Single-target tracking method based on space-time context

A spatio-temporal context and single-target technology, applied in image data processing, instruments, character and pattern recognition, etc., can solve the problems of low tracking effect and low accuracy, reduce model drift and improve tracking accuracy

Pending Publication Date: 2020-01-07
KUNMING UNIV OF SCI & TECH
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a single-target tracking method based on spatio-temporal context, which is used to solve the problems of low tracking effect and low accuracy rate caused by complex video scene interference and changes in the target itself during the visual target tracking process.

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
  • Single-target tracking method based on space-time context
  • Single-target tracking method based on space-time context
  • Single-target tracking method based on space-time context

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0029] Embodiment 1: as figure 1 and figure 2 As shown, a single target tracking method based on spatiotemporal context, the specific steps of the single target tracking method based on spatiotemporal context are as follows:

[0030] Step1. Obtain the initial position information and scale information of the target.

[0031] In Step 1, since the invention verifies the effectiveness of the invention on the public test set OTB-2013, the position information and scale information of the first frame of the tracking target are marked in the test set. By reading the annotation file of the test set, the initial information of the target can be obtained.

[0032] Step2, extract the HOG feature and color histogram feature of the target and the CN feature around the target according to the initial information obtained in Step1, and use the principal component analysis to reduce the 11-dimensional CN feature to 3 dimensions.

[0033] The specific steps of using the principal componen...

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 relates to a single-target tracking method based on space-time context, and belongs to the technical field of video target tracking. The method comprises the following steps: firstly, extracting direction gradient histogram features and color histogram features from a target area and a background area; fusing the correlation filtering responses of the two features through a fixed weight strategy, and then performing dimension reduction on background color features extracted around the target through a PCA algorithm, and obtaining a space-time context response through a maximum likelihood function based on a Bayesian framework. The two model responses are fused by adopting an adaptive weight fusion strategy, an estimated target position is obtained based on the fused responsegraph, and the target scale change problem is solved by adopting a scale estimation method; according to the method, the tracking drift condition of the tracking target caused by factors such as shielding, scale change and illumination can be effectively relieved, and robust target tracking is realized.

Description

technical field [0001] The invention relates to a single target tracking method based on spatio-temporal context, and belongs to the technical field of video target tracking. Background technique [0002] Target tracking technology is currently widely used in intelligent transportation, video surveillance, human-computer interaction, and military guidance and other fields. In recent decades, great progress has been made in the field of object tracking, but due to the complex changes of video scenes and object appearance during object motion, it is still a very challenging problem to design a robust and efficient object tracking algorithm. [0003] According to the different modeling methods of target models, target tracking models can be divided into two categories: generative models and discriminative models. The target tracking algorithm based on the generative model uses the generative model to describe the apparent characteristics of the target, minimizes the reconstruc...

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): G06T7/246G06T7/262G06K9/62
CPCG06T7/251G06T7/262G06T2207/10016G06T2207/20024G06F18/2135
Inventor 尚振宏陈万敏
Owner KUNMING UNIV OF SCI & 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