Target tracking method based on TLD algorithm framework

A target tracking and algorithm technology, applied in the field of target tracking, can solve the problems of TLD tracking algorithm calculation amount, large room for improving robustness, poor real-time tracking performance, weak robustness, etc., achieve good classification ability and improve real-time performance , the effect of improving tracking accuracy and robustness

Pending Publication Date: 2018-08-24
CHINA JILIANG UNIV
View PDF0 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The TLD algorithm better solves the problem of deformation and occlusion of the tracked target during the tracking process, and can realize long-term online tracking of the target. However, the current TLD tracking algorithm has a large amount of calculation, high computing cost, and poor real-time tracking performance. , the robustness is not strong
[0006] Therefore, in view of the above problems, it can be seen that the current TLD tracking algorithm still has a lot of room for improvement in terms of calculation volume and robustness. How to effectively improve the TLD tracking algorithm from multiple perspectives will be the focus of research for a period of time

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
  • Target tracking method based on TLD algorithm framework
  • Target tracking method based on TLD algorithm framework
  • Target tracking method based on TLD algorithm framework

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] Attached below figure 2 , the technical solution of the present invention will be described in detail.

[0035] The present invention improves the existing TLD algorithm in two aspects, and the following is a detailed description of the improvements.

[0036] 1. Improvements to the design of the tracker in the TLD algorithm

[0037] In the original TLD tracking algorithm, the tracker uses the forward-backward tracking algorithm and the NCC predictor to screen the local tracker. For the FB (forward-backward tracking) method, the optical flow method needs to work backwards and forwards twice, and the processing time Too long, in the present invention, the local tracker is evenly arranged to the midpoint of the image block, and it is limited to the activities of each image block, which solves the problem of error drift that may occur in the original TLD algorithm, and uses the spatio-temporal context predictor and NCC predictor A cascade of predictors is formed to filte...

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 target tracking method based on a TLD algorithm framework. The method comprises steps that (1) a user selects a tracking target in an initial frame, and initializes the algorithm; (2) a local tracker in a tracker module predicts the position in the next frame by an optical flow method and a cascaded predictor; (3) a detector detects the target of the current frame through the sliding window scanning and the cascaded classifier, and sends a classification result to a learning module, wherein the tracker and the detector work in parallel; (4) an integrator determines afinal target position by determining and integrating a target result obtained by the tracker and the detector; (5) the learning module corrects the results of the tracker and the detector through structural constraints and updates a target sample; (6) whether the video frame is finished is determined, and if not, the steps (2)-(4) are repeated until the end of the tracking. The method can improvethe robustness of the tracking target and ensures the real-time performance in the tracking process.

Description

technical field [0001] The invention belongs to the field of target tracking, and in particular relates to a target tracking method based on a TLD algorithm framework. Background technique [0002] Object tracking technology is a hot topic in the field of computer vision, and its research value and practical value are very important. The so-called target tracking technology refers to the use of computer and camera equipment to imitate the human visual system, obtain image sequences through camera equipment for analysis and processing, and calculate the parameters of the required target, such as the coordinate position information of the moving target, the target area, the target size, etc. , according to the different feature information of the target, correlate the target of interest in the image, and get the complete trajectory of the target of interest, which has important research and application value in many fields, such as intelligent transportation systems in the civ...

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): G06T7/269G06T7/246G06K9/62
CPCG06T7/248G06T7/269G06T2207/10016G06T2207/20081G06F18/24147G06F18/24
Inventor 李亚波卿兆波王满生
Owner CHINA JILIANG UNIV
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