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

A target tracking method based on local features and scale pooling

A target tracking and local feature technology, applied in computer parts, image analysis, image enhancement, etc., can solve the problems of low robustness and poor accuracy of target tracking algorithms, and achieve improved tracking accuracy and stability, and improved accuracy. , the effect of improving the robustness of the algorithm

Active Publication Date: 2022-07-01
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the above-mentioned research problems, the purpose of the present invention is to provide a target tracking method based on local features and scale pools to solve the problem of low robustness and poor accuracy of target tracking algorithms in complex environments such as illumination changes, scale changes, and background interference. question

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
  • A target tracking method based on local features and scale pooling
  • A target tracking method based on local features and scale pooling
  • A target tracking method based on local features and scale pooling

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0124] The present invention will be further described below with reference to the accompanying drawings and specific embodiments.

[0125] The present invention is based on the KCF framework. The first frame of image acquires the target according to the initial information, and the classifier is trained based on two features of the target to obtain the target model of the corresponding feature and the classifier regression coefficient for reinitialization. The second frame of image uses the scale pool to obtain different scales. , and extract 31-dimensional FHOG features as feature 1, and fuse 1-dimensional grayscale features, 1-dimensional de-averaged grayscale features, and 1-dimensional local binary pattern LBP features into 3-dimensional fusion features as feature 2; The initialized target model and classifier regression coefficients corresponding to feature 1 and feature 2 are used to obtain the multi-layer kernel correlation filter response map corresponding to the two f...

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 target tracking method based on local features and scale pools, which belongs to the technical field of grayscale image target tracking and solves the problem of poor accuracy of target tracking algorithms in complex environments such as illumination changes, scale changes and background interference. In the present invention, the first frame of image obtains the target according to the initial information, and the classifier is trained based on the two characteristics of the target, and the target model and the classifier regression coefficient are re-initialized. and feature 2; based on the initialized target model and the classifier regression coefficient, the multi-layer kernel correlation filter response map of the two features is obtained, and then linearly interpolated to a consistent size, weighted and fused to obtain the multi-layer kernel correlation filter response map, and then the target's correlation filter response map is obtained. The predicted position and the predicted scale are to complete one target tracking. If the tracking is not over, the tracking from the second frame image to the third frame image is realized until the loop reaches the last frame image. The present invention is used for target tracking.

Description

technical field [0001] A target tracking method based on local features and scale pools is used for target tracking and belongs to the technical field of grayscale image target tracking. Background technique [0002] Target tracking is of great significance and value in the field of computer vision research. It is widely used in many fields, such as intelligent video surveillance, medical treatment, human-computer interaction and other civil fields. In the military, fast and accurate tracking of enemy moving targets search and tracking, etc. Object tracking is mainly divided into generative models and discriminative models. The generative model completes the matching between the candidate target and the target model by establishing the target mathematical model, and takes the most similar candidate region as the prediction target. The discriminative model trains the classification algorithm with a training set consisting of positive samples belonging to the target and nega...

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 Patents(China)
IPC IPC(8): G06T7/246G06T7/269G06V10/80G06V10/764G06K9/62
CPCG06T7/246G06T7/269G06T2207/20056G06T2207/20081G06T2207/10016G06F18/253G06F18/214
Inventor 张文超彭真明李美惠龙鸿峰彭凌冰秦飞义张鹏飞曹兆洋孔轩张兰丹程晓彬
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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