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

Target positioning method based on image local self-similarity

A self-similarity and target positioning technology, applied in the field of image processing, can solve problems such as inability to accurately extract targets

Inactive Publication Date: 2018-06-08
ARMOR ACADEMY OF CHINESE PEOPLES LIBERATION ARMY
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The region of interest detection method can only extract the general position of the target, but cannot accurately extract the outline of the target. How to achieve accurate segmentation and positioning of the target has become a technical problem to be solved urgently

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 positioning method based on image local self-similarity
  • Target positioning method based on image local self-similarity
  • Target positioning method based on image local self-similarity

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] In order to make the purpose, content, and advantages of the present invention clearer, the specific implementation manners of the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments.

[0034] Self-similarity is a ubiquitous feature in images, and usually self-similarity is used for fractal image compression. The local self-similarity (local self-similarity) descriptor was proposed by Shechtman in 2007. It is used to describe the shape. It matches the same shape in different images, or the same image has different colors or textures, but has the same shape. Shape features are usually quantified in log-polar form. The local self-similarity descriptor describes and extracts the self-similarity of the color, brightness or geometric features that are regularly repeated in the image. According to the feature that the image has better local self-similarity at the edge, the present invention uses a detectio...

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

PropertyMeasurementUnit
Radiusaaaaaaaaaa
Login to View More

Abstract

The present invention relates to a target positioning method based on image local self-similarity, and relates to the technical field of image processing. The present invention introduces a detectionmethod based on image local self-similarity to accurately segment and position a target; in the method, a region of interest detected by the visual attention model is used to initially find the targetcentroid position, the position is taken as prior information, and the image local self-similarity method is used to carry out regional growth on the vicinity of the position; and by calculating theEuclidean distance between the descriptor of the local self-similarity of each point in the region of interest of the image target and the descriptor of the center point in the region of interest, theEuclidean distance is taken as the similarity basis, a precise segmentation result of the target is obtained, and the centroid position of the target is calculated, and precise positioning of the target can be implemented.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a target positioning method based on local self-similarity of images. Background technique [0002] Regions of Interest (ROI) is the area where people are interested, concerned or noticed when observing and understanding an image, that is, the area in the image that most arouses people's interest and expresses the content of the image. It pays attention to the important concepts presented in the application of the mechanism. The ROI can be considered as the most salient (saliency) pixel set in the image, that is, a set of salient points or interest points. How to automatically extract the region of interest from an image is the region of interest detection technology. [0003] Region of interest detection, that is, salient region detection is to use computer technology to simulate the human visual system, use the visual attention model, extract some key information 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
no application Login to View More
IPC IPC(8): G06T7/11G06K9/32G06K9/62
CPCG06T7/11G06T2207/10004G06V10/245G06V10/25G06F18/22
Inventor 徐振辉毛保全朱锐杨雨迎白向华吴东亚韩小平冯帅李程张天意辛学敏郑博文王之千李俊李晓刚兰图
Owner ARMOR ACADEMY OF CHINESE PEOPLES LIBERATION ARMY