CN105550670B - A kind of target object dynamically track and measurement and positioning method - Google Patents
A kind of target object dynamically track and measurement and positioning method Download PDFInfo
- Publication number
- CN105550670B CN105550670B CN201610054348.8A CN201610054348A CN105550670B CN 105550670 B CN105550670 B CN 105550670B CN 201610054348 A CN201610054348 A CN 201610054348A CN 105550670 B CN105550670 B CN 105550670B
- Authority
- CN
- China
- Prior art keywords
- image
- target object
- background
- target
- camera
- 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.)
- Expired - Fee Related
Links
Classifications
-
- 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
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
- G06T2207/10021—Stereoscopic video; Stereoscopic image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/247—Aligning, centring, orientation detection or correction of the image by affine transforms, e.g. correction due to perspective effects; Quadrilaterals, e.g. trapezoids
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
A kind of target object dynamically track and measurement and positioning method, this method acquire monitoring area images using two cameras, are updated by monitoring area background dynamics and target object extracts, utilized binocular to identify positioning principle, generate field of view three-dimensional point cloud；Combining target Object Extraction and binocular identify positioning principle, and dynamically track positions target object.The present invention combines visual token with target following in field of video monitoring, is tracked by target dynamic, and the pixel coordinate of image where determining target in conjunction with the three-dimensional point cloud that visual token generates, lock onto target object, and determines its three-dimensional coordinate.When target object enters warning region, system can be sounded an alarm, and achieve the purpose that real-time early warning；The location information of the target object captured provides scientific basis to the practical manipulation of background work personnel.
Description
Technical field
The present invention relates to video security protection and human-computer interaction technique field more particularly to a kind of field of video monitoring target objects
Dynamically track and measurement and positioning method.
Background technique
Currently, video surveillance applications are more prevalent, immeasurable effect is brought to the work of people in safety-security area,
However existing monitoring technology intelligence degree is low, still relies on a large amount of human resources and comes to video content recognition, with reply
Dangerous and emergency event.Most of traditional video monitoring systems can only acquire the video information of monitoring area, the monitoring side
Formula dependent on manually continues working with detect monitoring area burst and unsafe condition, lack to the dangerous information in monitoring area into
Row intelligent early-warning, actual motion need to put into a large amount of manpowers and carry out in real time or ex-post analysis, and the video monitoring mode is passed back
Image cannot provide target object accurate location information, and operator only can rule of thumb speculate the substantially position of target object
It sets, so that the tracking of target object and position inaccurate and lack of wisdom.
Summary of the invention
The present invention provides a kind of target object dynamically track and measurement and positioning method, makes up the picture that traditional video surveillance is passed back
Face cannot provide the deficiency of target object exact position, improve its status for relying on a large amount of human resources, improve video monitoring system
The intelligent level of system.
For this purpose, used technical solution are as follows:
A kind of target object dynamically track and measurement and positioning method, this method acquire monitoring area figures using two cameras
Picture, is updated by monitoring area background dynamics and target object extracts, and is identified positioning principle using binocular, is generated field of view three
Dimension point cloud；Combining target Object Extraction and binocular identify positioning principle, and dynamically track positions target object.
