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

Historical-route-based target tracking method and electronic equipment

A technology of target tracking and historical trajectory, applied in the field of computer vision, can solve problems such as tracking failure and inaccurate tracking results

Inactive Publication Date: 2016-03-30
PALMWIN INFORMATION TECH SHANGHAI
View PDF3 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, in the actual tracking scene, when the appearance of the target object changes greatly, the target object moves suddenly, the target object is severely occluded, and the background is cluttered, the linear model will drift over time, resulting in tracking results. Inaccurate or failed to track

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
  • Historical-route-based target tracking method and electronic equipment
  • Historical-route-based target tracking method and electronic equipment
  • Historical-route-based target tracking method and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0101] The embodiment of the present invention provides a kind of target tracking method based on historical track, refer to figure 1 As shown, the method flow includes:

[0102] 101. For a current frame, acquire tracking positions for a target object respectively output by the current expert tracker and at least one historical expert tracker.

[0103] The current expert tracker is a snapshot of the base tracker at the current frame; and

[0104] At least one historical expert tracker is a snapshot of the base tracker at least one historical frame.

[0105] Among them, the basic tracker is a tracker based on correlation filtering.

[0106] Specifically, the process may include:

[0107] Acquiring positions corresponding to the maximum values ​​of the response graphs of the current expert tracker and at least one historical expert tracker as tracking positions for the target object respectively output by the current expert tracker and the at least one historical expert track...

Embodiment 2

[0127] The embodiment of the present invention provides a kind of target tracking method based on historical track, refer to figure 2 As shown, the method flow includes:

[0128] 201. For a current frame, acquire tracking positions for a target object respectively output by the current expert tracker and at least one historical expert tracker.

[0129] The current expert tracker is a snapshot of the base tracker at the current frame; and

[0130] At least one historical expert tracker is a snapshot of the base tracker at least one historical frame.

[0131] Among them, the basic tracker is a tracker based on correlation filtering.

[0132] Specifically, the process may include:

[0133] Acquiring positions corresponding to the maximum values ​​of the response graphs of the current expert tracker and at least one historical expert tracker as tracking positions for the target object respectively output by the current expert tracker and the at least one historical expert trac...

Embodiment 3

[0158] The embodiment of the present invention provides a kind of target tracking method based on historical track, refer to image 3 As shown, the method flow includes:

[0159] 301. Obtain a response graph of the current expert tracker and at least one historical expert tracker.

[0160] The current expert tracker is a snapshot of the base tracker at a current frame; and the at least one historical expert tracker is a snapshot of the base tracker at at least one historical frame.

[0161] Among them, the basic tracker is a tracker based on correlation filtering.

[0162] The response map is an output map based on correlation filtering of the current expert tracker and at least one historical expert tracker.

[0163] Specifically, the current expert tracker and at least one historical expert tracker respectively calculate the output graph of the correlation filter in the tracking detection process, and the output graph can be obtained in the following manner:

[0164] In 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, which belongs to the computer vision field, discloses a historical-route-based target tracking method and electronic equipment. The method comprises: for a current frame, tacking positions that correspond to a target object and are outputted by a current expert tracker and at least one history expert tracker respectively are obtained; and according to the tracking positions outputted by the current expert tracker and the at least one history expert tracker, an optimal position of the target object at the current frame is determined. According to the invention, because the optimal position of the target object at the current frame can be determined according to the tracking positions outputted by the current expert tracker and the at least one history expert tracker respectively, the optimal position of the target object can be determined from tracking positions outputted by a plurality of expert trackers, so that the tracking position determination becomes accurate. Meanwhile, with the multiple expert trackers, a problem of failed tracking due to factors like a disordered background, sudden movement of a target object, a shielded state of the target object, and appearance changing during the tracking process can be solved.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to a historical track-based target tracking method and electronic equipment. Background technique [0002] In the process of tracking the target object in the video, due to the changes in the shape of the target object, lighting changes, sudden movement of the target object, occlusion, and background clutter, it is more difficult for the tracker to detect and track the target. , often causing tracking failures. [0003] In the prior art, in the process of tracking a target object in a video, an online model capable of quickly adapting to changes in the appearance of the target object is used to realize the tracking of the target object, so as to avoid the tracking failure caused by the above-mentioned problems. [0004] However, in the actual tracking scene, when the appearance of the target object changes greatly, the target object moves suddenly, the target object is severely occlu...

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
CPCG06T2207/20081
Inventor 洪智滨
Owner PALMWIN INFORMATION TECH SHANGHAI
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