CN105761279A - Method for tracking object based on track segmenting and splicing - Google Patents
Method for tracking object based on track segmenting and splicing Download PDFInfo
- Publication number
- CN105761279A CN105761279A CN201610089780.0A CN201610089780A CN105761279A CN 105761279 A CN105761279 A CN 105761279A CN 201610089780 A CN201610089780 A CN 201610089780A CN 105761279 A CN105761279 A CN 105761279A
- Authority
- CN
- China
- Prior art keywords
- tracklet
- obj
- track
- target
- frame
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a method for tracking an object based on track segmenting and splicing, aimed at addressing the technical problem of poor accuracy of current object tracking methods. The technical solution comprises the following steps: first initializing a track of each object, then conducting effective segmentation on the tracks in accordance with the degree of coincidence between associated results and track history information, performing accurate splicing on the segmented tracks, finally performing splicing on the tracks among framing windows based on the degree of overlapping so as to obtain a final track of the object. The method of the invention addresses the problems of lost tracking and wrong tracking of current multi-object tracking methods in the absence of appearance information of the object, and realizes more accurate multi-object tracking.
Description
Technical field
The present invention relates to a kind of method for tracking target, particularly relate to a kind of method for tracking target based on track segmentation with splicing.
Background technology
Target following technology all has in military affairs or civil area and is extremely widely applied.Effective data association is the key solving multiple target tracking problem.Data association is deriving from the process that the metric data of single or multiple sensor and known track carry out being mutually paired.The Hungary Algorithm that Edmonds proposes is to solve for the classic algorithm of two dimension assignment problem optimal solution.
Document " Robustobjecttrackingbyhierarchicalassociationofdetection responses; ComputerVision ECCV2008.SpringerBerlinHeidelberg, 2008:788-801 " proposes a kind of method for tracking target based on individual-layer data association.The document, when using Hungary Algorithm to carry out second layer data association, only accounts for the spatial information of target, such as the direction of the distance between target, path segment.When there is target occlusion problem in image sequence, the information of the target that is blocked can produce loss in various degree.If only with spatial information as the input of data association, it is impossible to exactly the position of target is judged, it is easy to produce leakage with or mistake with phenomenon.
Summary of the invention
In order to overcome the deficiency of the accurate rate variance of existing method for tracking target, the present invention provides a kind of method for tracking target based on track segmentation with splicing.First the method initializes the track of each target, then track is effectively split by the matching degree according to association results Yu track historical information, again the track after segmentation is accurately spliced, finally the track between frame window is carried out splicing according to degree of overlapping and obtain the final track of target.The present invention compensate for when lack target appearance information, the leakage of existing multi-object tracking method with and mistake with phenomenon, it is achieved that more accurate multiple target tracking.
The technical solution adopted for the present invention to solve the technical problems is: a kind of method for tracking target based on track segmentation and splicing, is characterized in comprising the following steps:
Step one, one initialization constants f of setting0, when picture numbers frameNo meets 0 < frameNo < f0Time, to the object detection results Object in two adjacent two field pictures1={ obj11,obj12..., obj1mAnd Object2={ obj21,obj22..., obj2m, calculation cost matrix
Wherein, costijFor obj1iWith obj2jBetween Euclidean distance, be calculated as follows:
By cost matrixAs the input matrix of data association, with Hungarian Method, obtain coupling matrixIf obj1iWith obj2jThe match is successful, then by obj2jIt is stored in obj1iTrack in the middle of.By all images in this procedure ergodic initialization constants, obtain the initialization path segment tracklet of each targeti.With method of least square, path segment being carried out conic fitting and try to achieve fitting parameter param, the curvilinear equation of matching is: Ax2+ Bx+C=0.
As picture numbers frameNo > f0Time, adjacent two two field picture Hungary Algorithms are carried out data association, and judges whether the path segment after association meets segmentation condition.Segmentation condition is:
simi(param(trackleti),param(trackleti+obj2j))>simithreshold(4)
Wherein, sizethreshold is the minimum dimension of target, and simithreshold is the similarity threshold of path segment.If obj1iWith obj2jThe match is successful, if meeting segmentation condition, then splits obj at present frame1iPath segment, namely terminate trackleti, by obj associated with it2jAs emerging target.By said process, the every two field picture in traversal frame window, namely obtains the path segment set split in present frame window successively.