The specific steps of which are as follows:
Step 1, target object extracts: dynamically establishing background picture library and real-time update, assigns to the background of Different Dynamic degree
Different threshold values is given, according to the calculus of differences of image in present image and background picture library as a result, distinguishing the prospect in present image
With background parts, and by background parts update into background picture library；
Step 2, binocular ranging:
(1) it eliminates pattern distortion and camera corrects: using Taylor series expansion and combining addition correction factor, correct institute
Acquire pattern distortion；Using 1612 chessboards demarcate camera as calibration object, maximum by distance minimization, projection
Change principle to be uniformly distributed come the characteristic point ensured in checkerboard image, be obtained using the geometrical relationship of chessboard characteristic point and image characteristic point
Coordinate points are to equation out, to solve camera inside and outside parameter, by the correcting distorted image of intrinsic parameter, obtain more true nature
Image；Angles and positions of two sub-pictures with respect to chessboard are adjusted by outer parameter, export the correction image of row alignment；
(2) images match: while in the multiple image of different visual field photographic subjects objects, left and right camera is searched same
The same characteristic features of image captured by moment difference visual field, analyze difference therein, export same characteristic point on left images
Pixel coordinate difference；
(3) re-projection: by left images same characteristic features point pixel coordinate difference result by triangulation be converted to away from
From exporting the three-dimensional point cloud of multi-view image；
Step 3, target following positions: by any one width current frame image in image captured by the camera of left and right and accordingly
Background image makees difference, the target in dynamic lock image, and extracts it in the pixel coordinate of present frame, in conjunction with binocular ranging life
At three-dimensional point cloud information, determine the three-dimensional point cloud of the target, acquire coordinate of the target object in world coordinate system.
Mixed Gauss model is used in the step 1, weakens and is similar to the disturbing factor that leaf shakes in image, to reduce
Prospect and background interfere with each other；Present frame prospect and background image are efficiently separated according to dynamic threshold, and by present image
Background parts are updated into background picture library；According to the foreground image extracted, the pixel coordinate of image locating for prospect is determined, to calculate
The three-dimensional world coordinate of foreground image provides scientific basis.
The present invention combines visual token with target following in field of video monitoring, is tracked by target dynamic, determines
The pixel coordinate of image where target in conjunction with the three-dimensional point cloud that visual token generates, lock onto target object, and determines that its three-dimensional is sat
Mark.When target object enters warning region, system can be sounded an alarm, and achieve the purpose that real-time early warning；The object captured
The location information of body provides scientific basis to the practical manipulation of background work personnel.
To sum up, the present invention has the advantage that (1) passes through the dynamic background figure of foundation compared with existing video monitoring
Library model can dynamically lock into the target object of monitoring area through image procossing, provide branch for the real-time early warning of safety-security area
Support.(2) binocular range measurement principle is used, the foreground extraction of combining target object can accurately obtain the location information of target object, more
The deficiency of target object precise position information cannot be provided by mending traditional video surveillance, improve the intelligent level of video monitoring.
Detailed description of the invention
Fig. 1 is general principles schematic diagram of the present invention；
Fig. 2 is target object measurement and positioning flow chart of the present invention
Fig. 3 is camera imaging illustraton of model；
Fig. 4 is triangulation schematic diagram.
Specific embodiment
The present invention is described in further detail below in conjunction with the accompanying drawings.
General principles signal of the invention is as shown in Figure 1, acquire binocular image letter by the left and right camera of USB interface
Breath, is handled image through ARM11 development board, captures target object location and geometric size information, be automatic early-warning and
Background work personnel take corresponding measure to provide foundation.
Target object measurement and positioning process in the present invention acquires binocular image information as shown in Fig. 2, passing through left and right camera,
With 1612 chessboards are calibration object, using distance minimization, projection maximization principle stereo calibration camera, acquire camera ginseng
Several and correcting distorted image matches left images characteristic point, and the three-dimensional point cloud of image is generated by triangulation；Dynamic is set
Similarity threshold is set accurately to extract target object, target object pixel coordinate is obtained and is caught in conjunction with generated three-dimensional point cloud
Target object location and geometric size information are caught, provides foundation for human-computer interaction and intelligent early-warning.The specific method is as follows:
Step 1, target object extracts: background picture library and real-time update is dynamically established, to the background of different degree of dynamism
Different threshold values is assigned, image in present image and background picture library is made into difference, when difference result is more than the threshold value of setting, i.e.,
It can determine that present image and background image difference result be more than threshold portion are background, rest part is then prospect.The back of image
Scape part needs to update into background picture library.
