CN111192297A - Multi-camera target association tracking method based on metric learning - Google Patents
Multi-camera target association tracking method based on metric learning Download PDFInfo
- Publication number
- CN111192297A CN111192297A CN201911407164.5A CN201911407164A CN111192297A CN 111192297 A CN111192297 A CN 111192297A CN 201911407164 A CN201911407164 A CN 201911407164A CN 111192297 A CN111192297 A CN 111192297A
- Authority
- CN
- China
- Prior art keywords
- idi
- tracking
- img
- frame
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000001514 detection method Methods 0.000 claims abstract description 30
- 238000004364 calculation method Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 239000013598 vector Substances 0.000 abstract description 5
- 230000007547 defect Effects 0.000 abstract description 3
- 238000012545 processing Methods 0.000 abstract description 3
- 238000005259 measurement Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000020169 heat generation Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000002918 waste heat Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/292—Multi-camera tracking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
Abstract
The invention belongs to the technical field of computer video image processing, and particularly relates to a multi-camera target association tracking method based on metric learning. The multi-camera target association tracking method based on metric learning aims to overcome the technical defects that information cannot be shared and information is mixed up among multiple cameras, tracking loss caused by shielding of a single camera is avoided, and meanwhile, a tracking algorithm can be further embedded into hardware equipment, so that the stability and the practicability of the algorithm are improved. The multi-camera target association tracking method comprises the following steps: simultaneously acquiring a video set of a target object in a target place through n cameras; detecting and tracking a target object to obtain a tracking result; extracting a detection frame from the tracking result; sending the extracted detection frame into a deep convolution network, and extracting a feature vector; calculating the cosine distance; judging whether the objects in the same frame are similar or not through threshold comparison; the association successfully implements the trace.
Description
Technical Field
The invention belongs to the technical field of computer video image processing, and particularly relates to a multi-camera target association tracking method based on metric learning.
Background
With the development of computer video image processing technology, multi-target tracking has important application in the fields of intelligent monitoring, action and behavior analysis, automatic driving and the like. Multi-target tracking finds moving objects in an image sequence by giving the image sequence, identifies moving objects of different frames, and determines an accurate target identifier, wherein the moving objects can be any objects such as pedestrians, vehicles, animals and the like. With the development of the field of target detection in recent years, the Tracking-by-detection algorithm becomes the mainstream in multi-target Tracking, and a flow network formula and a probability graph model for detection appear before, but the global optimization problem of the whole process is handled by the algorithm and the method is not suitable for an online scene. Common tracking algorithms used after detection are an SORT algorithm and a Deep Sort algorithm. The SORT algorithm uses simple Kalman filtering to process the relevance of frame-by-frame data and uses the Hungarian algorithm to carry out relevance measurement, the simple algorithm obtains good performance under a high frame rate, but the SORT algorithm is accurate only when the uncertainty of object state estimation is low due to the fact that the surface characteristics of detected objects are ignored. The Deep Sort algorithm uses more reliable measurement to replace the correlation measurement, and uses the convolutional neural network to train on a large-scale pedestrian data set, so as to extract features, thereby increasing the robustness of the network to loss and obstacles. Although the Yolo algorithm and Deep Sort algorithm are combined to perform multi-target tracking and become one of mainstream algorithms, under the conditions of personnel occlusion, crossing and the like caused by a complex environment, the corresponding error between the object identifier of the previous frame and the same object identifier of the next frame often occurs; if the algorithm is used for multi-camera tracking, although the ranges which can be observed by a plurality of cameras have a common area, the tracking information of the plurality of cameras cannot be associated, and finally the multi-target tracking effect is not high in precision and the information of a target object is wrong.
Disclosure of Invention
The invention provides a multi-camera target association tracking method based on metric learning, which aims to overcome the technical defects that information cannot be shared and is confused among multiple cameras, tracking loss is caused by shielding of a single camera and the like, and can further embed a tracking algorithm into hardware equipment so as to improve the stability and the practicability of the algorithm.
