Unlock instant, AI-driven research and patent intelligence for your innovation.

A target tracking system and a target tracking method based on a correlation filter

A correlation filter and target tracking technology, applied in instruments, image analysis, computing and other directions, can solve problems such as inability to ensure effective target tracking, target tracking failure, etc., to improve the recognition accuracy and speed, improve the recognition accuracy, The effect of ensuring continuity

Active Publication Date: 2019-05-03
厦门瑞利特信息科技有限公司
View PDF12 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, neither the generative method nor the discriminative method can ensure the effective tracking of the target in the same video. In special cases, it is easy to fail to track the target. Once the tracking fails, the entire target recognition and tracking process is terminated. Therefore, it is necessary to An innovative target tracking and recognition method to further improve the recognition accuracy and tracking speed of the target

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 system and a target tracking method based on a correlation filter
  • A target tracking system and a target tracking method based on a correlation filter
  • A target tracking system and a target tracking method based on a correlation filter

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] Please refer to figure 1 , the target tracking system based on the correlation filter provided by Embodiment 1 of the present invention includes:

[0046] An acquisition unit 1, configured to acquire and output the video collected by the video acquisition device;

[0047] The video splitting unit 2 is connected to the acquisition unit 1, and is used to decompose the video into a video frame sequence and output it;

[0048] Tracking identification unit 3 is connected to video splitting unit 2, and tracking identification unit 3 is preset with a target tracking identification algorithm, which is used to identify and output the image features corresponding to the target on each frame picture in the video frame sequence; and for tracking identification The location information of the target on the corresponding picture and output;

[0049] The response rate calculation unit 4 is connected to the tracking recognition unit 3, and is used to calculate the tracking response r...

Embodiment 2

[0077] The difference between Embodiment 2 and Embodiment 1 is that in the target tracking method provided in Embodiment 2, the method for judging the tracking of the target is the second judging method, and the second judging method is based on the target in the two frames of pictures before and after. The overlap rate is used to judge the tracking situation of the target.

[0078] In the second embodiment, it should first be explained that in step S2, the principle of the target tracking system to calculate the overlap rate is as follows:

[0079] Select the original frame used to track the target in the current frame picture, and the position of the original frame represents the position of the target on the current frame picture. Then select the candidate frame for tracking the target in the next frame picture, and then analyze the position information corresponding to the positions of the original frame and the candidate frame on the current frame picture and the next fra...

Embodiment 3

[0087] The difference between Embodiment 3 and Embodiment 1 and Embodiment 2 is that in the target tracking method provided by Embodiment 3, the tracking status of the target is judged based on the tracking response rate and the overlap rate at the same time. That is to say, when the second tracking response rate of the target on the next frame picture is greater than or equal to the first threshold, and the second tracking response rate of the target on the next frame picture is compared with the first tracking response rate on the current frame picture The absolute value of the difference of the response rate is less than or equal to a second threshold, and at the same time, when the overlapping rate of the target in the current frame and the next frame is greater than or equal to a third threshold, it indicates that the tracking of the target is effective;

[0088] Otherwise, it indicates that the tracking of the target has failed.

[0089] The first threshold in the third ...

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 system based on a correlation filter, and the system comprises an obtaining unit which is used for obtaining and outputting a video; the video splitting unitis used for decomposing the video into a video frame sequence; the tracking identification unit is used for tracking and identifying image features corresponding to the targets on each frame of picture in the video frame sequence and tracking and identifying position information of the targets on the corresponding pictures; the response rate calculation unit is used for calculating the tracking response rate of the target based on the first image feature and the second image feature, corresponding to each other in sequence, of the target on the front and rear frames of pictures; the overlapping rate calculating unit is used for calculating the overlapping rate of the position of the target on the front and rear frames of pictures based on the first position information and the second position information, which correspond to each other in sequence, of the target on the front and rear frames of pictures; and the judgment unit is used for judging whether the tracking of the target is effective or not according to the tracking response rate and / or the overlapping rate.

Description

technical field [0001] The invention relates to the technical field of object tracking and recognition, in particular to a correlation filter-based target tracking system and target tracking method. Background technique [0002] According to the tracking method of the target, target tracking methods can generally be divided into generative methods and discriminative methods. The so-called generative method is to model the target area in the current frame, and find the area most similar to the model in the next frame as the target tracking method of the predicted position. The generative methods in the prior art include methods such as Kalman filter and particle filter. . Since the discriminative method has higher target tracking accuracy and tracking efficiency than the generative method, it is currently popular to use the discriminative method to track and detect targets. The so-called discriminative class method is to use the target area as a positive sample in the curre...

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 Applications(China)
IPC IPC(8): G06T7/246
Inventor 谢锦滨顾寅铮张奕
Owner 厦门瑞利特信息科技有限公司