CN109246397A - Multichannel video camera intelligent tracking shooting flock of birds type Sample Method and system - Google Patents
Multichannel video camera intelligent tracking shooting flock of birds type Sample Method and system Download PDFInfo
- Publication number
- CN109246397A CN109246397A CN201811303011.1A CN201811303011A CN109246397A CN 109246397 A CN109246397 A CN 109246397A CN 201811303011 A CN201811303011 A CN 201811303011A CN 109246397 A CN109246397 A CN 109246397A
- Authority
- CN
- China
- Prior art keywords
- target
- camera
- birds
- cruise
- flock
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
Abstract
The present invention provides a kind of multichannel video camera intelligent tracking shooting flock of birds type Sample Method and systems, including establish hardware environment, each camera of cruise control；Moving object segmentation is carried out using optical flow method；Target detection is carried out using background subtraction method, obtains doubtful birds target in camera picture；According to light stream in target area as a result, screening target to be identified；Design automatically tracks rule, carries out mobile tracking to target to be identified and scales；Clearly target to be identified is obtained after scaling, is saved to hard disk and is carried out further category identification.The present invention controls camera by intelligent-tracking and obtains birds picture sample, it realizes automatic control, intelligent-tracking, camera is adjusted according to acquisition result intelligent, greatly improve the quality of flock of birds type sample, the credibility of birds identification is improved, is suitable for semi open model zoo and watches and the plurality of application scenes such as aviation safety detection.
Description
Technical field
The present invention relates to computer vision fields, and in particular, to a kind of multichannel video camera intelligent tracking shooting flock of birds kind
Class Sample Method and system, more particularly, to it is a kind of based on image procossing, automation control, artificial intelligence control video camera from
The sample automatic obtaining method of motion tracking shooting birds picture sample.
Background technique
As nature bring increasingly heavy burden is given in the development of industrial society, people increasingly focus on people and oneself
Right gets along amiably and peacefully.Compared with traditional zoo is ornamental, more and more tourists tend to the semi-open of similar bird's twitter woods formula
Animal excursion district.By taking birds garden as an example, large-size net rack is often set up in this open zoo above mountain valley, is formed
The larger space of relative closure, the free flight therebetween of different types of birds are inhabited, and tourist can watch more active
Small bird enjoys the beautiful and enjoyment of the Nature to the full.However, since birds mobility is larger, habitat is difficult in such zoo
With determination, label how is arranged introducing the relevant information of certain specific birds becomes a urgent problem to be solved.Meanwhile
In aviation industry, birds identification problem also has important application.Birds and aircraft bump against caused aircraft accident, severe one in the sky
Engine can be made to run out of steam, or even make air crash, cause great casualties.Therefore detecting real-time whether there is birds in the air
It is also significant for the safe navigation of aircraft.
The algorithm of traditional birds identification is mostly shape, the still image feature of infrared thermal imaging technique acquisition based on bird
Etc. modes achieve the purpose that birds category identification.These methods require largely, clearly, suitable flock of birds type sample graph
Based on piece, how from actual environment, intelligent control camera, which obtains, is suitble to the flock of birds type sample of identification to be one
The problem of urgent need to resolve.
Patent document CN201426153Y is disclosed for video conference intelligent video camera head control system comprising has Mike
Wind array acquisition sound module, preprocessing module, judging treatmenting module, Speech signal detection module, location Calculation module, camera shooting
Head control module.Its purpose is to provide the source position that one kind can accurately determine sound, control camera is rotated
Timely and accurately take conference speech human face is used for video conference intelligent video camera head control system.But above-mentioned patent text
It offers dependence sound and determines position, distant object such as birds target cannot be accurately positioned.