In order to solve the technical problems, the invention adopts the following technical scheme:
a multi-camera target association tracking method based on metric learning comprises the following steps:
step 4, extracting the detection frame DF1And DF2Sending into a deep convolution network, extracting diAnd fiRespectively marked as rVj={r1 idi,r2 idi,…,rn idi},rVk={r1 idi,r2 idi,…,rn idi}; wherein r isVjAnd rVkRepresenting cameras j and k at imgiId of frame acquisitioniThe appearance characteristics of (a);
step 5, for rVj={r1 idi,r2 idi,…,rn idiAnd rVk={r1 idi,r2 idi,…,rn idiCalculating the cosine distance, wherein the calculation formula is shown as formula (1):
Cos(dis(rVj,rVk))=1-rvj Trvk(1)
wherein r isvj TIs rvjThe transposed matrix of (2);
step 6, comparing and judging V through a threshold αjAnd VkWhether the objects in the same frame are similar or not, and the threshold α is obtained by training, when Cos (dis (r)Vj,rVk) D) is less than or equal to αiAnd fiThe association is successful, and the result is judged to be id in two detection framesiSimilarly; otherwise, returning to the step 5 to continue cosine calculation until all comparisons are finished;
step 7, when diAnd fiThe association is successful, will fiCorresponding idiTo diCorresponding idi。
The invention provides a multi-camera target association tracking method based on metric learning, which comprises the following steps: simultaneously acquiring a video set of a target object in a target place through n cameras; detecting and tracking a target object to obtain a tracking result; extracting a detection frame from the tracking result; sending the extracted detection frame into a deep convolution network, and extracting a feature vector; calculating the cosine distance; judging whether the objects in the same frame are similar or not through threshold comparison; the association successfully implements the trace. The multi-camera target association tracking method based on metric learning, which has the characteristics of the steps, improves the recording effect in a mode of simultaneously recording by multiple cameras; the appearance characteristics of the object in the detection frame are extracted by adopting a deep neural network, so that the method is simple and high in robustness; by adopting the cosine distance as a measurement learning method, the similarity between the characteristic vectors can be measured better without direct connection with absolute numerical values; by adopting an embedded method, the stability and the practicability of the algorithm are improved. And the conditions of personnel shielding, crossing and the like caused by complex environment in the multi-target tracking problem are solved, and the tracking precision can be effectively improved.
Drawings
Fig. 1 is a schematic view of an application scenario of a multi-camera target association tracking method based on metric learning according to the present invention;
fig. 2 is a schematic structural diagram of an embedded device of the multi-camera target association tracking method based on metric learning according to the present invention.
Detailed Description
The invention provides a multi-camera target association tracking method based on metric learning, which aims to overcome the technical defects that information cannot be shared and is confused among multiple cameras, tracking loss is caused by shielding of a single camera and the like, and can further embed a tracking algorithm into hardware equipment so as to improve the stability and the practicability of the algorithm.
A multi-camera target association tracking method based on metric learning comprises the following steps:
Step 4, extracting the detection frame DF1And DF2Sending into a deep convolution network, extracting diAnd fiRespectively marked as rVj={r1 idi,r2 idi,…,rn idi},rVk={r1 idi,r2 idi,…,rn idi}; wherein r isVjAnd rVkRepresenting cameras j and k at imgiId of frame acquisitioniThe appearance characteristics of (1).
Step 5, for rVj={r1 idi,r2 idi,…,rn idiAnd rVk={r1 idi,r2 idi,…,rn idiCalculating the cosine distance, wherein the calculation formula is shown as formula (1):
Cos(dis(rVj,rVk))=1-rvj Trvk(1)
wherein r isvj TIs rvjThe transposed matrix of (2).
Step 6, comparing and judging V through a threshold αjAnd VkWhether the objects in the same frame are similar or not, and the threshold α is obtained by training, when Cos (dis (r)Vj,rVk) D) is less than or equal to αiAnd fiThe association is successful, and the result is judged to be id in two detection framesiSimilarly; otherwise, returning to the step 5 to continue the cosine calculation until all the comparisons are finished.
Step 7, when diAnd fiThe association is successful, will fiCorresponding idiTo diCorresponding idi。
Therefore, the multi-camera target association tracking method based on metric learning realizes the association of the multi-camera targets.
It should be added that, in order to further improve the application scenario of the multi-camera target association tracking method, the relevant contents in steps 1 to 7 may be embedded into a hardware device, for example: such as the embedded terminal device shown in fig. 2. In particular, the embedded terminal device preferably uses PCIe (x8) slots, is specially designed for edge artificial intelligence and machine vision applications, adopts an intelligent power supply, and has the advantages of low cost, less waste heat generation and more stable system.