Step 2, to input path segment set construct its cost matrix costn*n.Cost in matrixijFor trackletiWith trackletjBetween distinctiveness ratio, be calculated as follows:
costij=w1*distij+w2*frameGapij+w3*direDiffij+w4*veloDiffij(5)
Wherein, distij, frameGapij, direDiffij, veloDiffijRespectively trackletiWith trackletjBetween space length, frame is poor, and speed difference and direction are poor, are respectively calculated as follows:
Wherein, (xstartj,ystartj) for trackletjTrack initial frame in target location, (xendi,yendi) for trackletiTrack end frame in target location.
frameGapij=startFramej-endFramei(7)
Wherein, startFramejFor trackletjTrack initial frame number, endFrameiFor trackletiTrack end frame sequence number.
direDiffij=cos (Line (trackleti))-cos(Line(trackletj))(8)
Wherein, cos (Line (trackleti)) for trackletiThe cosine value of orbit tangent.
veloDiffij=| veloi-veloj|(9)
Wherein, veloiFor trackletiIn target velocity, velojFor in target velocity.
According to frameGapijJudge whether have blank frame between the path segment being successfully associated every a pair.If frameGapij=0, then according to frame sequential by this path segment splicing to being successfully associated.If frameGapij≠ 0, then need the position calculating target at disappearance frame place, splice according still further to frame sequential.Target is at the position (x at blank frame miss placemiss,ymiss) historical information of application target estimates:
xmiss=(xestimatei+xestimatej)/2(10)
xestimatei=endLocationi+veloi*(miss-endFramei)(11)
xestimatej=startLocationj+veloj*(startFramej-miss)(12)
Wherein, xestimateiAnd xestimatejRespectively according to track trackletiAnd trackletjThe target that goes out of data-evaluation in the position of the x coordinate at miss place.veloiAnd velojRespectively according to trackletiAnd trackletjTrace information repeatedly estimate the target the tried to achieve average speed at this section of track.Estimate the target position at each blank frame place by this process, finally three sections of tracks are spliced to form long path segment according to frame sequential.
Overlap between step 3, each two consecutive frame window is overlap frame, carries out the screening of preliminary candidate track accordingly:
After obtaining the candidate tracks of every section of track, retraining with other space time informations of track, that tries to achieve every section of track finally splices track.Spliced track is the arithmetic average of target location in two sections of tracks in the target location at overlapping frame overlap place.
The invention has the beneficial effects as follows: first initialize the track of each target, then track is effectively split by the matching degree according to association results Yu track historical information, again the track after segmentation is accurately spliced, finally the track between frame window is carried out splicing according to degree of overlapping and obtain the final track of target.The present invention compensate for when lack target appearance information, the leakage of existing multi-object tracking method with and mistake with phenomenon, it is achieved that more accurate multiple target tracking.
Below in conjunction with detailed description of the invention, the present invention is elaborated.
Detailed description of the invention
The present invention specifically comprises the following steps that based on the method for tracking target of track segmentation with splicing
1. in frame window, path segment generates and segmentation.
Set an initialization constants f0, when picture numbers frameNo meets 0 < frameNo < f0Time, to the object detection results Object in two adjacent two field pictures1={ obj11,obj12..., obj1mAnd Object2={ obj21,obj22..., obj2m, calculation cost matrix
Wherein, costijFor obj1iWith obj2jBetween Euclidean distance, be calculated as follows:
By cost matrixAs the input matrix of data association, with Hungarian Method, obtain coupling matrixIf obj1iWith obj2jThe match is successful, then by obj2jIt is stored in obj1iTrack in the middle of.By all images in this procedure ergodic initialization constants, obtain the initialization path segment tracklet of each targeti.With method of least square, path segment is carried out conic fitting and try to achieve fitting parameter param (trackleti), the curvilinear equation of matching is: Ax2+ Bx+C=0.
As picture numbers frameNo > f0Time, adjacent two two field picture Hungary Algorithms are carried out data association, and judges whether the path segment after association meets segmentation condition.Segmentation condition is:
simi(param(trackleti),param(trackleti+obj2j))>simithreshold(4)
Wherein, sizethreshold is the minimum dimension of target, and simithreshold is the similarity threshold of path segment.If obj1iWith obj2jThe match is successful, if meeting segmentation condition, then splits obj at present frame1iPath segment, namely terminate trackleti, by obj associated with it2jAs emerging target.By said process, the every two field picture in traversal frame window, namely obtains the path segment set split in present frame window successively.