Patent document CN106780850A provides a kind of camera intelligent recognition vehicle management access control system, including center
Control system, gate mechanism, camera module are handled, the central processing control system is by wirelessly or non-wirelessly connecting gate machine
Structure, the central processing control system are connect with the camera module signal, and the camera module uses two adjustable focus
Multipoint focalizing pick-up lens, the beneficial effect is that: two cameras use infrared auxiliary light source, illumination stablizes, it is photochromic it is single,
Clutter is small, not only solves the problems, such as night identification, and can be improved identification quality and speed；Recognition efficiency is higher, has in character
Anti-interference ability is good when appropriateness is stained, and realizes relatively simple；Intelligent management, it is unattended, save human resources；Full-automatic chemical industry
Operation mode greatly improves working efficiency；Using biological identification technology (recognition of face), security performance is substantially improved；Enjoyment convenience,
Quickly, safe passage treatment；Automatic charging, it is easy to use, it is at low cost.But the camera camera site of above patent document
It is fixed, can not intelligent control camera movement and scaling.
Summary of the invention
For the defects in the prior art, the object of the present invention is to provide a kind of multichannel video camera intelligent tracking shooting flocks of birds
Type Sample Method and system.
A kind of multichannel video camera intelligent tracking shooting flock of birds type Sample Method provided according to the present invention, comprising:
Camera shooting cruise step: deployment multi-cam carries out cruise camera shooting, multichannel video flowing to be identified is obtained, using optical flow method
Multichannel video flowing to be identified is detected, target to be tracked is obtained；
It tracks and identifies step: target to be tracked being tracked and amplified using the intelligent-tracking and scaling of camera, is obtained
To target picture sample.
Preferably, the camera shooting cruise step includes:
Deployed environment step: disposing the hardware environment of multi-cam, and foundation is connect with the video flowing of multi-cam；
Cruise control step: cruise control setting is carried out to multi-cam, the multi-path video stream that multi-cam is formed is comprehensive
Conjunction processing；
Motion detection step: identifying multi-path video stream, detects whether moving object occur using optical flow method, if going out
Existing moving object, then dynamic update background obtains target region by background subtraction, carries out to target region more
Target detection obtains light stream testing result；If not occurring moving object, persistently identify；
Object filtering step: object filtering is carried out according to light stream testing result, target to be tracked is obtained, is denoted as doubtful birds
Target.
Preferably, the step that tracks and identifies includes:
Effective detecting step: effective target is carried out to target to be tracked and there is detection, if it exists effective target, then tracking has
Target is imitated, if it does not exist effective target, then terminate this cruise, starting is cruised next time；
Target following step: carrying out camera lens mobile tracking to effective target, scales effective target, and dynamic updates background, obtains
To target picture sample.
Preferably, the cruise control step includes:
On-the-flier compiler step: under a linux operating system, on-the-flier compiler camera corresponds to library file, forms basic control
Library；
Management of process step: based on basic control library, using multi-process, dynamic management control multi-path video stream is established and is known
The synchronously control management of other process and video flowing process.
Preferably, the optical flow method is sparse optical flow method, carries out optical flow computation to the picture in multichannel video flowing to be identified,
Light stream size, light stream direction are obtained, if light stream size is greater than given threshold, then it represents that there are targets to be tracked, otherwise, then continue
Cruise camera shooting.
Preferably, the target following step includes:
Frame position identification step: determining whether target to be identified is in the center of present frame, if it is not, then triggering camera shooting
Head is mobile, if so, determining the area ratio of target to be identified and present frame；
Frame area identification step: determining the area ratio of target to be identified and present frame, if area ratio meets setting value,
Target identification is then triggered, if area ratio does not meet setting value, triggers camera scaling.
A kind of multichannel video camera intelligent tracking shooting flock of birds type sample system provided according to the present invention, comprising:
Camera shooting cruise module: deployment multi-cam carries out cruise camera shooting, multichannel video flowing to be identified is obtained, using optical flow method
Multichannel video flowing to be identified is detected, target to be tracked is obtained；
It tracks and identifies module: target to be tracked being tracked and amplified using camera intelligent-tracking and scaling strategy,
Obtain clearly target picture sample.
