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

Object Recognition Method Based on Salient Contour Feature Fragments

A target recognition and contour feature technology, applied in the field of target recognition, can solve the problems of unreasonable contour division, evaluation, and no contour fragments, and achieve the effect of improving the target recognition rate.

Active Publication Date: 2022-05-27
SHENYANG LIGONG UNIV
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] A target recognition method based on salient contour feature fragments, the purpose of which is to solve the problem of unreasonable contour division or no evaluation of contour fragments in target recognition based on contour fragments. The method calculates the curvature of the obtained object contour, Segment the contour according to the contour division scheme, and evaluate the value of the contour segment from the three aspects of curvature difference, fluctuation range and bending ratio

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
  • Object Recognition Method Based on Salient Contour Feature Fragments
  • Object Recognition Method Based on Salient Contour Feature Fragments
  • Object Recognition Method Based on Salient Contour Feature Fragments

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] In view of the problem of unreasonable contour division or no evaluation of contour fragments in the above target recognition, the overall evaluation of contour fragments should be considered in the process of obtaining contour fragments, so as to ensure that the fragments have significant features. The present invention proposes a target recognition algorithm based on salient contour feature segments. The contour is segmented according to the contour division scheme, and the value of the contour segment is evaluated from three aspects of curvature difference, fluctuation amplitude and bending ratio, and the importance of the contour segment is evaluated from the length of the contour segment relative to the overall contour length. . On this basis, the unreasonably divided segments are merged to obtain the segmentation result of contour segments. The similarity measurement of the reasonably divided contour fragments and the contour fragment test library is carried out ...

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 target recognition method based on salient contour feature segments comprises the following steps: step 1, contour curvature calculation and division; step 2, obtaining contour segments with salient features; and step 3, target recognition of the contour segments. Compared with the existing technology, the present invention determines the salience evaluation parameters for the division of contour segments, conducts overall evaluation of the contour segments through value and importance, ensures that the divided contour segments have salient features, and is effectively applied to the contour segments target recognition, improving the target recognition rate.

Description

technical field [0001] The invention relates to the field of target recognition, in particular to a target recognition method based on salient contour feature segments. Background technique [0002] Target detection and recognition technology has been more and more widely used in military and civilian fields such as aerospace, satellite navigation, video surveillance, intelligent robot navigation, unmanned vehicle driving, attitude recognition, shape retrieval, animation synthesis, and household smart devices. Contour features have incomparable advantages in object recognition: even when an image object loses its color or texture features, the human eye can still identify the object's category. Numerous experiences have shown that the contour feature is a higher-level visual information, and the recognition robustness and stability are higher. Target recognition based on contour fragments Because contour division cannot guarantee that the fragments have salient features, an...

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 Patents(China)
IPC IPC(8): G06T7/13G06T5/00G06T7/60
CPCG06T7/13G06T7/60G06T2207/20192G06T5/70
Inventor 宋建辉李云功刘砚菊于洋刘韵婷
Owner SHENYANG LIGONG UNIV