A semi-automatic labeling method for video objects based on correlation filtering and tracking
A technology of correlation filtering and automatic labeling, applied in the field of computer vision, can solve problems such as difficult to satisfy, limited human energy, time-consuming and labor-intensive, and achieve the effect of saving time and manpower consumption and strong robustness
Active Publication Date: 2021-06-18
HANGZHOU JIESHANG SMART GRID TECH CO LTD
View PDF9 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The traditional purely manual data labeling method, due to its inherent characteristics: limited human energy, has the disadvantages of time-consuming and manpower-consuming, it is difficult to meet the needs of computer vision for a large number of labeled data samples
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0020] In order to make the purposes, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments It is only a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.
[0021] The technical scheme adopted in the present invention is as follows: a tracking algorithm of correlation filtering is used to track the target to be marked in the video, and the target to be marked in the video is preliminarily marked automatically by using the tracking result of the algorithm, and then the ...
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
Login to View More Abstract
The invention discloses a semi-automatic tagging method for video objects based on correlation filter tracking. The present invention uses a target tracking algorithm to track the target to be marked in the video, uses the tracking result obtained by the algorithm to perform preliminary automatic marking on the target to be marked in the video, and then checks the video target automatically by combining manual and mathematical calculations. Annotate the results, and finally complete the video target annotation. The present invention combines manual detection and verification with mathematical calculations to obtain a large number of marked image samples with less manpower consumption. In addition, the correlation filter tracking algorithm used in the present invention is robust and can be performed every 3 frames Manual inspection and correction saves time and manpower consumption to a great extent.
Description
technical field [0001] The invention belongs to the technical field of computer vision, and relates to a semi-automatic labeling method for video objects based on correlation filtering and tracking. Background technique [0002] With the continuous application of machine learning technology in the field of computer vision, the demand for labeled data is increasing. The traditional pure manual data labeling method, due to its inherent characteristics: limited human energy, has the disadvantage of time-consuming and labor-intensive, and it is difficult to meet the needs of a large number of labeled data samples for computer vision. In particular, video data annotation is more difficult than simple image data annotation. The annotation of a piece of video data is often equivalent to tens of thousands or even millions of image data annotations. However, the video data itself is a sequence of continuously changing image information, and the image information between consecutive ...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/20
CPCG06T7/20G06T2207/10016G06T2207/20024
Inventor 尚凌辉王弘玥张兆生
Owner HANGZHOU JIESHANG SMART GRID TECH CO LTD