Preferably, the camera shooting cruise module includes:
Deployed environment module: disposing the hardware environment of multi-cam, and foundation is connect with the video flowing of multi-cam；
Cruise control module: cruise control setting is carried out to multi-cam, the multi-path video stream that multi-cam is formed is comprehensive
Conjunction processing；
Motion detection block: identifying multi-path video stream, detects whether moving object occur using optical flow method, if going out
Existing moving object, then dynamic updates background and obtains target region using background subtraction strategy, to target region into
Row multi-target detection obtains light stream testing result；If not occurring moving object, persistently identify；
Object filtering module: object filtering is carried out according to light stream testing result, target to be tracked is obtained, is denoted as doubtful birds
Target.
Preferably, the module that tracks and identifies includes:
Effective detection module: effective target is carried out to target to be tracked and there is detection, if it exists effective target, then tracking has
Target is imitated, if it does not exist effective target, then terminate this cruise, starting is cruised next time；
Target tracking module: carrying out camera lens mobile tracking to effective target, scales effective target, and dynamic updates background, obtains
To clearly target picture sample.
Compared with prior art, the present invention have it is following the utility model has the advantages that
1, present invention is specifically directed to birds scenes to be optimized, by target identification, deep learning etc. at video image
The common technique in reason field is applied to intelligence and obtains in this specific practical application of flock of birds type sample, is greatly promoted
The quality of flock of birds type sample, to improve the credibility of birds identification.
2, the present invention has filled up the blank that intelligent control camera carries out flock of birds type sample acquisition, and sample acquisition is clear；
3, it can be applied to that semi open model zoo is ornamental and aviation safety according to sample adjustment camera is obtained
The plurality of application scenes such as detection.
Detailed description of the invention
Upon reading the detailed description of non-limiting embodiments with reference to the following drawings, other feature of the invention,
Objects and advantages will become more apparent upon:
Fig. 1 is method model frame diagram of the invention；
Fig. 2 is target detection flow chart of the invention；
Fig. 3 is camera intelligent control process figure of the invention.
Specific embodiment
The present invention is described in detail combined with specific embodiments below.Following embodiment will be helpful to the technology of this field
Personnel further understand the present invention, but the invention is not limited in any way.It should be pointed out that the ordinary skill of this field
For personnel, without departing from the inventive concept of the premise, several changes and improvements can also be made.These belong to the present invention
Protection scope.
The present invention discloses the method and system that a kind of video camera intelligent control obtains clear flock of birds type sample, according to multichannel
The hardware environment of camera, the camera video stream based on multi-process obtain, control and recognizer, according to target detection knot
Fruit, intelligent control camera automatically track birds, reach obtain properly identify flock of birds type sample as a result, solving current bird
In class recognizer the problem of actual environment sample acquisition.
A kind of multichannel video camera intelligent tracking shooting flock of birds type Sample Method provided according to the present invention, comprising:
Camera shooting cruise step: deployment multi-cam carries out cruise camera shooting, multichannel video flowing to be identified is obtained, using optical flow method
Multichannel video flowing to be identified is detected, target to be tracked is obtained；
It tracks and identifies step: target to be tracked being tracked and amplified using camera intelligent-tracking and scaling strategy,
Obtain clearly target picture sample.
Specifically, the camera shooting cruise step includes:
Deployed environment step: disposing the hardware environment of multi-cam, and foundation is connect with the video flowing of multi-cam；
Cruise control step: cruise control setting is carried out to multi-cam, the multi-path video stream that multi-cam is formed is comprehensive
Conjunction processing；
Motion detection step: identifying multi-path video stream, detects whether moving object occur using optical flow method, if going out
Existing moving object, then dynamic updates background and obtains target region using background subtraction strategy, to target region into
Row multi-target detection obtains light stream testing result；If not occurring moving object, persistently identify；
Object filtering step: object filtering is carried out according to light stream testing result, target to be tracked is obtained, is denoted as doubtful birds
Target.
Specifically, the step that tracks and identifies includes:
Effective detecting step: effective target is carried out to target to be tracked and there is detection, if it exists effective target, then tracking has
Target is imitated, if it does not exist effective target, then terminate this cruise, starting is cruised next time；
Target following step: carrying out camera lens mobile tracking to effective target, scales effective target, and dynamic updates background, obtains
To clearly target picture sample.