Step 2, binocular ranging:
(1) eliminate pattern distortion and camera corrects: ideal camera imaging model is pin-hole model, as shown in figure 3, taking the photograph
As head increases light transmission capacity in actual production, lens are used, but lens can generate error in the manufacture and installation, cause
The image of camera acquisition is distorted.In order to reduce influence of the pattern distortion to image analysis to the greatest extent, selection uses 1612 chesses
Disk demarcates camera as calibration object, solves camera inside and outside parameter.By the correcting distorted image of intrinsic parameter, make image
More true nature；Angles and positions of two sub-pictures with respect to chessboard are adjusted by outer parameter, export row alignment image.
(2) images match: while in the multiple image of different visual field photographic subjects objects, left and right camera is searched same
The same characteristic features of image captured by moment difference visual field export pixel coordinate difference of the same characteristic point on left images.
(3) re-projection: by left images same characteristic features point pixel coordinate difference result by triangulation be converted to away from
From exporting the three-dimensional point cloud of multi-view image.
Step 3, target following positions: by any one width current frame image in image captured by the camera of left and right and accordingly
Background image makees difference, the target in dynamic lock image, and extracts it in the pixel coordinate of present frame, in conjunction with binocular ranging life
At three-dimensional point cloud information, determine the three-dimensional point cloud of the target object, acquire coordinate value of the target object in world coordinate system.
(1) it elaborates about target object extraction in step 1
In video monitoring, dynamic target object is often focus concerned by people, and target object extraction is intelligent monitoring
Core procedure.Based on background model, needs to analyze the difference of image in current frame image and background picture library, work as to extract
The foreground part of prior image frame；However, background image is often illuminated by the light or the influence of complex scene in actual extracting, so that
Threshold value for distinguishing current frame image prospect and background parts is not capable of fixing, and therefore, it is necessary to real-time update background models, constantly
The threshold value of display foreground and background parts is distinguished in adjustment.Present invention introduces mixed Gauss models to be similar to leaf to weaken in image
The disturbing factors such as shake, with interfering with each other for reduction prospect and background.Utilize the matching result of background model and current frame image
S, dynamic adjust matching similarity threshold k.The relationship of matching result s and threshold k is as follows:
Wherein a, b, m are preset parameters；When background changes, threshold k meeting appropriate adjustment is to adapt to background perturbation.
(2) it elaborates about binocular ranging in step 2
Binocular ranging is related to the important content of two large divisions: camera calibration and binocular ranging.
Introduce the basic principle of binocular ranging first before introducing camera calibration.Ideal binocular ranging model is as schemed
Triangulation shown in 4.In Fig. 4, two sub-picture optical axises of pixel column alignment are strictly parallel, and (optical axis is projection centre towards principal point
The ray that the direction c is drawn)WithRespectively left and right projection centre,WithThe focal length of respectively two cameras and equal,
Principal pointWithThe pixel coordinate having the same on left images, imaging point of the characteristic point X on left images are respectively
With,WithHorizontal displacement is respectively in respective pixel coordinate systemWith, parallax are as follows:If f is to take the photograph
As it is as follows can to release equation of the object from cam lens distance Z using similar triangle theory for the focal length of head:
In order to establish ideal binocular ranging platform, need to carry out stereo calibration, the imaging model of camera to camera
As shown in Figure 3.With 16As camera calibration object, the point characterized by black and white lattice crosspoint passes through the chessboard that 12 black and white lattice intersect
Chessboard characteristic point is established in the transformation such as Matrix Translation, rotationAnd image characteristic pointBetween contact,
Equation is established, solves the parameters such as focal length, the distortion factor of camera using least square scheduling algorithm.
