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
CN106910205AInactive Publication Date: 2017-06-30SHENZHEN WEITESHI TECH
3 Cites 16 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
SHENZHEN WEITESHI TECH
Publication Date
2017-06-30
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

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.
Need to check novelty before this filing date? Find Prior Art

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