Specifically, the cruise control step includes:
On-the-flier compiler step: under a linux operating system, on-the-flier compiler camera corresponds to library file, forms basic control
Library；
Management of process step: based on basic control library, using multi-process, dynamic management control multi-path video stream is established and is known
The synchronously control management of other process and video flowing process.
Specifically, the optical flow method is sparse optical flow method, carries out optical flow computation to the picture in multichannel video flowing to be identified,
Light stream size, light stream direction are obtained, if light stream size is greater than given threshold, then it represents that there are targets to be tracked, otherwise, then continue
Cruise camera shooting.
Specifically, the target following step includes:
Frame position identification step: determining whether target to be identified is in the center of present frame, if it is not, then triggering camera shooting
Head is mobile, if so, determining the area ratio of target to be identified and present frame；
Frame area identification step: determining the area ratio of target to be identified and present frame, if area ratio meets setting value,
Target identification is then triggered, if area ratio does not meet setting value, triggers camera scaling.
A kind of multichannel video camera intelligent tracking shooting flock of birds type sample system provided according to the present invention, comprising:
Camera shooting cruise module: deployment multi-cam carries out cruise camera shooting, multichannel video flowing to be identified is obtained, using optical flow method
Multichannel video flowing to be identified is detected, target to be tracked is obtained；
It tracks and identifies module: target to be tracked being tracked and amplified using camera intelligent-tracking and scaling strategy,
Obtain clearly target picture sample.
Specifically, the camera shooting cruise module includes:
Deployed environment module: disposing the hardware environment of multi-cam, and foundation is connect with the video flowing of multi-cam；
Cruise control module: cruise control setting is carried out to multi-cam, the multi-path video stream that multi-cam is formed is comprehensive
Conjunction processing；
Motion detection block: identifying multi-path video stream, detects whether moving object occur using optical flow method, if going out
Existing moving object, then dynamic updates background and obtains target region using background subtraction strategy, to target region into
Row multi-target detection obtains light stream testing result；If not occurring moving object, persistently identify；
Object filtering module: object filtering is carried out according to light stream testing result, target to be tracked is obtained, is denoted as doubtful birds
Target.
Specifically, the module that tracks and identifies includes:
Effective detection module: effective target is carried out to target to be tracked and there is detection, if it exists effective target, then tracking has
Target is imitated, if it does not exist effective target, then terminate this cruise, starting is cruised next time；
Target tracking module: carrying out camera lens mobile tracking to effective target, scales effective target, and dynamic updates background, obtains
To clearly target picture sample.
Multichannel video camera intelligent tracking shooting flock of birds type sample system provided by the invention, can pass through multichannel video camera
The step process of intelligent tracking shooting flock of birds type Sample Method is realized.Those skilled in the art can be by multichannel video camera intelligence
Track up flock of birds type Sample Method is interpreted as the excellent of the multichannel video camera intelligent tracking shooting flock of birds type sample system
Select example.
Preference of the invention is further elaborated below in conjunction with attached drawing.
As shown in Figure 1, a kind of multichannel video camera intelligent tracking shooting flock of birds type Sample Method, using intelligent-tracking, control
System, includes the following steps:
Step S1 disposes hardware environment, establishes the connection with multi-cam video flowing；
Step S2, cruise control multi-cam, integrated treatment multi-path video stream；
Step S3 detects whether moving object occur using optical flow algorithm to the multichannel inputted in real time video flowing to be identified
Step S4, if there is moving object, dynamic updates background, obtains target region using background subtraction method,
Carry out multi-target detection；
Step S5 screens target in step S4, obtains doubtful according to the light stream testing result in target region
As birds target；
Step S6 is included in target to be tracked to birds target doubtful in step S5, carries out camera tracking.
Step S7 tracks simultaneously amplification target, detects clearly Target Photo using camera intelligent-tracking and scaling algorithm
Sample, according to testing result feedback control camera.