Traditional camera calibration uses 9The chessboard that 6 black and white lattice intersect shares 54 schools as calibration object, the chessboard one
Positive characteristic point, correction feature point is less, and there are blind areas when leading to fractional distortion regional correction, influences visual token precision.This hair
It is bright to use intensive chessboard (1612) it is used as camera calibration object, while using distance minimization, projection maximization principle, being had
Following advantage: there are more correction feature points in unit area image, can be in the hope of the higher distortion factor of accuracy；Distance is most
Smallization, projection maximization principle maximize checkerboard image in the screen accounting of field of view, it is ensured that field of view characteristic point
It is uniformly distributed, improves stated accuracy.This low coverage multiple spot camera calibration mode can improve camera calibration precision, improve image
Flake phenomenon, promote binocular ranging efficiency, improve visual token precision.
Effect of the invention is further illustrated below by specific application scenarios:
Scene 1: video monitoring safety-security area real-time early warning.Traditional monitor mode needs staff to check prison for a long time
Video is controlled to achieve the purpose of real-time monitoring, depends on a large amount of human resources, the efficiency and intelligent level of monitoring are lower.
Present invention dynamic establishes background model and real-time update, extracts foreground image by image difference operation, fixed in conjunction with binocular identification
Position principle, dynamically track simultaneously position target object, realize real-time early warning.The present invention provides a large amount of manpowers in traditional video surveillance
Source frees from real work, improves the intelligent level of monitoring system.
Scene 2: visual token.Common distance measuring method has laser ranging, infrared distance measurement, ultrasonic distance measurement, radar range finding
Deng, visual token of the present invention compared with these types of distance measuring method, when measurement, is not required to issue any letter to testee
Number, principle is simple, at low cost, can measure target object location under complex environment.Meanwhile it if being selected in space by mouse
Characteristic point can calculate distance and relative positional relationship between characteristic point using Pythagorean theorem, sine and cosine theorem etc., further count
Calculate the geometric size information of target object.
Scene 3: object edge detection.Common Edge-Detection Algorithm, often through analysis variation of image grayscale
Single order or second dervative obtain the profile information of object, and the type edge detection algorithm cannot be to target object in complex scene
Profile information is effectively extracted.The present invention can by drawing function according to the depth information that vision measurement generates three-dimensional point cloud
The profile of different depth object is drawn, realizes and accurately extracts specified objects' contour in multiple foreground objects.This method can
The fields such as autonomous intelligence operation and vision guided navigation for robot.
Scene 4: human-computer interaction.Most of traditional video monitoring systems only acquire the video information of monitoring area, the prison
Prosecutor formula is that the transinformation content that staff provides is insufficient, and staff need to combine the micro-judgment of oneself and speculate object
The approximate location of body, heavy workload, precision are low.The present invention identifies positioning principle according to binocular, obtains the three-dimensional point of field of view
Cloud, combining target Object Extraction determine the location information of target object, provide foundation for the decision of staff.
To sum up, the present invention simulates the mode of human eye processing scenery, partially understands instead of things of the human brain to nature
And understanding, the three-dimensional point cloud of field of view is generated based on binocular range measurement principle；Based on the background picture library model that dynamic updates, pass through
Image difference operation obtains target object image pixel coordinate；In conjunction with the three-dimensional point cloud information and target object figure of field of view
As pixel coordinate, the dynamically track and positioning of target object are realized.