The invention provides a multi-camera target association tracking method based on metric learning, which comprises the following steps: simultaneously acquiring a video set of a target object in a target place through n cameras; detecting and tracking a target object to obtain a tracking result; extracting a detection frame from the tracking result; sending the extracted detection frame into a deep convolution network, and extracting a feature vector; calculating the cosine distance; judging whether the objects in the same frame are similar or not through threshold comparison; the association successfully implements the trace. The multi-camera target association tracking method based on metric learning, which has the characteristics of the steps, improves the recording effect in a mode of simultaneously recording by multiple cameras; the appearance characteristics of the object in the detection frame are extracted by adopting a deep neural network, so that the method is simple and high in robustness; by adopting the cosine distance as a measurement learning method, the similarity between the characteristic vectors can be measured better without direct connection with absolute numerical values; by adopting an embedded method, the stability and the practicability of the algorithm are improved. And the conditions of personnel shielding, crossing and the like caused by complex environment in the multi-target tracking problem are solved, and the tracking precision can be effectively improved.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (1)
1. A multi-camera target association tracking method based on metric learning is characterized by comprising the following steps:
step 1, simultaneously acquiring a video set V ═ V { V of a target object in a target site through n cameras1,V2,…,Vn}; wherein, ViRepresents a video captured by a camera with the index i, and Vi={img1,img2,…,imgn},imgiRepresents ViAn ith frame picture in the video;
step 2, using a Yolo algorithm to pair ViDetecting the target object in (1), and tracking by using Deep Sort algorithm to obtain ViDetection frame DF of medium object ═ { DF ═ DF1,df2,…,dfnAnd specific identity set ID ═ ID1,id2,…,idn}; wherein idiRepresents ViThe object in (1) named i; then, the tracking result E of each frame is { (df)1,id1),(df2,id2),…,(dfn,idn) Saving to the local;
step 3, extracting tracking results of p cameras from the tracking result E; let p be 2 and the camera numbers j and k, respectively; extract the same frame of video, i.e. V, captured by cameras j and kjAnd VkMiddle and same frame imgi(ii) a Respectively extracting imgiDetection frame DF of q objects in (1)1={d1,d2,…,dqAnd DF2={f1,f2,…,fq}; wherein d isiRepresents VjImg ofiWherein ID is IDiDetection frame of fiRepresents VkImg ofiWherein ID is IDiThe detection frame of (2);
step 4, extracting the detection frame DF1And DF2Sending into a deep convolution network, extracting diAnd fiRespectively marked as rVj={r1 idi,r2 idi,…,rn idi},rVk={r1 idi,r2 idi,…,rn idi}; wherein r isVjAnd rVkRepresenting cameras j and k at imgiId of frame acquisitioniThe appearance characteristics of (a);
step 5, for rVj={r1 idi,r2 idi,…,rn idiAnd rVk={r1 idi,r2 idi,…,rn idiCalculating the cosine distance, wherein the calculation formula is shown as formula (1):
Cos(dis(rVj,rVk))=1-rvj Trvk(1)
wherein r isvj TIs rvjThe transposed matrix of (2);
step 6, comparing and judging V through a threshold αjAnd VkWhether the objects in the same frame are similar or not, and the threshold α is obtained by training, when Cos (dis (r)Vj,rVk) D) is less than or equal to αiAnd fiThe association is successful, and the result is judged to be id in two detection framesiSimilarly; otherwise, returning to the step 5 to continue cosine calculation until all comparisons are finished;
step 7, when diAnd fiThe association is successful, will fiCorresponding idiTo diCorresponding idi。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911407164.5A CN111192297A (en) | 2019-12-31 | 2019-12-31 | Multi-camera target association tracking method based on metric learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911407164.5A CN111192297A (en) | 2019-12-31 | 2019-12-31 | Multi-camera target association tracking method based on metric learning |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111192297A true CN111192297A (en) | 2020-05-22 |
Family
ID=70709696
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911407164.5A Pending CN111192297A (en) | 2019-12-31 | 2019-12-31 | Multi-camera target association tracking method based on metric learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111192297A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111654668A (en) * | 2020-05-26 | 2020-09-11 | 李绍兵 | Monitoring equipment synchronization method and device and computer terminal |
CN112200021A (en) * | 2020-09-22 | 2021-01-08 | 燕山大学 | Target crowd tracking and monitoring method based on limited range scene |
CN112200841A (en) * | 2020-09-30 | 2021-01-08 | 杭州海宴科技有限公司 | Cross-domain multi-camera tracking method and device based on pedestrian posture |
CN112381132A (en) * | 2020-11-11 | 2021-02-19 | 上汽大众汽车有限公司 | Target object tracking method and system based on fusion of multiple cameras |
