Pedestrian vision tracking method and device, model training method and device, equipment and storage medium

A pedestrian tracking and visual tracking technology, applied in the field of target tracking, can solve problems such as poor performance

Pending Publication Date: 2019-10-01
PING AN TECH (SHENZHEN) CO LTD
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The current pedestrian visual tracking method usually pre-selects multiple candidate boxes and then determines which candidate box is most likely to contain the target

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 vision tracking method and device, model training method and device, equipment and storage medium
  • Pedestrian vision tracking method and device, model training method and device, equipment and storage medium
  • Pedestrian vision tracking method and device, model training method and device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

[0051] The flow charts shown in the drawings are just illustrations, and do not necessarily include all contents and operations / steps, nor must they be performed in the order described. For example, some operations / steps can be decomposed, combined or partially combined, so the actual order of execution may be changed according to the actual situation. In addition, although the division of functional blocks is made in the schematic diagram of the device,...

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 the field of prediction models, can predict a pedestrian boundary frame in a video stream frame image, and is high in prediction accuracy. The invention relates to the technical field of pedestrian tracking, and particularly discloses a pedestrian vision tracking method and device, a model training method and device, computer equipment and a storage medium. The pedestrianvision tracking method comprises the steps: acquiring a pedestrian boundary frame of a current frame and boundary frame action vectors of a plurality of historical frames, wherein the historical frames are frames before the current frame; based on a feature extraction sub-network of a pedestrian tracking model, performing feature extraction on a target pedestrian image in the pedestrian boundary frame to obtain a hidden feature vector of the target pedestrian image; based on a prediction sub-network of the pedestrian tracking model, predicting a boundary frame action vector of the current frame according to the implicit feature vector and the respective boundary frame action vectors of the plurality of historical frames; and predicting the pedestrian boundary frame of the next frame afterthe current frame according to the pedestrian boundary frame of the current frame and the boundary frame action vector of the current frame.

Description

technical field [0001] The present application relates to the technical field of target tracking, in particular to a pedestrian visual tracking method, model training method, device, computer equipment and storage medium. Background technique [0002] Pedestrian tracking using video is an important research content in the field of video analysis. It uses algorithms to analyze video frame sequences to locate and track pedestrians in video streams. widely used. The current pedestrian visual tracking method usually pre-selects multiple candidate boxes and then determines which candidate box is most likely to contain the target pedestrian through similarity; in actual video scenes, it is obviously affected by illumination and occlusion, and it is easy to cause Large tracking error, the effect is not good. Contents of the invention [0003] The embodiment of the present application provides a pedestrian visual tracking method, model training method, device, computer equipment...

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
IPC IPC(8): G06K9/00G06K9/62
CPCG06V20/41G06F18/214Y02T10/40
Inventor 石磊王健宗
Owner PING AN TECH (SHENZHEN) CO LTD
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