Cross-camera target detection and tracking system and method

A target detection and cross-camera technology, applied in the field of intelligent transportation, can solve problems such as error-prone, boring monitoring personnel, waste of manpower, etc., and achieve the effect of improving accuracy, early perception ability, improving accuracy and real-time performance

Pending Publication Date: 2022-05-27
TONGJI UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] At present, the use of cameras is very common, but for a large amount of video data, it can only be processe

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Cross-camera target detection and tracking system and method
  • Cross-camera target detection and tracking system and method
  • Cross-camera target detection and tracking system and method

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0043] Example

[0044] like figure 1 As shown, a system embodiment of the present invention is given, a cross-camera target detection and tracking system, the system includes a target detection module, a target association module, a target tracking module and a result visualization module, the target detection module, target association module The camera video data is processed successively with the target tracking module, and the result visualization module visualizes the processing results of the above modules, specifically:

[0045] The target detection module is used to perform target detection on the obtained camera video data;

[0046] a target association module for constructing a target data set and a valid target list based on the target detection result, and associating the targets;

[0047] The target tracking module is used to track targets under different cameras according to the target detection results and target association results of different cameras;

[...

Example Embodiment

[0072] Example 2

[0073] like Figure 4 In the scene of an intersection shown, taking a 3-way intersection as an example, a camera is installed in each direction to monitor the corresponding direction area. Different computing devices are used according to different requirements for offline computing and online computing in different application scenarios.

[0074] The specific working process of the cross-camera target detection and tracking method in this embodiment includes:

[0075] Step S1, assign IP to all cameras at the intersection, and obtain camera data;

[0076] Step S2, transmitting all the camera video data to the computing unit, and using the deep convolutional neural network for target detection, outputting the detected target information, and constructing a target data set and an effective target list;

[0077] Step S3, according to the detection information, use the attention mechanism to extract the feature information of all current targets, including th...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to a cross-camera target detection and tracking system and method, and the system comprises a target detection module, a target association module, a target tracking module, and a result visualization module, and the target detection module, the target association module, and the target tracking module successively process camera video data. The result visualization module is used for carrying out visualization processing on a module processing result; the target detection module is used for performing target detection on the acquired camera video data; the target association module is used for constructing a target data set and an effective target list based on the target detection result, and associating the targets; the target tracking module is used for carrying out target tracking under different cameras according to the target detection results of the different cameras and the target association result; and the result visualization module is used for keeping the number of the same target unchanged in the tracking process and updating an effective target list in real time. Compared with the prior art, the method has the advantages of high target detection and tracking accuracy and good real-time performance.

Description

technical field [0001] The invention relates to the field of intelligent transportation, in particular to a cross-camera target detection and tracking system and method. Background technique [0002] With the reduction of camera hardware cost and the improvement of memory capacity, as well as the rapid development of network technology and communication technology, cameras have spread all over the streets. As a key component of intelligent video surveillance system, target detection and tracking technology has a high research value and application value. At present, the main research direction is single-camera target tracking, but the monitoring range of a single camera is limited, which leads to its large limitations, and it cannot continuously track the target. [0003] Because the multiple cameras used in the cross-camera target tracking system are located in different positions, the field of view can be spliced ​​into a larger space area, thereby overcoming the inherent...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06T7/00G06T7/246G06K9/62G06N3/04G06N3/08G06V10/74
CPCG06T7/0002G06T7/246G06N3/08G06N3/045G06F18/22
Inventor 王平王超王新红朱纪龙
Owner TONGJI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap