Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Single-camera multi-target pedestrian tracking method

A pedestrian tracking, single camera technology, applied in the field of computer vision, to achieve the effect of improving model accuracy, high accuracy and stability, and improving accuracy

Pending Publication Date: 2021-05-25
ZHEJIANG UNIV OF TECH
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, pedestrian tracking in most practical application scenarios needs to achieve high stability, high accuracy and high real-time performance. Therefore, how to develop a high-performance tracking algorithm has become the most urgent problem at present.

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
  • Single-camera multi-target pedestrian tracking method
  • Single-camera multi-target pedestrian tracking method
  • Single-camera multi-target pedestrian tracking method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044]The present invention will be further described below with reference to the accompanying drawings.

[0045]ReferFigure 1 ~ 7 A single-camera multi-target pedestrian tracking method, first use the camera installed in the monitoring area to collect pedestrian video images, then adjust the collected image size, then adjust the adjusted image to the training improvement YOLOV4-TINY pedestrian detection network, using the split box method removes the abnormal pedestrian detection box in the test results, and then inputs the screening detection result into the Deepsort algorithm to track the tracking and record the tracking information, and finally use the pedestrian unpredictable frame. The correction algorithm of the number and predictive position correction of the abnormally disappeared pedestrian target.

[0046]The single-camera multi-target pedestrian tracking method of this embodiment includes the following steps:

[0047]S1, using the camera video image installed in the monitoring ar...

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 single-camera multi-target pedestrian tracking method, which comprises the following steps: firstly, acquiring pedestrian video images by using a camera installed in a monitoring area, then correspondingly adjusting the size of the acquired images, inputting the adjusted images into a trained and improved YoloV4-Tiny pedestrian detection network, removing an abnormal pedestrian detection frame in a detection result by adopting a binning method, then inputting the screened detection result into a DeepSort algorithm to track pedestrians and record tracking information, and finally correcting an abnormally disappeared pedestrian target by adopting a correction algorithm based on a pedestrian unmatched frame number and a predicted position. Based on the improved YoloV4-Tiny, the binning method, the improved DeepSort and the correction method of the pedestrian unmatched frame number and the predicted position, high performance suitable for a real scene is basically achieved, and the method has the advantages of simultaneous multi-target positioning, accurate positioning, high real-time performance and high stability.

Description

Technical field[0001]The present invention relates to the field of computer visual, in particular, based on improved YOLOV4-TINY, split box method, improved Deepsort and a single camera multi-target pedestrian tracking method based on correction algorithms based on pedestrian unmatched frames and predictive positions.Background technique[0002]Computer vision refers to a machine vision such as a camera and computer instead of human eye to identify, track, and measuring machine vision, and further graphical processing to obtain the result. In recent years, with the continuous development of computer vision technology, computer vision is already unsearched in various applications, such as manufacturing, intelligent monitoring, virtual reality, hospital diagnosis, and military, and other intelligent systems.[0003]Pedestrian tracking is a hot problem in the field of non-rigid motion target tracking fields in computer vision, which is to continuously track pedestrians in video. However, p...

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): G06K9/00G06K9/42G06K9/62G06T7/246G06N3/04G06N3/08G06T3/40
CPCG06T7/246G06N3/08G06T2207/10016G06T2207/20081G06T2207/20084G06T2207/30196G06T2207/30232G06T2207/30241G06T3/4007G06V40/23G06V10/32G06V10/751G06N3/048G06F18/241Y02T10/40
Inventor 张江鑫徐加斌郑天悦沈科纳
Owner ZHEJIANG UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products