Claims (2)
1. a kind of target object dynamically track and measurement and positioning method, it is characterised in that: this method is acquired using two cameras
Monitoring area image, is updated by monitoring area background dynamics and target object extracts, and is identified positioning principle using binocular, is generated
Field of view three-dimensional point cloud: combining target Object Extraction and binocular identify positioning principle, and dynamically track positions target object, specifically
Include:
Step 1, target object extracts: dynamically establishing background picture library and real-time update, assigns not to the background of Different Dynamic degree
Same threshold value, according to the calculus of differences of image in present image and background picture library as a result, distinguishing the prospect and back in present image
Scape part, and background parts are updated into background picture library；
Step 2, binocular ranging:
(1) it eliminates pattern distortion and camera corrects: using Taylor series expansion and combining addition correction factor, correction is acquired
Pattern distortion: camera is demarcated as calibration object using 16*12 chessboard, is maximized by distance minimization, projection former
Then the characteristic point to ensure in checkerboard image is uniformly distributed, and obtains seat using the geometrical relationship of chessboard characteristic point and image characteristic point
Punctuate is to equation, to solve camera inside and outside parameter, by the correcting distorted image of intrinsic parameter, obtains the figure of more true nature
Picture: angles and positions of two sub-pictures with respect to chessboard are adjusted by outer parameter, export the correction image of row alignment；
(2) images match: while in the multiple image of different visual field photographic subjects objects, left and right camera is searched in synchronization
The same characteristic features of image captured by different visual fields analyze difference therein, export pixel of the same characteristic point on left images
Coordinate difference；
(3) re-projection: being converted to distance by triangulation for left images same characteristic features point pixel coordinate difference result, defeated
The three-dimensional point cloud of multi-view image out；
Step 3, target following positions: by any one width current frame image and respective background in image captured by the camera of left and right
Image makees difference, the target in dynamic lock image, and extracts it in the pixel coordinate of present frame, generates in conjunction with binocular ranging
Three-dimensional point cloud information determines the three-dimensional point cloud of the target, acquires coordinate of the target object in world coordinate system.
2. a kind of target object dynamically track according to claim 1 and measurement and positioning method, it is characterised in that: the step
Mixed Gauss model is used in rapid 1, weakens the disturbing factor in image, it is described dry with interfering with each other for reduction prospect and background
Factor is disturbed as leaf shaking；Present frame prospect and background image are efficiently separated according to dynamic threshold, and by the background portion of present image
Divide and updates into background picture library；According to the foreground image extracted, the pixel coordinate of image locating for prospect is determined, to calculate foreground picture
The three-dimensional world coordinate of picture provides scientific basis.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610054348.8A CN105550670B (en) | 2016-01-27 | 2016-01-27 | A kind of target object dynamically track and measurement and positioning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610054348.8A CN105550670B (en) | 2016-01-27 | 2016-01-27 | A kind of target object dynamically track and measurement and positioning method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105550670A CN105550670A (en) | 2016-05-04 |
| CN105550670B true CN105550670B (en) | 2019-07-12 |
Family
ID=55829853
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610054348.8A Expired - Fee Related CN105550670B (en) | 2016-01-27 | 2016-01-27 | A kind of target object dynamically track and measurement and positioning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105550670B (en) |
