Multi-target tracking method and system based on tracking chain

A multi-target tracking and tracking chain technology, applied in the field of image recognition, can solve problems such as difficulty in meeting actual needs and tracking failure, and achieve the effect of efficient synchronous tracking and high reliability

Active Publication Date: 2022-05-31
SHANGHAI AWARE INFORMATION TECH +1
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In 2017, the SORT algorithm based on deep learning target detection, the SORT algorithm took into account the tracking effect and speed, and achieved good results, but it is easy to cause tracking failure due to occlusion
[0003] It can be seen that there are still many technical problems in the multi-target tracking technology in the prior art, and it is difficult to meet the actual needs.

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
  • Multi-target tracking method and system based on tracking chain
  • Multi-target tracking method and system based on tracking chain
  • Multi-target tracking method and system based on tracking chain

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0066] It should be noted that the solution of the present invention can be implemented on the field side, and can also be implemented on the server side. That

[0070] The third tracking chain is assigned to the identified target objects in the sequence of identification.

[0075] A first number is determined according to the number and the speed, and the third tracking chain is generated according to the first number.

[0078] Optionally, the first tracking chain and the second tracking chain include speed data and position data;

[0083] Wherein, the distance between the first moment and the second moment is less than a preset threshold.

[0086] Optionally, the state includes not comatose, comatose;

[0089] If the first target object recognition fails, then add 1 to the non-coma times n2, and record the corresponding time.

[0092] before the calculation of the similarity between the first tracking chain and the second tracking chain, further

[0095] Calculate the number of ...

Embodiment 2

[0111] the processing module (101) is used to call the executable computer in the storage module (102)

Embodiment 3

[0117] The processor calls the executable program code stored in the memory, and executes the execution as described in the first embodiment

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 provides a multi-target tracking method and system based on a tracking chain. The method comprises the following steps: identifying a first target object in a monitoring image according to a preset interval, and generating a first tracking chain according to an identification result; when the identification of the first target object fails, modifying the state of the first tracking chain; generating a second tracking chain for the newly recognized second target object; the similarity between the first tracking chain and the second tracking chain is calculated, and the first tracking chain and the second tracking chain are connected in series according to the similarity; according to the method, synchronous tracking of multiple target objects can be simply and efficiently achieved, tracking failure caused by shielding is avoided, and higher reliability is achieved.

Description

A tracking chain-based multi-target tracking method and system technical field The present invention relates to the technical field of image recognition, in particular, to a kind of multi-target tracking method based on tracking chain. methods, systems, electronic devices, and computer storage media. Background technique [0002] Multiple object tracking (Multiple Object Tracking), in short, its main task is to give a graph Like a sequence, after identifying the object in the image, the same object in different frames is represented by a Trace id, So as to complete the task of target tracking. Of course, these objects can be arbitrary, such as pedestrians, vehicles, various animals, etc. Many goals Tracking is a hot spot in computer vision technology, and it is also a difficult point in practical applications. In 2017, the target detection based on deep learning SORT algorithm, the SORT algorithm takes into account the tracking effect and speed, and achieves good ...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/246G06V20/52
CPCG06T7/246
Inventor 范柘
Owner SHANGHAI AWARE INFORMATION TECH
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