2. path segment splicing in frame window.
First, the path segment set of input is constructed its cost matrixCost in matrixijFor trackletiWith trackletjBetween distinctiveness ratio, be calculated as follows:
costij=w1*distij+w2*frameGapij+w3*direDiffij+w4*veloDiffij(5)
Wherein distij, frameGapij, direDiffij, veloDiffijRespectively trackletiWith trackletjBetween space length, frame is poor, and speed difference and direction are poor, are respectively calculated as follows:
Wherein, (xstartj,ystartj) for trackletjTrack initial frame in target location, (xendi,yendi) for trackletiTrack end frame in target location.
frameGapij=startFramej-endFramei(7)
Wherein, startFramejFor trackletjTrack initial frame number, endFrameiFor trackletiTrack end frame sequence number.
direDiffij=cos (Line (trackleti))-cos(Line(trackletj))(8)
Wherein, cos (Line (trackleti)) for trackletiThe cosine value of orbit tangent.
veloDiffij=| veloi-veloj|(9)
Wherein, veloiFor trackletiIn target velocity, velojFor in target velocity.
According to frameGapijJudge whether have blank frame between the path segment being successfully associated every a pair.If frameGapij=0, then according to frame sequential by this path segment splicing to being successfully associated.If frameGapij≠ 0, then need the position calculating target at disappearance frame place, splice according still further to frame sequential.Target is at the position (x at blank frame miss placemiss,ymiss) historical information of application target estimates:
xmiss=(xestimatei+xestimatej)/2(10)
xestimatei=endLocationi+veloi*(miss-endFramei)(11)
xestimatej=startLocationj+veloj*(startFramej-miss)(12)
Wherein, xestimateiAnd xestimatejRespectively according to track trackletiAnd trackletjThe target that goes out of data-evaluation in the position of the x coordinate at miss place.veloiAnd velojRespectively according to trackletiAnd trackletjTrace information repeatedly estimate the target the tried to achieve average speed at this section of track.Estimate the target position at each blank frame place by this process, finally three sections of tracks are spliced to form long path segment according to frame sequential.
3. the splicing of long path segment and track output between frame window.
Overlap between each two consecutive frame window is overlap frame, therefore in two frame windows, the track of same target has certain overlap.Carry out the screening of preliminary candidate track accordingly:
After obtaining the candidate tracks of every section of track accordingly, retrain with other space time informations of track, such as veloDiffijAnd direDiffij, that tries to achieve every section of track finally splices track.Spliced track is the arithmetic average of target location in two sections of tracks in the target location at overlapping frame overlap place.
Claims (1)
1. the method for tracking target based on track segmentation with splicing, it is characterised in that comprise the following steps:
Step one, one initialization constants f of setting0, when picture numbers frameNo meets 0 < frameNo < f0Time, to the object detection results Object in two adjacent two field pictures1={ obj11,obj12..., obj1mAnd Object2={ obj21,obj22..., obj2m, calculation cost matrix
Wherein, costijFor obj1iWith obj2jBetween Euclidean distance, be calculated as follows:
By cost matrix costm*nAs the input matrix of data association, with Hungarian Method, obtain coupling matrix associatem*n;If obj1iWith obj2jThe match is successful, then by obj2jIt is stored in obj1iTrack in the middle of;By all images in this procedure ergodic initialization constants, obtain the initialization path segment tracklet of each targeti;With method of least square, path segment being carried out conic fitting and try to achieve fitting parameter param, the curvilinear equation of matching is: Ax2+ Bx+C=0;
As picture numbers frameNo > f0Time, adjacent two two field picture Hungary Algorithms are carried out data association, and judges whether the path segment after association meets segmentation condition;Segmentation condition is:
simi(param(trackleti),param(trackleti+obj2j))>simithreshold(4)
Wherein, sizethreshold is the minimum dimension of target, and simithreshold is the similarity threshold of path segment;If obj1iWith obj2jThe match is successful, if meeting segmentation condition, then splits obj at present frame1iPath segment, namely terminate trackleti, by obj associated with it2jAs emerging target;By said process, the every two field picture in traversal frame window, namely obtains the path segment set split in present frame window successively;