The step S2 includes the following steps:
Step S2.1, under a linux operating system, on-the-flier compiler camera correspond to library file, form basic control library；
Step S2.2, in the way of multi-process, management multi-path video stream process, control process and identification process.
In the step S2.1 and S2.2, establishes basic control library and management multichannel process includes the following steps:
Step a compiles the dynamic link library under (SuSE) Linux OS with C language, and makes python interface；
Step b utilizes multiprocessing, dynamic management, control multi-path video stream；
Step c establishes the synchronously control management of identification process Yu video flowing process；
In the step S3, using sparse optical flow algorithm, optical flow computation is carried out to picture, obtains light stream size, direction etc.
Information；
In cruise module shown in Fig. 1, setting camera is scaled minimum first, opens cruise, and setting cruise direction is
20 frames of right cruise stop cruise, and the multichannel video flowing to be identified generated to multi-cam carries out light stream detection, when light stream size
When value is greater than given threshold, then target detection is carried out with background subtraction strategy, otherwise, then continues to repeat the right side next time to patrol
Navigate 20 frames.In tracking and identifying module, object filtering to be tracked is carried out according to the result of target detection, when there are effective mesh for discovery
When mark, then pass through the camera lens mobile tracking target of intelligent camera, by scaling target, updates the intelligent operations such as background, detection
The samples pictures of clear target are obtained, after samples pictures are saved, and video camera continuation is fed back to and cruises next time.
As shown in Fig. 2, the step S4 includes the following steps:
Step S4.1, intelligent cruise multi-path camera are complete to obtain camera surrounding enviroment；
Step S4.2, interval carry out the target detection based on background subtraction, the doubtful birds target of Preliminary detection；
In the step S5, with threshold method screening present frame in fair-sized target, and according to the threshold value of S3 light stream into
Row screening.
In terms of the processing to picture, input picture is denoised first, the pretreatment such as gray processing, and subtracted by background
It removes, after contours extract, carries out Morphological scale-space, divide connected region, identify multiple target position coordinates, save Target Photo to hard
Disk.
As shown in figure 3, the step S7 includes the following steps:
Step S7.1, using the positional relationship of target to be identified and current frame center, the movement of corresponding control camera；
Step S7.2, using target to be identified and present frame area ratio relationship, the scaling of corresponding control camera；
Step S7.3 is moved according to obtained in step S7.1 and S7.2 as a result, if target to be identified meets identification clearly
Degree and size requirements carry out screenshot and are stored on hard disk；
Step S7.4 repeats step S7.1~step S7.3, until not having unread knowledge in present frame target to be identified
Until other target.
Present invention is specifically directed to birds scenes to be optimized, by target identification, deep learning etc. in video image processing
The common technique in field is applied to intelligence and obtains in this specific practical application of flock of birds type sample, greatly improves
The quality of flock of birds type sample, to improve the credibility of birds identification.
One skilled in the art will appreciate that in addition to realizing system provided by the invention in a manner of pure computer readable program code
It, completely can be by the way that method and step be carried out programming in logic come so that provided by the invention other than system, device and its modules
System, device and its modules are declined with logic gate, switch, specific integrated circuit, programmable logic controller (PLC) and insertion
The form of controller etc. realizes identical program.So system provided by the invention, device and its modules may be considered that
It is a kind of hardware component, and the knot that the module for realizing various programs for including in it can also be considered as in hardware component
Structure；It can also will be considered as realizing the module of various functions either the software program of implementation method can be Hardware Subdivision again
Structure in part.
Specific embodiments of the present invention are described above.It is to be appreciated that the invention is not limited to above-mentioned
Particular implementation, those skilled in the art can make a variety of changes or modify within the scope of the claims, this not shadow
Ring substantive content of the invention.In the absence of conflict, the feature in embodiments herein and embodiment can any phase
Mutually combination.
Claims (9)
1. a kind of multichannel video camera intelligent tracking shooting flock of birds type Sample Method characterized by comprising
Camera shooting cruise step: deployment multi-cam carries out cruise camera shooting, multichannel video flowing to be identified is obtained, using optical flow method to more
Road video flowing to be identified is detected, and target to be tracked is obtained；
It tracks and identifies step: target to be tracked being tracked and amplified using the intelligent-tracking and scaling of camera, obtains mesh
Mark photo sample.
