Multi-objective tracking method based on continuous minimum-energy appearance model

A multi-target tracking and appearance model technology, applied in the field of computer vision

Inactive Publication Date: 2014-08-27
NANJING UNIV OF POSTS & TELECOMM
View PDF5 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Although multi-target tracking is widely used in many aspects, it is necessary to robustly detect and track multiple targets at the same time, especially when the target is occluded by external objects, occluded by each other, or the target changes its direction of motion. , still a huge challenge

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-objective tracking method based on continuous minimum-energy appearance model
  • Multi-objective tracking method based on continuous minimum-energy appearance model
  • Multi-objective tracking method based on continuous minimum-energy appearance model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0033] The present invention provides a preferred embodiment, which specifically includes the following steps:

[0034] Step 1: Construct an objective function using the observation model, appearance model, motion model, mutual exclusion model, trajectory maintenance model and trajectory correction model;

[0035] 1. Observation model

[0036] The observation model is mainly used to detect the comparison between the tracking trajectory and the initialization trajectory to ensure that the energy is searched in the descending direction: when the position of the target in each direction exactly matches the initialization position, the energy obtained at this time is the minimum energy. track the target by smoothing with a given detection object A more accurate target location can be obtained. The expression for the energy function of the observation model is as follows:

[0037]

[0038] Among them, F represents the total number of frames of the video sequence, N represe...

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 multi-objective tracking method based on a continuous minimum-energy appearance model. The method comprises the steps that an objective function is built by means of an observation model, the appearance model, a motion model, a mutual exclusion model, a track keeping model and a track modifying model; the built objective function is solved by means of the gradient descent method to obtain approximately minimum energy of tracked objectives at each moment and the corresponding number and state of the objectives; a smooth and continuous tracking path is obtained by adopting the intelligent detection method based on the minimum energy. The multi-objective tracking method based on the continuous minimum-energy appearance model can achieve correct correlation of the objectives in the complex scene with clutter, false alarming and detection missing and obtain the stable and continuous tracking path.

Description

technical field [0001] The invention relates to a multi-target tracking method based on a continuous minimum energy appearance model, which belongs to the technical field of computer vision. Background technique [0002] Object tracking technology is a hot topic in the field of computer vision and pattern recognition. It has attracted widespread attention from scholars at home and abroad, and has broad application prospects. The purpose of target tracking is to obtain the position and quantity information of the tracked target, and use the current motion information of the tracked target to predict the subsequent motion state of the target, and finally realize the tracking of the target trajectory and the authentication of identity. In recent years, due to the improvement of object detection performance, detection-based tracking techniques have become more and more popular. These methods mainly use the target's profile, displacement, velocity and other information to constr...

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): G06K9/62
Inventor 朱松豪孙伟李向向陈玲玲
Owner NANJING UNIV OF POSTS & TELECOMM
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