Pedestrian multi-target tracking method based on centernet and depth correlation matrix

A multi-target tracking and correlation matrix technology, applied in the field of pedestrian multi-target tracking based on CenterNet and deep correlation matrix, can solve the problems of complex framework and low efficiency, and achieve the effect of ensuring high precision, high efficiency and reducing network parameters

Active Publication Date: 2022-06-21
余姚市浙江大学机器人研究中心 +1
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] Aiming at the problems of complex frame and low efficiency of the existing pedestrian multi-target tracking algorithm, the present invention provides a pedestrian multi-target tracking method based on CenterNet and depth correlation matrix

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 multi-target tracking method based on centernet and depth correlation matrix
  • Pedestrian multi-target tracking method based on centernet and depth correlation matrix
  • Pedestrian multi-target tracking method based on centernet and depth correlation matrix

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0067] Training phase:

[0068] (1) Framing the collected video into a picture sequence with a total of 65,000 pictures, and mark the pedestrians in each frame of picture I with rectangular boxes, and each rectangular box is marked as

[0069] (2) If figure 1 shown, the labeled adjacent data pairs I t with I t+1 Input the CenterNet network to extract pedestrian features respectively, and network parameters are shared;

[0070] (3) The CenterNet detection network predicts the picture I t There are M pedestrians in total. I t+1 There are N pedestrians in total. Each pedestrian location is framed by a rectangle D d =(x, y, w, h) represents, where x, y represent the coordinates of the upper left vertex of the rectangular frame. w, h represent the length and width of the rectangular box;

[0071] (4) Calculate the L2 loss L of the network detection result and the labeled ground truth d =||D d -D t || 2 , and calculate the center (Cx, Cy) of each pedestrian frame, whe...

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 discloses a pedestrian multi-target tracking method based on CenterNet and depth correlation matrix. Firstly, CenterNet is used to extract the pedestrian features in the input picture, and the position of the pedestrian in the input picture is detected in the form of a rectangular frame, and then each pedestrian is calculated. In the center of a rectangular frame, the features corresponding to the center are extracted in each stage of the CenterNet network, and then the extracted features are stitched together to construct a feature correlation matrix, and then the extracted features are compressed and associated with the deep affinity network DAN to realize complex scenes. Downstream multi-target tracking. The present invention is a high-performance and high-efficiency pedestrian multi-target tracking technology, which adopts a detection and Id association matching shared feature extraction network, and an innovative mode of joint training, which reduces efficiency and ensures high tracking accuracy.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to a pedestrian multi-target tracking method based on CenterNet and depth correlation matrix. Background technique [0002] In the field of computer vision, pedestrian target tracking is an important topic. It integrates knowledge in different fields such as artificial intelligence, image processing, pattern recognition, automatic control, etc., and has important applications in intelligent video surveillance, human-computer interaction, robot visual navigation, target recognition, traffic detection, motion analysis and other fields. In addition to the above civilian applications, image sequence-based moving target detection and tracking technology also has broad application prospects in the military field, especially in guidance and navigation. [0003] Pedestrian target tracking is difficult and lacks high-quality training data, so although target tracking has been extensively stud...

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): G06V40/20G06V40/10G06V10/774G06V10/82G06K9/62G06N3/04
CPCG06V40/25G06V40/10G06N3/045G06F18/214
Inventor 王文靖段志钊张建明王志坚
Owner 余姚市浙江大学机器人研究中心
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