Target detection method, device and storage device based on superpixel segmentation algorithm
A technology for superpixel segmentation and target detection, which is applied in the field of target detection methods, devices and storage devices based on superpixel segmentation algorithms, can solve the problems of complex algorithms, large or small rectangular frames, and insufficient positioning accuracy, and achieves The effect of high positioning accuracy
Active Publication Date: 2021-02-19
ZHEJIANG DAHUA TECH CO LTD
View PDF11 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Based on the positioning of the detection algorithm, the final output result is a rectangular frame containing the target. Although the object can be detected, the positioning accuracy is not high enough, and the rectangular frame is too large or too small.
Based on the positioning of the segmentation algorithm, the object boundary is found by clustering the pixels, and the positioning accuracy is high, but the algorithm is complex and difficult to implement
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
[0014] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.
[0015] The terms "first", "second", and "third" in this application are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of indicated technical features. Thus, features defined as "first", "second", and "third" may explicitly or implicitly include at least one of these features. In the description of the present application, "plurality" means at least t...
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 target detection method, device and storage device based on a superpixel segmentation algorithm. The method includes: using a target detection algorithm to perform target detection on the image to be detected to obtain an initial detection frame; using a superpixel segmentation algorithm to segment the image to be detected to obtain a superpixel region; obtaining superpixel regions that each border in the initial detection frame passes through , get the set of superpixel regions corresponding to each border; in the superpixel region set, vote whether to move the border according to the distribution of clustering pixels in each superpixel region and the voting threshold corresponding to the border; when moving the border When the affirmative votes cast meet the predetermined conditions, the frame is moved and the voting threshold is updated according to the predetermined rules. Through the above method, the present invention can optimize the position of the initial detection frame by using the superpixel segmentation algorithm and the movement strategy of the initial detection frame, so as to achieve higher positioning accuracy.
Description
technical field [0001] The present application relates to the technical field of image processing, in particular to a target detection method, device and storage device based on a superpixel segmentation algorithm. Background technique [0002] At present, the positioning of the target is mainly realized from two aspects. One aspect is to detect the approximate position of the target through the detection algorithm. Another aspect is to obtain the precise outline of the target through the segmentation algorithm. Based on the positioning of the detection algorithm, the final output is a rectangular frame containing the target. Although the object can be detected, the positioning accuracy is not high enough, and the rectangular frame is too large or too small. Based on the positioning of the segmentation algorithm, the object boundary is found by clustering the pixels, and the positioning accuracy is high, but the algorithm is complex and difficult to implement. Contents of...
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): G06K9/00G06K9/46G06T7/10G06T7/73
CPCG06T7/10G06T7/73G06V20/00G06V10/454
Inventor 薛佳乐
Owner ZHEJIANG DAHUA TECH CO LTD