Multi-target tracking method based on random finite set filter coupling

A multi-target tracking and filter technology, applied in the field of multi-target tracking

Inactive Publication Date: 2017-06-30
SHENZHEN WEITESHI TECH
View PDF3 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of the fact that existing methods cannot effectively solve the problem of unknown clutter rate, the purpose of the present invention is to provide a multi-target tracking method based on random finite set filter coupling, and a multi-target tracker is designed to generate independent trajectories for each target. And estimate the unknown clutter rate on the fly, which can effectively adapt to real scenes and achieve robust multi-target tracking performance

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
  • Multi-target tracking method based on random finite set filter coupling
  • Multi-target tracking method based on random finite set filter coupling
  • Multi-target tracking method based on random finite set filter coupling

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present invention will be further described in detail below in conjunction with the drawings and specific embodiments.

[0050] figure 1 It is a system flowchart of a multi-target tracking method based on random finite set filter coupling in the present invention. Mainly including Robust Multi-Bernoulli (RMB) Filter, Generalized Label Multi-Bernoulli (GLMB) Filter, Enhanced GLMB Filter, Multi-Target Tracker.

[0051] Wherein, the robust multi-Bernoulli (RMB) filter, the multi-Bernoulli filter parameterizes the posterior density of multiple targets, by using a set of Bernoulli parameters where r (i) and p (i) Representing the existence probability and state density in M ​​Bernoulli components, the multi-Bernoulli filter used to expand the state space is recursively called a robust multi-Bernoulli (RMB...

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 proposes a multi-target tracking method based on random finite set filter coupling, and the method comprises the contents: an RMB (robust multi-Bernoulli) filter, a GLMB (generalized label multi-Bernoulli) filter, an enhanced GLMB filter, and a multi-target tracker. The process comprises the steps: employing the GLMB filter as a main tracker under the condition of an unknown clutter rate so as to generate a track parameter; enabling the one-step RMB filer to modify the unknown clutter rate based on the provided track parameter and track existing probability; inputting the clutter rate estimated by the RMB filter into the GLMB filter, thereby achieving the robust online visual multi-target tracking. The method breaks the limit that different targets cannot be tracked and recognized during the filtering of the unknown clutter rate, and one multi-target tracker is designed for generating independent tracks. Moreover, the unknown clutter rate is estimated in operation, and the method can effectively adapt to a real scene, and achieves a robust multi-target tracking performance.

Description

technical field [0001] The invention relates to the field of multi-target tracking, in particular to a multi-target tracking method based on random finite set filter coupling. Background technique [0002] Multi-target tracking is often used in the fields of intelligent video surveillance, traffic, and automatic driving and assisted driving of automobiles. It can automatically track multiple targets in a video scene without human intervention. Specifically in the field of intelligent video surveillance, multiple target persons can be tracked in complex videos. In addition, when applied to car assisted driving, multi-target tracking can track multiple pedestrians in the video captured by the car to achieve effective avoidance. Although multi-object tracking is a basic problem in many applications and has been richly researched, it is still far from being able to achieve the purpose of practical use. [0003] The invention proposes a multi-target tracking method based on ran...

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): G06T7/277
Inventor 夏春秋
Owner SHENZHEN WEITESHI TECH
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