Pedestrian tracking method based on least square locus prediction and intelligent obstacle avoidance model

A least squares, intelligent obstacle avoidance technology, applied in the field of image processing, can solve problems such as color change, deviation, multi-target tracking occlusion, etc., to achieve the effect of improving accuracy

Inactive Publication Date: 2016-10-12
NANJING UNIV OF POSTS & TELECOMM
View PDF5 Cites 46 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the tracking problems of severe occlusion, excessive displacement and color changes in multi-target tracking, and provides a pedestrian tracking method based on least squares trajectory prediction and intelligent obstacle avoidance model. , taking the surrounding environmental factors into account, because if the influence of these objective environmental factors is not considered, the results calculated by the tracking algorithm will deviate from the real 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 based on least square locus prediction and intelligent obstacle avoidance model
  • Pedestrian tracking method based on least square locus prediction and intelligent obstacle avoidance model
  • Pedestrian tracking method based on least square locus prediction and intelligent obstacle avoidance model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The following is attached with the manual picture The technical scheme of the present invention is described in detail:

[0039] The present invention provides a pedestrian tracking method based on least squares trajectory prediction and intelligent obstacle avoidance model. The realization idea is as follows: firstly, the traditional Kalman algorithm is used to realize initial target tracking, and improvements are made to address its shortcomings; then Aiming at the high follow-up and wrong rate of pedestrian tracking by Kalman method, the least square method is proposed to fit the pedestrian motion curve, predict the pedestrian's position in the next video frame, and use this position as the initial moving target to search; Finally, due to the particularity of pedestrians, their psychology and exercise habits will greatly affect their movement, which is more random. Aiming at this characteristic, a combination of adaptive obstacle avoidance algorithm is proposed to t...

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 tracking method based on least square locus prediction and an intelligent obstacle avoidance model. The method comprises the steps of: first, utilizing a traditional Kalman algorithm to realize initial stage target tracking, and to overcome deficiencies; in order to solve the problem that the pedestrian tracking lost and fault rate of the Kalman algorithm is higher, a least square method being provided to perform pedestrian motion curve fitting, predicting a pedestrian position in a next video frame, and employing the position as an initial motion target for searching; and finally, tracking pedestrians based on a self-adaption obstacle avoidance method, and improving tracking accuracy.

Description

technical field [0001] The invention relates to a method for extracting video summaries, in particular to a pedestrian tracking method based on least squares trajectory prediction and intelligent obstacle avoidance model, which belongs to picture Like dealing with technical fields. Background technique [0002] Object tracking technology is an important topic in the field of computer vision and pattern recognition. The main purpose of target tracking technology is to locate the moving target, mark the target, and obtain the trajectory of the target, but the target tracking effect of the existing methods is not ideal under the conditions of target occlusion, sudden illumination change, and background change. [0003] Target tracking technology has received more and more attention from scholars, and at this stage it has gained a new definition: use the current motion state information to estimate and predict the number of targets to be tracked in the area and their state info...

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): G06T7/20
CPCG06T2207/30241
Inventor 朱松豪陈玲玲李向向荆晓远岳东
Owner NANJING UNIV OF POSTS & TELECOMM
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