2. multichannel video camera intelligent tracking shooting flock of birds type Sample Method according to claim 1, which is characterized in that institute
Stating camera shooting cruise step includes:
Deployed environment step: disposing the hardware environment of multi-cam, and foundation is connect with the video flowing of multi-cam；
Cruise control step: cruise control setting is carried out to multi-cam, the multi-path video stream General Office that multi-cam is formed
Reason；
Motion detection step: identifying multi-path video stream, detects whether moving object occur using optical flow method, if transporting
Animal body, then dynamic update background obtains target region by background subtraction, carries out multiple target to target region
Detection, obtains light stream testing result；If not occurring moving object, persistently identify；
Object filtering step: object filtering is carried out according to light stream testing result, target to be tracked is obtained, is denoted as doubtful birds mesh
Mark.
3. multichannel video camera intelligent tracking shooting flock of birds type Sample Method according to claim 1, which is characterized in that institute
It states and tracks and identifies step and include:
Effective detecting step: effective target is carried out to target to be tracked and there is detection, effective target, then track effective mesh if it exists
Mark, effective target, then terminate this cruise if it does not exist, and starting is cruised next time；
Target following step: carrying out camera lens mobile tracking to effective target, scales effective target, and dynamic updates background, obtains mesh
Mark photo sample.
4. multichannel video camera intelligent tracking shooting flock of birds type Sample Method according to claim 2, which is characterized in that institute
Stating cruise control step includes:
On-the-flier compiler step: under a linux operating system, on-the-flier compiler camera corresponds to library file, forms basic control library；
Management of process step: based on basic control library, using multi-process, dynamic management control multi-path video stream, foundation identify into
The synchronously control management of journey and video flowing process.
5. multichannel video camera intelligent tracking shooting flock of birds type Sample Method according to claim 1, which is characterized in that institute
Stating optical flow method is sparse optical flow method, carries out optical flow computation to the picture in multichannel video flowing to be identified, obtains light stream size, light stream
Direction, if light stream size is greater than given threshold, then it represents that there are targets to be tracked, otherwise, then continue cruise camera shooting.
6. multichannel video camera intelligent tracking shooting flock of birds type Sample Method according to claim 3, which is characterized in that institute
Stating target following step includes:
Frame position identification step: determining whether target to be identified is in the center of present frame, if it is not, then triggering camera shifting
It is dynamic, if so, determining the area ratio of target to be identified and present frame；
Frame area identification step: determining the area ratio of target to be identified and present frame, if area ratio meets setting value, touches
Target identification is sent out, if area ratio does not meet setting value, triggers camera scaling.
7. a kind of multichannel video camera intelligent tracking shooting flock of birds type sample system characterized by comprising
Camera shooting cruise module: deployment multi-cam carries out cruise camera shooting, multichannel video flowing to be identified is obtained, using optical flow method to more
Road video flowing to be identified is detected, and target to be tracked is obtained；
It tracks and identifies module: target to be tracked being tracked and amplified using camera intelligent-tracking and scaling strategy, is obtained
Clearly target picture sample.
8. multichannel video camera intelligent tracking shooting flock of birds type sample system according to claim 1, which is characterized in that institute
Stating camera shooting cruise module includes:
Deployed environment module: disposing the hardware environment of multi-cam, and foundation is connect with the video flowing of multi-cam；
Cruise control module: cruise control setting is carried out to multi-cam, the multi-path video stream General Office that multi-cam is formed
Reason；
Motion detection block: identifying multi-path video stream, detects whether moving object occur using optical flow method, if transporting
Animal body, then dynamic update background obtains target region using background subtraction strategy, carries out to target region more
Target detection obtains light stream testing result；If not occurring moving object, persistently identify；
Object filtering module: object filtering is carried out according to light stream testing result, target to be tracked is obtained, is denoted as doubtful birds mesh
Mark.
