding photo, transfer to
Cloud Analysis Service device judges that the scene has an abnormality such as comprising the probability score of a dangerous goods, then by the cloud
The scene there is the abnormality such as probability score comprising a dangerous goods to be transmitted back to the image analysing computer by end Analysis Service device
Device, to generate alarm.
Claims (19)
1. a kind of distributed image analysis system, characterized by comprising:
Multiple image analysing computer devices, to analyze video streaming;And
One cluster management device is connected to multiple image analysing computer device;
Wherein, when the image analysing computer device in multiple image analysing computer devices is analyzed in one video streaming of execution but can not be individually complete
When being analyzed at the video streaming, the image analysing computer device pass through the cluster management device so that other image analysing computer device and/
Or the cluster management device is analyzed to execute at least part of work of video streaming analysis with completing the video streaming.
2. the system as claimed in claim 1, which is characterized in that the cluster management device distributes at least part of work
To other image analysing computer devices, which is sent to the shadow for the implementing result of at least part of work again
As analytical equipment to complete video streaming analysis.
3. the system as claimed in claim 1, which is characterized in that the cluster management device is connected to cloud Analysis Service dress
It sets, wherein at least part of work includes an image analysing computer, and multiple image analysing computer device, which does not have, executes the image point
The work of the image analysing computer is transferred to the cloud Analysis Service device to execute by the ability of analysis, the cluster management device, then by this
The result of the image analysing computer is sent to the image analysing computer device by cloud Analysis Service device.
4. system as claimed in claim 3, which is characterized in that the cloud Analysis Service device will by the cluster management device
The implementing result of the image analysing computer is sent to the image analysing computer device.
5. system as claimed in claim 3, which is characterized in that the cloud Analysis Service device is by the execution knot of the image analysing computer
Fruit is sent to the image analysing computer device without by the cluster management device.
6. system as claimed in claim 3, which is characterized in that when the image analysing computer device detects event generation, by this
Image analysing computer transfers to the cloud Analysis Service device to execute, to judge that the image has the probability score of an abnormality, then
The probability score is transmitted back to the image analysing computer device by the cloud Analysis Service device.
7. system as claimed in claim 6, which is characterized in that it is by the image that the image analysing computer device, which detects the event,
A preliminary analysis, the event is detected when the preliminary analysis meets a trigger condition.
8. system as claimed in claim 6, which is characterized in that, the image analysing computer device receive an arrangement for detecting information with
Detect the event.
9. system as claimed in claim 6, which is characterized in that, which is that the image includes a dangerous goods or one
Fiery scape.
10. system as claimed in claim 7, which is characterized in that, which is the movement of object.
11. system as claimed in claim 8, which is characterized in that, which is a temperature detection device.
12. a kind of distributed image analysis system, characterized by comprising:
Multiple image analysing computer devices, to analyze video streaming;And
One cluster management device is connected to multiple image analysing computer device, and wherein the cluster management device is connected to a cloud point
Analyse service unit;
Wherein, when the image analysing computer device in multiple image analysing computer devices is analyzed in one video streaming of execution but can not be individually complete
When being analyzed at the video streaming, the image analysing computer device pass through the cluster management device so that other image analysing computer device and/
Or the cloud Analysis Service device executes at least part of work of video streaming analysis, then by the cluster management device
The implementing result of at least part of work is back to the image analysing computer device to complete video streaming analysis.
13. a kind of distributed image analysis system, characterized by comprising:
One image analysing computer device, wherein the image analysing computer device is connected to a cloud Analysis Service device;
Wherein, when the image analysing computer device is when executing video streaming analysis but can not execute an image analysing computer, which divides
The work of the image analysing computer is transferred to the cloud Analysis Service device to execute by analysis apparatus, then will by the cloud Analysis Service device
The implementing result of the image analysing computer is transmitted back to the image analysing computer device to complete video streaming analysis.
