Pedestrian tracking method, device, storage medium and equipment based on pedestrian re-identification

A pedestrian re-identification and pedestrian tracking technology, applied in image analysis, instrumentation, calculation, etc., can solve problems such as wrong tracking results, time-consuming and labor-intensive, and achieve the effect of improving accuracy

Active Publication Date: 2022-05-06
小视科技(江苏)股份有限公司
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] This application provides a pedestrian tracking method, device, storage medium and equipment based on pedestrian re-identification, which is used to solve the problem of manually labeling pedestrians, which is not only time-consuming and labor-intensive, but also prone to labeling the same pedestrian with different pedestrian labels Annotation results, resulting in wrong tracking results

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
  • Pedestrian tracking method, device, storage medium and equipment based on pedestrian re-identification
  • Pedestrian tracking method, device, storage medium and equipment based on pedestrian re-identification
  • Pedestrian tracking method, device, storage medium and equipment based on pedestrian re-identification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0064] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the following will further describe the embodiments of the present application in detail in conjunction with the accompanying drawings.

[0065] The ordinary pedestrian tracking method can keep the pedestrian label unchanged in a short period of time. However, when the pedestrian disappears from the screen for a period of time and then reappears on the screen, it will be regarded as a new pedestrian, and the pedestrian label will be added, thus lead to pedestrian tracking errors. In this embodiment, it can be determined whether pedestrians have appeared in the video stream according to the similarity of pedestrian features, which can realize long-term tracking, and try to ensure that pedestrians appearing at different times in the same video stream are assigned the same pedestrian label to avoid redundant Pedestrian labels are convenient for subsequent...

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 application discloses a pedestrian tracking method, device, storage medium and equipment based on pedestrian re-identification, belonging to the technical field of image processing. The method comprises: extracting detection frames and first feature vectors of n pedestrians from the current video frame of the video stream; acquiring allocated m pedestrian trackers, the pedestrian tracker includes a tracking frame of a pedestrian identified , the second eigenvector and the pedestrian label; calculate the intersection ratio matrix according to n detection frames and m tracking frames; calculate the cosine similarity matrix according to n first eigenvectors and m second eigenvectors; Perform a weighted operation on the ratio matrix and the cosine similarity matrix to obtain a cost matrix; match the n pedestrians and the m trackers according to the cost matrix. This application assigns the same pedestrian label to pedestrians appearing at different times in the same video stream, avoiding redundant pedestrian labels, avoiding the exchange of trackers, and distinguishing overlapping pedestrians.

Description

technical field [0001] The present application relates to the technical field of image processing, and in particular to a pedestrian tracking method, device, storage medium and equipment based on pedestrian re-identification. Background technique [0002] Pedestrian re-identification is a technology that uses computer vision technology to retrieve whether a specific pedestrian exists in an image or video sequence. When a pedestrian image is given, the pedestrian re-identification technology can be used to determine whether the pedestrian has appeared in other surveillance videos. Pedestrian re-identification can be combined with pedestrian detection, pedestrian tracking and other technologies, and is widely used in intelligent video surveillance, intelligent security and other fields. [0003] In related technologies, the monitoring video stream can be obtained from the monitoring camera, the video frame can be extracted from the monitoring video stream, the pedestrian imag...

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 Patents(China)
IPC IPC(8): G06T7/246G06T7/277G06V10/74
Inventor 杨帆朱莹陈凯琪张凯翔胡建国
Owner 小视科技(江苏)股份有限公司
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