CN115278042A (en) * | 2021-04-30 | 2022-11-01 | 西门子股份公司 | Method and apparatus for setting frame rate in image processing, and computer readable medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109344792A (en) * | 2018-10-18 | 2019-02-15 | 电子科技大学 | A kind of Motion parameters tracking |
CN109934844A (en) * | 2019-01-28 | 2019-06-25 | 中国人民解放军战略支援部队信息工程大学 | A kind of multi-object tracking method and system merging geospatial information |
CN110197502A (en) * | 2019-06-06 | 2019-09-03 | 山东工商学院 | A kind of multi-object tracking method that identity-based identifies again and system |
CN110378931A (en) * | 2019-07-10 | 2019-10-25 | 成都数之联科技有限公司 | A kind of pedestrian target motion track acquisition methods and system based on multi-cam |
CN110443210A (en) * | 2019-08-08 | 2019-11-12 | 北京百度网讯科技有限公司 | A kind of pedestrian tracting method, device and terminal |
-
2019
- 2019-12-31 CN CN201911407164.5A patent/CN111192297A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109344792A (en) * | 2018-10-18 | 2019-02-15 | 电子科技大学 | A kind of Motion parameters tracking |
CN109934844A (en) * | 2019-01-28 | 2019-06-25 | 中国人民解放军战略支援部队信息工程大学 | A kind of multi-object tracking method and system merging geospatial information |
CN110197502A (en) * | 2019-06-06 | 2019-09-03 | 山东工商学院 | A kind of multi-object tracking method that identity-based identifies again and system |
CN110378931A (en) * | 2019-07-10 | 2019-10-25 | 成都数之联科技有限公司 | A kind of pedestrian target motion track acquisition methods and system based on multi-cam |
CN110443210A (en) * | 2019-08-08 | 2019-11-12 | 北京百度网讯科技有限公司 | A kind of pedestrian tracting method, device and terminal |
Non-Patent Citations (2)
Title |
---|
NICOLAI WOJKE,ET AL.: "SIMPLE ONLINE AND REALTIME TRACKING WITH A DEEP ASSOCIATION METRIC", ARXIV, 21 March 2017 (2017-03-21) * |
想自由的MONSTER: "多目标跟踪 DeepSort 代码与原理分析", Retrieved from the Internet <URL:https://blog.csdn.net/weixin_42823393/article/details/100335737> * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111654668A (en) * | 2020-05-26 | 2020-09-11 | 李绍兵 | Monitoring equipment synchronization method and device and computer terminal |
CN112200021A (en) * | 2020-09-22 | 2021-01-08 | 燕山大学 | Target crowd tracking and monitoring method based on limited range scene |
CN112200021B (en) * | 2020-09-22 | 2022-07-01 | 燕山大学 | Target crowd tracking and monitoring method based on limited range scene |
CN112200841A (en) * | 2020-09-30 | 2021-01-08 | 杭州海宴科技有限公司 | Cross-domain multi-camera tracking method and device based on pedestrian posture |
CN112381132A (en) * | 2020-11-11 | 2021-02-19 | 上汽大众汽车有限公司 | Target object tracking method and system based on fusion of multiple cameras |
CN115278042A (en) * | 2021-04-30 | 2022-11-01 | 西门子股份公司 | Method and apparatus for setting frame rate in image processing, and computer readable medium |
CN115278042B (en) * | 2021-04-30 | 2023-11-28 | 西门子股份公司 | Method, apparatus and computer readable medium for setting frame rate in image processing |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111192297A (en) | Multi-camera target association tracking method based on metric learning | |
CN111462200B (en) | Cross-video pedestrian positioning and tracking method, system and equipment | |
CN110349250B (en) | RGBD camera-based three-dimensional reconstruction method for indoor dynamic scene | |
CN103246896B (en) | A kind of real-time detection and tracking method of robustness vehicle | |
CN108537829B (en) | Monitoring video personnel state identification method | |
CN110458025B (en) | Target identification and positioning method based on binocular camera | |
CN102982537B (en) | A kind of method and system detecting scene change | |
CN103164858A (en) | Adhered crowd segmenting and tracking methods based on superpixel and graph model | |
CN102243765A (en) | Multi-camera-based multi-objective positioning tracking method and system | |
CN105160649A (en) | Multi-target tracking method and system based on kernel function unsupervised clustering | |
CN110827321B (en) | Multi-camera collaborative active target tracking method based on three-dimensional information | |
CN104301712A (en) | Monitoring camera shaking detection method based on video analysis | |
CN101324958A (en) | Method and apparatus for tracking object | |
CN114022910A (en) | Swimming pool drowning prevention supervision method and device, computer equipment and storage medium | |
Landabaso et al. | Foreground regions extraction and characterization towards real-time object tracking | |
CN112634368A (en) | Method and device for generating space and OR graph model of scene target and electronic equipment | |
CN114529583B (en) | Power equipment tracking method and tracking system based on residual regression network | |
CN101877135B (en) | Moving target detecting method based on background reconstruction | |
CN106023252A (en) | Multi-camera human body tracking method based on OAB algorithm | |
CN116342645A (en) | Multi-target tracking method for natatorium scene | |
Min et al. | COEB-SLAM: A Robust VSLAM in Dynamic Environments Combined Object Detection, Epipolar Geometry Constraint, and Blur Filtering | |
Biswas et al. | Short local trajectory based moving anomaly detection | |
CN112163502B (en) | Visual positioning method under indoor dynamic scene | |
Lee et al. | Fast people counting using sampled motion statistics | |
CN112001252A (en) | Multi-target tracking method based on heteromorphic graph network |
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 |