14. system as claimed in claim 13, which is characterized in that, will when the image analysing computer device detects event generation
The image analysing computer transfers to the cloud Analysis Service device to execute, to judge that the image has the probability score of an abnormality,
The probability score is transmitted back to the image analysing computer device by the cloud Analysis Service device again.
15. system as claimed in claim 14, which is characterized in that it is by the shadow that the image analysing computer device, which detects the event,
One preliminary analysis of picture, the event is detected when the preliminary analysis meets a trigger condition.
16. system as claimed in claim 14, which is characterized in that the image analysing computer device receive an arrangement for detecting information with
Detect the event.
17. system as claimed in claim 14, which is characterized in that the abnormality is that the image includes a dangerous goods or one
Fiery scape.
18. system as claimed in claim 15, which is characterized in that the trigger condition is the movement of object.
19. system as claimed in claim 16, which is characterized in that the arrangement for detecting is a temperature detection device.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810150471.9A CN110149355A (en) | 2018-02-13 | 2018-02-13 | A kind of distributed image analysis system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810150471.9A CN110149355A (en) | 2018-02-13 | 2018-02-13 | A kind of distributed image analysis system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110149355A true CN110149355A (en) | 2019-08-20 |
Family
ID=67588178
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810150471.9A Pending CN110149355A (en) | 2018-02-13 | 2018-02-13 | A kind of distributed image analysis system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110149355A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111540171A (en) * | 2020-04-28 | 2020-08-14 | 河北地质大学 | Fatigue driving early warning system, corresponding early warning method and construction method |
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101350098A (en) * | 2008-08-19 | 2009-01-21 | 黄建军 | Method, system and equipment for processing image |
JP2010097327A (en) * | 2008-10-15 | 2010-04-30 | Fujitsu Ltd | Data processing system |
CN102760053A (en) * | 2012-06-20 | 2012-10-31 | 东南大学 | Human body detection method based on CUDA (Compute Unified Device Architecture) parallel calculation and WCF framework |
CN102882910A (en) * | 2011-07-15 | 2013-01-16 | 中华电信股份有限公司 | Distributed operation system applied to image monitoring platform |
CN102883145A (en) * | 2012-09-28 | 2013-01-16 | 安科智慧城市技术(中国)有限公司 | Method and system for identifying dynamic objects |
US20130167187A1 (en) * | 2011-12-21 | 2013-06-27 | Thomson Licensing | Processing cluster and method for processing video content |
CN103186649A (en) * | 2011-12-31 | 2013-07-03 | 由田信息技术(上海)有限公司 | Cloud processing system of image analysis |
CN203112272U (en) * | 2012-12-11 | 2013-08-07 | 东芝电梯株式会社 | Elevator control device |
CN104782136A (en) * | 2012-09-28 | 2015-07-15 | 英特尔公司 | Processing video data in a cloud |
CN104822047A (en) * | 2015-04-16 | 2015-08-05 | 中国科学院上海技术物理研究所 | Network-based self-adaptive medical image transmission display method |
US20150256835A1 (en) * | 2014-03-05 | 2015-09-10 | Nec Corporation | Video analysis apparatus, monitoring system, and video analysis method |
US20170046574A1 (en) * | 2014-07-07 | 2017-02-16 | Google Inc. | Systems and Methods for Categorizing Motion Events |
CN106534344A (en) * | 2016-12-07 | 2017-03-22 | 高新兴科技集团股份有限公司 | Cloud platform video processing system and application method thereof |
-
2018
- 2018-02-13 CN CN201810150471.9A patent/CN110149355A/en active Pending
Patent Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101350098A (en) * | 2008-08-19 | 2009-01-21 | 黄建军 | Method, system and equipment for processing image |
JP2010097327A (en) * | 2008-10-15 | 2010-04-30 | Fujitsu Ltd | Data processing system |
