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

Spatial-temporal context target tracking method based on human brain memory mechanism

A space-time context and target tracking technology, which is applied in the field of computer vision, can solve the problems of decreased tracking accuracy and achieve the effects of improving robustness, fast speed, and high computing speed

Active Publication Date: 2021-07-30
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to solve the problem of the tracking accuracy decline of the STC method in the process of target tracking such as illumination changes, sudden changes in target attitude, occlusion, reappearance after a short disappearance, etc., the present invention proposes a space-time context target tracking method based on the human brain memory mechanism

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
  • Spatial-temporal context target tracking method based on human brain memory mechanism
  • Spatial-temporal context target tracking method based on human brain memory mechanism
  • Spatial-temporal context target tracking method based on human brain memory mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0055] This embodiment discloses a target tracking method based on the combination of human brain memory mechanism and space-time context. The overall process is as follows figure 1 As shown, it specifically includes the following steps:

[0056] Step 1: Initialize memory space and tracking window.

[0057] Two layers of memory space are initialized, and each layer is constructed as short-term memory space, short-term memory space and long-term memory space. Wherein, the short-term memory space and the long-term memory space respectively store S color histogram features. The instantaneous memory space is used to save the color histogram features of the target in the current frame; the first layer of short-term memory space and the first layer of long-term memory space are used to save the target matching template parameter q t ; The second layer of short-term memory space and the second layer of long-term memory space are used to save the spatio-temporal context model.

[0...

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 space-time context target tracking method based on human brain memory mechanism. This method introduces the visual information processing cognitive model of the human brain memory mechanism into the updating process of the spatiotemporal relationship model of the STC method, so that each template must be transmitted and processed in three spaces: instantaneous memory, short-term memory and long-term memory. Form a memory-based model update strategy. By memorizing the previous scene, the method can still track continuously and robustly when the current target has problems such as illumination change, pose mutation, occlusion, and reappearance after a short disappearance. In addition, when calculating the confidence map according to the spatiotemporal context information, N candidate points of target center positions are set, and the target center position with the greatest similarity with the target template is selected as the final tracking result, thereby reducing the error caused by the confidence map and improving the tracking. precision. Finally, a moving target tracking method with high accuracy and robustness is formed.

Description

technical field [0001] The invention relates to a method for tracking a moving target in a video image, in particular to a method for tracking a target in a spatio-temporal context (STC, Spatio-Temporal Context) based on a human brain memory mechanism, and belongs to the technical field of computer vision. Background technique [0002] As an important research direction in the field of computer vision, object tracking has broad application prospects in the fields of video surveillance, human-computer interaction, and intelligent transportation. [0003] According to different target appearance modeling, typical target tracking methods can be divided into: generative target tracking methods and discriminative target tracking methods. Among them, the generative target tracking method learns a target model through features, and then searches for the area closest to the target model to achieve target tracking. Discriminative tracking methods frame tracking as a binary classific...

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): G06T7/246G06T7/262G06T7/277
CPCG06T2207/10016G06T2207/20076G06T7/248G06T7/262G06T7/277
Inventor 宋勇李旭赵尚男赵宇飞李云陈学文
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com