9. multichannel video camera intelligent tracking shooting flock of birds type sample system according to claim 1, which is characterized in that institute
It states and tracks and identifies module and include:
Effective detection module: effective target is carried out to target to be tracked and there is detection, effective target, then track effective mesh if it exists
Mark, effective target, then terminate this cruise if it does not exist, and starting is cruised next time；
Target tracking module: carrying out camera lens mobile tracking to effective target, scales effective target, and dynamic updates background, obtains clear
Clear target picture sample.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811303011.1A CN109246397A (en) | 2018-11-02 | 2018-11-02 | Multichannel video camera intelligent tracking shooting flock of birds type Sample Method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811303011.1A CN109246397A (en) | 2018-11-02 | 2018-11-02 | Multichannel video camera intelligent tracking shooting flock of birds type Sample Method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109246397A true CN109246397A (en) | 2019-01-18 |
Family
ID=65076698
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811303011.1A Pending CN109246397A (en) | 2018-11-02 | 2018-11-02 | Multichannel video camera intelligent tracking shooting flock of birds type Sample Method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109246397A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110062169A (en) * | 2019-05-13 | 2019-07-26 | Oppo广东移动通信有限公司 | Image pickup method, filming apparatus, terminal device and computer readable storage medium |
| CN110059641A (en) * | 2019-04-23 | 2019-07-26 | 重庆工商大学 | Depth birds recognizer based on more preset points |
| CN110740264A (en) * | 2019-10-31 | 2020-01-31 | 重庆工商职业学院 | intelligent camera data rapid acquisition system and acquisition method |
| CN112004028A (en) * | 2020-09-03 | 2020-11-27 | 杭州宣迅电子科技有限公司 | Intelligent security monitoring management system for smart community based on machine vision |
| CN115019373A (en) * | 2022-06-30 | 2022-09-06 | 北京瑞莱智慧科技有限公司 | Method, device and storage medium for tracking and detecting specific person |
| CN115761802A (en) * | 2022-11-21 | 2023-03-07 | 广东鉴面智能科技有限公司 | Dynamic bird identification method and system |
| CN116086408A (en) * | 2023-04-10 | 2023-05-09 | 山东省青东智能科技有限公司 | Intelligent mapping system based on industrial camera |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101068342A (en) * | 2007-06-05 | 2007-11-07 | 西安理工大学 | Video frequency motion target close-up trace monitoring method based on double-camera head linkage structure |
| US20080232643A1 (en) * | 2007-03-23 | 2008-09-25 | Technion Research & Development Foundation Ltd. | Bitmap tracker for visual tracking under very general conditions |
| CN101572804A (en) * | 2009-03-30 | 2009-11-04 | 浙江大学 | Multi-camera intelligent control method and device |
| CN102307297A (en) * | 2011-09-14 | 2012-01-04 | 镇江江大科茂信息系统有限责任公司 | Intelligent monitoring system for multi-azimuth tracking and detecting on video object |
| CN104966305A (en) * | 2015-06-12 | 2015-10-07 | 上海交通大学 | Foreground detection method based on motion vector division |
| CN107729363A (en) * | 2017-09-06 | 2018-02-23 | 上海交通大学 | Based on GoogLeNet network model birds population identifying and analyzing methods |
-
2018
- 2018-11-02 CN CN201811303011.1A patent/CN109246397A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080232643A1 (en) * | 2007-03-23 | 2008-09-25 | Technion Research & Development Foundation Ltd. | Bitmap tracker for visual tracking under very general conditions |
| CN101068342A (en) * | 2007-06-05 | 2007-11-07 | 西安理工大学 | Video frequency motion target close-up trace monitoring method based on double-camera head linkage structure |
| CN101572804A (en) * | 2009-03-30 | 2009-11-04 | 浙江大学 | Multi-camera intelligent control method and device |
| CN102307297A (en) * | 2011-09-14 | 2012-01-04 | 镇江江大科茂信息系统有限责任公司 | Intelligent monitoring system for multi-azimuth tracking and detecting on video object |
