Target tracking method based on TLD (Tracking-Learning-Detection) algorithm

A target tracking and target technology, which is applied in the field of target tracking, can solve problems such as easy failure of tracking, inaccurate prediction results, narrowing of TLD algorithm detection area, etc., and achieve the effect of improving real-time performance and improving real-time performance

Active Publication Date: 2016-12-07
XIDIAN UNIV
View PDF3 Cites 54 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But this method has a fatal flaw: that is, when the tracked target has shape changes or occlusions, the tracking is easy to fail; therefore, for long-term tracking or tracking when the tracked target has shape changes, many Use detection instead of tracking
[0007] Then, w

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 (Tracking-Learning-Detection) algorithm
  • Target tracking method based on TLD (Tracking-Learning-Detection) algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] See figure 1 , figure 1 It is a schematic flowchart of a TLD algorithm-based target tracking method provided by an embodiment of the present invention. Wherein, the TLD algorithm includes a tracking module, a detection module and a learning module, and the method includes the following steps:

[0048] Step a, initializing the selected target area from the first frame of image;

[0049] Step b, the tracking module uses the median optical flow method to predict and determine the predicted target based on the target area information in the previous frame image as the target tracking result;

[0050] Step c, judging whether the number of pixels occupied by the target area in the current frame image in the previous frame image is greater than the pixel threshold; if so, shrinking the target area in the previous frame image and the current frame according to a certain aspect ratio image, the current frame image is globally traversed in a sliding window manner to obtain the...

Embodiment 2

[0082] See figure 2 , figure 2 It is a schematic diagram of the working principle of a detection module based on the TLD algorithm provided by the embodiment of the present invention. This embodiment focuses on the improvement of the detection module on the basis of the above embodiments, combined with the workflow of the TLD algorithm.

[0083] The workflow of the TLD algorithm is as follows:

[0084] The first step is to select the position and size of the target in the starting frame;

[0085] At the start frame of the video (or picture sequence), manually determine a rectangle containing the target with the mouse to obtain the position and size of the target to be tracked, that is, record the target coordinates, width and height.

[0086] In the second step, the tracking module and the detection module process each frame of image respectively to obtain their respective results;

[0087] Tracking module: Use the median optical flow method to get the result of the trac...

example 1

[0132] Example 1, the initial frame and the second frame: the purpose is to obtain the target area of ​​the second frame. Select the target position and size in the initial frame, find the same position (same size) in the second frame, set the center coordinates of this position as: (x, y) (x width direction, y height direction), and the target size is : width (width), height (height); then the area size is: upper left vertex bottom right vertex The center position is still (x,y).

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 (Tracking-Learning-Detection) algorithm. The method comprises the steps of: initially selecting a target region from a first frame of image; by adopting a mid-value optical flow method, according to target region information in a previous frame of image, predicting a determined prediction target as a target tracking result; judging whether a number of pixel points in a current frame of image, which are occupied by the target region in the previous frame of image, is greater than a pixel threshold value; if yes, shortening the target region in the previous frame of image and the current frame of image according to a certain length-width ratio, and carrying out global traversal in a mode of a sliding window so as to obtain to-be-selected targets; if no, carrying out local region partitioning on the current frame of image, and carrying out local traversal in a mode of the sliding window so as to obtain to-be-selected targets; processing at least one to-be-selected target to form a target detection result; and according to the target tracking result and the target detection result, determining a target tracking region. According to the target tracking method disclosed by the invention, a detection module and a learning module of the TLD algorithm are improved, and real-time performance of target tracking is improved.

Description

technical field [0001] The invention relates to the technical field of target tracking, in particular to a target tracking method based on a TLD algorithm. Background technique [0002] Using a camera for long-term tracking of a target, a key issue is that when the target reappears in the camera's field of view, the system should be able to re-detect it and start re-tracking. However, during the long-term tracking process, the tracked target will inevitably undergo shape changes, lighting conditions changes, scale changes, occlusions, etc. In the traditional tracking algorithm, the front end needs to cooperate with the detection module. When the tracked target is detected, it starts to enter the tracking module. After that, the detection module will not intervene in the tracking process. But this method has a fatal flaw: that is, when the tracked target has shape changes or occlusions, the tracking is easy to fail; Use detection instead of tracking. Although this method c...

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): G06T7/20
CPCG06T2207/10016G06T2207/20081
Inventor 赵小明向健勇胡淑桃周梦姣
Owner XIDIAN 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

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