Step 2, to input path segment set construct its cost matrix costn*n;Cost in matrixijFor trackletiWith trackletjBetween distinctiveness ratio, be calculated as follows:
costij=w1*distij+w2*frameGapij+w3*direDiffij+w4*veloDiffij(5)
Wherein, distij, frameGapij, direDiffij, veloDiffijRespectively trackletiWith trackletjBetween space length, frame is poor, and speed difference and direction are poor, are respectively calculated as follows:
Wherein, (xstartj,ystartj) for trackletjTrack initial frame in target location, (xendi,yendi) for trackletiTrack end frame in target location;
frameGapij=startFramej-endFramei(7)
Wherein, startFramejFor trackletjTrack initial frame number, endFrameiFor trackletiTrack end frame sequence number;
direDiffij=cos (Line (trackleti))-cos(Line(trackletj))(8)
Wherein, cos (Line (trackleti)) for trackletiThe cosine value of orbit tangent;
veloDiffij=| veloi-veloj|(9)
Wherein, veloiFor trackletiIn target velocity, velojFor in target velocity;
According to frameGapijJudge whether have blank frame between the path segment being successfully associated every a pair;If frameGapij=0, then according to frame sequential by this path segment splicing to being successfully associated;If frameGapij≠ 0, then need the position calculating target at disappearance frame place, splice according still further to frame sequential;Target is at the position (x at blank frame miss placemiss,ymiss) historical information of application target estimates:
xmiss=(xestimatei+xestimatej)/2(10)
xestimatei=endLocationi+veloi*(miss-endFramei)(11)
xestimatej=startLocationj+veloj*(startFramej-miss)(12)
Wherein, xestimateiAnd xestimatejRespectively according to track trackletiAnd trackletjThe target that goes out of data-evaluation in the position of the x coordinate at miss place;veloiAnd velojRespectively according to trackletiAnd trackletjTrace information repeatedly estimate the target the tried to achieve average speed at this section of track;Estimate the target position at each blank frame place by this process, finally three sections of tracks are spliced to form long path segment according to frame sequential;
Overlap between step 3, each two consecutive frame window is overlap frame, carries out the screening of preliminary candidate track accordingly:
After obtaining the candidate tracks of every section of track, retraining with other space time informations of track, that tries to achieve every section of track finally splices track;Spliced track is the arithmetic average of target location in two sections of tracks in the target location at overlapping frame overlap place.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610089780.0A CN105761279B (en) | 2016-02-18 | 2016-02-18 | Divide the method for tracking target with splicing based on track |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610089780.0A CN105761279B (en) | 2016-02-18 | 2016-02-18 | Divide the method for tracking target with splicing based on track |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105761279A true CN105761279A (en) | 2016-07-13 |
CN105761279B CN105761279B (en) | 2019-05-24 |
Family
ID=56330896
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610089780.0A Active CN105761279B (en) | 2016-02-18 | 2016-02-18 | Divide the method for tracking target with splicing based on track |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105761279B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106846358A (en) * | 2017-01-13 | 2017-06-13 | 西北工业大学深圳研究院 | Segmentation of Multi-target and tracking based on the ballot of dense track |
CN106887010A (en) * | 2017-01-13 | 2017-06-23 | 西北工业大学深圳研究院 | Ground moving target detection method based on high-rise scene information |
CN112561954A (en) * | 2020-09-11 | 2021-03-26 | 浙江大华技术股份有限公司 | Method and device for determining tracking track of target object and storage medium |
CN112802066A (en) * | 2021-01-26 | 2021-05-14 | 深圳市普汇智联科技有限公司 | Multi-target tracking method and system based on multi-track fusion |
CN113515982A (en) * | 2020-05-22 | 2021-10-19 | 阿里巴巴集团控股有限公司 | Track restoration method and equipment, equipment management method and management equipment |
CN114913200A (en) * | 2022-03-11 | 2022-08-16 | 中国科学院自动化研究所 | Multi-target tracking method and system based on space-time trajectory association |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7167519B2 (en) * | 2001-12-20 | 2007-01-23 | Siemens Corporate Research, Inc. | Real-time video object generation for smart cameras |
CN101334845B (en) * | 2007-06-27 | 2010-12-22 | 中国科学院自动化研究所 | Video frequency behaviors recognition method based on track sequence analysis and rule induction |
CN101520891B (en) * | 2009-03-17 | 2011-08-17 | 西北工业大学 | Starry sky image object track-detecting method |