| CN104966305A (en) * | 2015-06-12 | 2015-10-07 | 上海交通大学 | Foreground detection method based on motion vector division |
| CN107729363A (en) * | 2017-09-06 | 2018-02-23 | 上海交通大学 | Based on GoogLeNet network model birds population identifying and analyzing methods |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110059641A (en) * | 2019-04-23 | 2019-07-26 | 重庆工商大学 | Depth birds recognizer based on more preset points |
| CN110062169A (en) * | 2019-05-13 | 2019-07-26 | Oppo广东移动通信有限公司 | Image pickup method, filming apparatus, terminal device and computer readable storage medium |
| CN110740264A (en) * | 2019-10-31 | 2020-01-31 | 重庆工商职业学院 | intelligent camera data rapid acquisition system and acquisition method |
| CN110740264B (en) * | 2019-10-31 | 2021-06-04 | 重庆工商职业学院 | Intelligent camera data rapid acquisition system and acquisition method |
| CN112004028A (en) * | 2020-09-03 | 2020-11-27 | 杭州宣迅电子科技有限公司 | Intelligent security monitoring management system for smart community based on machine vision |
| CN115019373A (en) * | 2022-06-30 | 2022-09-06 | 北京瑞莱智慧科技有限公司 | Method, device and storage medium for tracking and detecting specific person |
| CN115761802A (en) * | 2022-11-21 | 2023-03-07 | 广东鉴面智能科技有限公司 | Dynamic bird identification method and system |
| CN116086408A (en) * | 2023-04-10 | 2023-05-09 | 山东省青东智能科技有限公司 | Intelligent mapping system based on industrial camera |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109246397A (en) | Multichannel video camera intelligent tracking shooting flock of birds type Sample Method and system | |
| Nguyen et al. | A visual real-time fire detection using single shot multibox detector for uav-based fire surveillance | |
| Vaidya et al. | Real-time object detection for visually challenged people | |
| CN108776974B (en) | A kind of real-time modeling method method suitable for public transport scene | |
| CN105898107A (en) | Target object snapping method and system | |
| CN112257569A (en) | Target detection and identification method based on real-time video stream | |
| CN113763424B (en) | Real-time intelligent target detection method and system based on embedded platform | |
| CN109558790B (en) | Pedestrian target detection method, device and system | |
| WO2024051067A1 (en) | Infrared image processing method, apparatus, and device, and storage medium | |
| US20210081668A1 (en) | Method and system for improved object marking in sensor data | |
| CN116601668A (en) | Object segmentation and feature tracking | |
| Yang et al. | Counting crowds using a scale-distribution-aware network and adaptive human-shaped kernel | |
| CN114879891A (en) | Multi-mode man-machine interaction method under self-supervision multi-target tracking | |
| CN114140753A (en) | Method, device and system for identifying marine ship | |
| He et al. | A novel image recognition algorithm of target identification for unmanned surface vehicles based on deep learning | |
| CN102368301A (en) | Moving human body detection and tracking system based on video | |
| Zheng et al. | A lightweight algorithm capable of accurately identifying forest fires from UAV remote sensing imagery | |
| CN110334703B (en) | Ship detection and identification method in day and night image | |
| Li et al. | Image processing and recognition algorithm design in intelligent imaging device system | |
| CN106249895B (en) | Man-machine interaction method and system when a kind of robot environment-identification changes | |
| Shimizu et al. | Development of a person-searching algorithm using an omnidirectional camera and LiDAR for the Tsukuba challenge | |
| CN115018883A (en) | Transmission line unmanned aerial vehicle infrared autonomous inspection method based on optical flow and Kalman filtering | |
| CN114200934A (en) | Robot target following control method and device, electronic equipment and storage medium | |
| Wang et al. | Traffic light and vehicle signal recognition with high dynamic range imaging and deep learning | |
| Pan et al. | Traffic Light Detection for Self-Driving Vehicles Based on Deep Learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190118 |
|
| RJ01 | Rejection of invention patent application after publication |