CN102882910A (en) * | 2011-07-15 | 2013-01-16 | 中华电信股份有限公司 | Distributed operation system applied to image monitoring platform |
US20130167187A1 (en) * | 2011-12-21 | 2013-06-27 | Thomson Licensing | Processing cluster and method for processing video content |
CN103186649A (en) * | 2011-12-31 | 2013-07-03 | 由田信息技术(上海)有限公司 | Cloud processing system of image analysis |
CN102760053A (en) * | 2012-06-20 | 2012-10-31 | 东南大学 | Human body detection method based on CUDA (Compute Unified Device Architecture) parallel calculation and WCF framework |
CN102883145A (en) * | 2012-09-28 | 2013-01-16 | 安科智慧城市技术(中国)有限公司 | Method and system for identifying dynamic objects |
CN104782136A (en) * | 2012-09-28 | 2015-07-15 | 英特尔公司 | Processing video data in a cloud |
CN203112272U (en) * | 2012-12-11 | 2013-08-07 | 东芝电梯株式会社 | Elevator control device |
US20150256835A1 (en) * | 2014-03-05 | 2015-09-10 | Nec Corporation | Video analysis apparatus, monitoring system, and video analysis method |
US20170046574A1 (en) * | 2014-07-07 | 2017-02-16 | Google Inc. | Systems and Methods for Categorizing Motion Events |
CN104822047A (en) * | 2015-04-16 | 2015-08-05 | 中国科学院上海技术物理研究所 | Network-based self-adaptive medical image transmission display method |
CN106534344A (en) * | 2016-12-07 | 2017-03-22 | 高新兴科技集团股份有限公司 | Cloud platform video processing system and application method thereof |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111540171A (en) * | 2020-04-28 | 2020-08-14 | 河北地质大学 | Fatigue driving early warning system, corresponding early warning method and construction method |
CN111540171B (en) * | 2020-04-28 | 2021-09-10 | 河北地质大学 | Fatigue driving early warning system, corresponding early warning method and construction method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Liu et al. | Caesar: cross-camera complex activity recognition | |
US9667919B2 (en) | Method and system for anonymous video analytics processing | |
WO2005091639A1 (en) | Pipeline architecture for analyzing multiple video streams | |
US10776245B2 (en) | Analyzing physical machine impact on business transaction performance | |
CN106339208A (en) | Multimedia information popup processing method and equipment | |
CN110599728B (en) | Fire early warning method, device, equipment and storage medium based on block chain | |
CN110515808B (en) | Database monitoring method and device, computer equipment and storage medium | |
WO2015090099A1 (en) | Algorithm configuration method and system | |
US10726294B1 (en) | Logical sensor generation in a behavioral recognition system | |
CN112153343B (en) | Elevator safety monitoring method and device, monitoring camera and storage medium | |
WO2013131189A1 (en) | Cloud-based video analytics with post-processing at the video source-end | |
CN112017323A (en) | Patrol alarm method and device, readable storage medium and terminal equipment | |
US10102642B2 (en) | Image driver that samples high-resolution image data | |
CN108288025A (en) | A kind of car video monitoring method, device and equipment | |
JP2020119494A (en) | Distributed image analysis system | |
US9507655B2 (en) | Tracking asynchronous entry points for an application | |
CN110149355A (en) | A kind of distributed image analysis system | |
CN114490280A (en) | Log processing method, device, equipment and medium | |
CN112040090A (en) | Video stream processing method and device, electronic equipment and storage medium | |
CN112419639A (en) | Video information acquisition method and device | |
CN111209566A (en) | Intelligent anti-crawler system and method for multi-layer threat interception | |
US10761203B2 (en) | Decision based re-processing framework for radar technology | |
Lu et al. | TURBO: Opportunistic enhancement for edge video analytics | |
KR102549808B1 (en) | Fire detection system and method based on cloud computing technologies | |
Han et al. | IoT and Cloud Enabled Evidence-Based Smart Decision-Making Platform for Precision Livestock Farming |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190820 |
|
WD01 | Invention patent application deemed withdrawn after publication |