Families Citing this family (36)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106598075A (en) * | 2016-07-21 | 2017-04-26 | 深圳曼塔智能科技有限公司 | System and method for tracking control of unmanned aerial vehicle based on luminescence object identification |
| CN108090922A (en) * | 2016-11-21 | 2018-05-29 | 中国科学院沈阳计算技术研究所有限公司 | Intelligent Target pursuit path recording method |
| CN108087208A (en) * | 2016-11-21 | 2018-05-29 | 北京金风科创风电设备有限公司 | Wind generator set blade follower method and device based on unmanned plane |
| CN106447680B (en) * | 2016-11-23 | 2019-09-17 | 湖南华诺星空电子技术有限公司 | The object detecting and tracking method that radar is merged with vision under dynamic background environment |
| CN108537094B (en) * | 2017-03-03 | 2022-11-22 | 株式会社理光 | Image processing method, device and system |
| CN108664841B (en) * | 2017-03-27 | 2021-05-11 | 郑州宇通客车股份有限公司 | Dynamic and static target object identification method and device based on laser point cloud |
| CN108731587A (en) * | 2017-04-14 | 2018-11-02 | 中交遥感载荷（北京）科技有限公司 | A kind of the unmanned plane dynamic target tracking and localization method of view-based access control model |
| CN107122770B (en) * | 2017-06-13 | 2023-06-27 | 驭势（上海）汽车科技有限公司 | Multi-camera system, intelligent driving system, automobile, method and storage medium |
| CN107246696A (en) * | 2017-06-27 | 2017-10-13 | 上海卓思智能科技股份有限公司 | A kind of vent cabinet windowing area measuring method and system and a kind of controller |
| CN107367767A (en) * | 2017-06-27 | 2017-11-21 | 上海卓思智能科技股份有限公司 | A kind of vent cabinet window foreign matter detecting method and system and a kind of controller |
| CN107773248A (en) * | 2017-09-30 | 2018-03-09 | 优视眼动科技（北京）有限公司 | Eye tracker and image processing method |
| CN107884767A (en) * | 2017-10-31 | 2018-04-06 | 暨南大学 | A kind of method of binocular vision system measurement ship distance and height |
| CN107992820B (en) * | 2017-11-29 | 2021-08-03 | 北京伟景智能科技有限公司 | Self-help goods selling method for container based on binocular vision |
| CN108961155B (en) * | 2018-07-13 | 2023-06-27 | 惠州市德赛西威汽车电子股份有限公司 | High-fidelity fisheye lens distortion correction method |
| CN108989686B (en) * | 2018-09-05 | 2021-02-19 | 深圳技威时代科技有限公司 | Real-time shooting device based on human shape tracking and control method |
| CN109051321A (en) * | 2018-09-14 | 2018-12-21 | 山东上拓教育咨询有限公司 | A kind of fresh commodities circulating cases of the low temperature that intelligence follows automatically |
| CN108829116B (en) * | 2018-10-09 | 2019-01-01 | 上海岚豹智能科技有限公司 | Barrier-avoiding method and equipment based on monocular cam |
| CN109523592A (en) * | 2018-10-19 | 2019-03-26 | 天津大学 | A kind of interior flame localization method based on camera |
| CN109934873B (en) * | 2019-03-15 | 2021-11-02 | 百度在线网络技术（北京）有限公司 | Method, device and equipment for acquiring marked image |
| CN110298293B (en) * | 2019-06-25 | 2020-08-07 | 重庆紫光华山智安科技有限公司 | Anti-lost method and device, readable storage medium and electronic terminal |
| CN110342134B (en) * | 2019-07-23 | 2023-06-09 | 珠海一微半导体股份有限公司 | Garbage classification and identification system and method based on binocular vision |
| CN110595443A (en) * | 2019-08-22 | 2019-12-20 | 苏州佳世达光电有限公司 | Projection device |
| CN110673607B (en) * | 2019-09-25 | 2023-05-16 | 优地网络有限公司 | Feature point extraction method and device under dynamic scene and terminal equipment |
| CN113077511B (en) * | 2020-01-06 | 2022-06-10 | 魔门塔(苏州)科技有限公司 | Multi-camera target matching and tracking method and device for automobile |
| CN111429523B (en) * | 2020-03-16 | 2021-06-15 | 天目爱视（北京）科技有限公司 | Remote calibration method in 3D modeling |
| CN111640300B (en) * | 2020-04-28 | 2022-06-17 | 武汉万集信息技术有限公司 | Vehicle detection processing method and device |
| CN111583334B (en) * | 2020-05-26 | 2023-03-14 | 广东电网有限责任公司培训与评价中心 | Three-dimensional space positioning method, device and equipment for transformer substation personnel |
| CN112348493A (en) * | 2021-01-07 | 2021-02-09 | 北京电信易通信息技术股份有限公司 | Intelligent conference recording system and method |
| CN112819770B (en) * | 2021-01-26 | 2022-11-22 | 中国人民解放军陆军军医大学第一附属医院 | Iodine contrast agent allergy monitoring method and system |
| CN113221909B (en) * | 2021-05-12 | 2023-01-31 | 佛山育脉科技有限公司 | Image processing method, image processing apparatus, and computer-readable storage medium |