US8488007B2 (en) * | 2010-01-19 | 2013-07-16 | Sony Corporation | Method to estimate segmented motion |
CN102103748B (en) * | 2010-12-14 | 2014-02-05 | 西北工业大学 | Method for detecting and tracking infrared small target in complex background |
CN103679676A (en) * | 2013-12-02 | 2014-03-26 | 西北工业大学 | Quick unordered image stitching method based on multi-level word bag clustering |
CN104200492B (en) * | 2014-08-25 | 2017-03-29 | 西北工业大学 | Video object automatic detection tracking of taking photo by plane based on profile constraints |
-
2016
- 2016-02-18 CN CN201610089780.0A patent/CN105761279B/en active Active
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106846358A (en) * | 2017-01-13 | 2017-06-13 | 西北工业大学深圳研究院 | Segmentation of Multi-target and tracking based on the ballot of dense track |
CN106887010A (en) * | 2017-01-13 | 2017-06-23 | 西北工业大学深圳研究院 | Ground moving target detection method based on high-rise scene information |
CN113515982A (en) * | 2020-05-22 | 2021-10-19 | 阿里巴巴集团控股有限公司 | Track restoration method and equipment, equipment management method and management equipment |
CN113515982B (en) * | 2020-05-22 | 2022-06-14 | 阿里巴巴集团控股有限公司 | Track restoration method and equipment, equipment management method and management equipment |
CN112561954A (en) * | 2020-09-11 | 2021-03-26 | 浙江大华技术股份有限公司 | Method and device for determining tracking track of target object and storage medium |
CN112561954B (en) * | 2020-09-11 | 2023-07-14 | 浙江大华技术股份有限公司 | Method and device for determining tracking track of target object and storage medium |
CN112802066A (en) * | 2021-01-26 | 2021-05-14 | 深圳市普汇智联科技有限公司 | Multi-target tracking method and system based on multi-track fusion |
CN112802066B (en) * | 2021-01-26 | 2023-12-15 | 深圳市普汇智联科技有限公司 | Multi-target tracking method and system based on multi-track fusion |
CN114913200A (en) * | 2022-03-11 | 2022-08-16 | 中国科学院自动化研究所 | Multi-target tracking method and system based on space-time trajectory association |
Also Published As
Publication number | Publication date |
---|---|
CN105761279B (en) | 2019-05-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105761279A (en) | Method for tracking object based on track segmenting and splicing | |
US11763485B1 (en) | Deep learning based robot target recognition and motion detection method, storage medium and apparatus | |
Yoo et al. | A robust lane detection method based on vanishing point estimation using the relevance of line segments | |
Strasdat et al. | Double window optimisation for constant time visual SLAM | |
Su et al. | Vanishing point constrained lane detection with a stereo camera | |
CN103136726B (en) | Method and apparatus for recovering the depth information of image | |
CN111201451A (en) | Method and device for detecting object in scene based on laser data and radar data of scene | |
CN115372958A (en) | Target detection and tracking method based on millimeter wave radar and monocular vision fusion | |
CN113139470B (en) | Glass identification method based on Transformer | |
KR20190085464A (en) | A method of processing an image, and apparatuses performing the same | |
US20220270354A1 (en) | Monocular image-based model training method and apparatus, and data processing device | |
KR101780048B1 (en) | Moving Object Detection Method in dynamic scene using monocular camera | |
Joung et al. | Unsupervised stereo matching using confidential correspondence consistency | |
CN111178161A (en) | Vehicle tracking method and system based on FCOS | |
US20230132646A1 (en) | Artificial intelligence and computer vision powered driving-performance assessment | |
US20210407128A1 (en) | Learnable localization using images | |
Wang et al. | Depth map enhancement based on color and depth consistency | |
El Jaafari et al. | Fast edge-based stereo matching approach for road applications | |
EP4287137A1 (en) | Method, device, equipment, storage media and system for detecting drivable space of road | |
CN115035172B (en) | Depth estimation method and system based on confidence grading and inter-stage fusion enhancement | |
Duran et al. | Vehicle-to-vehicle distance estimation using artificial neural network and a toe-in-style stereo camera | |
CN111046829A (en) | Online lane-level positioning method and system based on prior reasoning | |
Al Noman et al. | A computer vision-based lane detection technique using gradient threshold and hue-lightness-saturation value for an autonomous vehicle | |
CN104809720A (en) | Small cross view field-based double-camera target associating method | |
Srikakulapu et al. | Depth estimation from single image using defocus and texture cues |
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 |