| CN113688724B (en) * | 2021-08-24 | 2023-03-24 | 桂林电子科技大学 | Swimming pool drowning monitoring method based on binocular vision |
| CN114267155A (en) * | 2021-11-05 | 2022-04-01 | 国能大渡河革什扎水电开发有限公司 | Geological disaster monitoring and early warning system based on video recognition technology |
| CN113923420B (en) * | 2021-11-18 | 2024-05-28 | 京东方科技集团股份有限公司 | Region adjustment method and device, camera and storage medium |
| CN114283119B (en) * | 2021-12-02 | 2022-12-13 | 上海韦地科技集团有限公司 | Irradiation-resistant camera control system |
| CN113965733A (en) * | 2021-12-07 | 2022-01-21 | 中国联合网络通信集团有限公司 | Binocular video monitoring method, system, computer equipment and storage medium |
| CN114993244A (en) * | 2022-05-09 | 2022-09-02 | 深圳供电局有限公司 | Target ranging device and method for power transformation operation area |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103868460A (en) * | 2014-03-13 | 2014-06-18 | 桂林电子科技大学 | Parallax optimization algorithm-based binocular stereo vision automatic measurement method |
| CN103903279A (en) * | 2014-03-21 | 2014-07-02 | 上海大学 | Parallel tracking system and method based on bionic binocular vision onboard platform |
| CN104463906A (en) * | 2014-11-11 | 2015-03-25 | 广东中星电子有限公司 | Object tracking device and method |
-
2016
- 2016-01-27 CN CN201610054348.8A patent/CN105550670B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103868460A (en) * | 2014-03-13 | 2014-06-18 | 桂林电子科技大学 | Parallax optimization algorithm-based binocular stereo vision automatic measurement method |
| CN103903279A (en) * | 2014-03-21 | 2014-07-02 | 上海大学 | Parallel tracking system and method based on bionic binocular vision onboard platform |
| CN104463906A (en) * | 2014-11-11 | 2015-03-25 | 广东中星电子有限公司 | Object tracking device and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105550670A (en) | 2016-05-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105550670B (en) | A kind of target object dynamically track and measurement and positioning method | |
| CN108731587A (en) | A kind of the unmanned plane dynamic target tracking and localization method of view-based access control model | |
| EP3588004B1 (en) | Stereoscopic camera and height acquisition method therefor and height acquisition system | |
| WO2017080102A1 (en) | Flying device, flying control system and method | |
| CN109211207B (en) | Screw identification and positioning device based on machine vision | |
| CN109215063A (en) | A kind of method for registering of event triggering camera and three-dimensional laser radar | |
| US20130208948A1 (en) | Tracking and identification of a moving object from a moving sensor using a 3d model | |
| WO2019062056A1 (en) | Smart projection method and system, and smart terminal | |
| CN114641809B (en) | Motion timing based on camera system | |
| CN110132226A (en) | The distance and azimuth angle measurement system and method for a kind of unmanned plane line walking | |
| CN103852060A (en) | Visible light image distance measuring method based on monocular vision | |
| Neves et al. | Acquiring high-resolution face images in outdoor environments: A master-slave calibration algorithm | |
| Jeges et al. | Measuring human height using calibrated cameras | |
| CN110909617B (en) | Living body face detection method and device based on binocular vision | |
| CN109035343A (en) | A kind of floor relative displacement measurement method based on monitoring camera | |
| CN110909571B (en) | High-precision face recognition space positioning method | |
| CN102930554B (en) | Method and system for accurately capturing target in monitored scene | |
| KR101733657B1 (en) | System for object counter using camera based on range image and counting method thereof | |
| CN103186233A (en) | Panoramic interaction control method for eye location | |
| CN115880643B (en) | Social distance monitoring method and device based on target detection algorithm | |
| Kochi et al. | 3D modeling of architecture by edge-matching and integrating the point clouds of laser scanner and those of digital camera | |
| CN116580107A (en) | Cross-view multi-target real-time track tracking method and system | |
| TWI502162B (en) | Twin image guiding-tracking shooting system and method | |
| CN112767452B (en) | Active sensing method and system for camera | |
| CN109492513A (en) | The face space De-weight method of light field monitoring |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190712 Termination date: 20220127 |