Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Polygonal target segmentation method based on Hough transform and template matching

A target segmentation and template matching technology, applied in image analysis, image enhancement, instrumentation, etc., can solve the problems of long time and large amount of calculation, and achieve the effect of high operation efficiency, improved efficiency, and fast and accurate directional feature capture.

Pending Publication Date: 2022-01-28
ZHEJIANG UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditional template matching has certain limitations when it is used for target recognition, mainly in the parallel movement of the template and the matching process requires a large amount of calculation and takes a long time

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
  • Polygonal target segmentation method based on Hough transform and template matching
  • Polygonal target segmentation method based on Hough transform and template matching
  • Polygonal target segmentation method based on Hough transform and template matching

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The purpose and effects of the present invention will become more apparent by describing the present invention in detail according to the accompanying drawings and preferred implementation examples. It should be understood that the specific implementation examples described here are only used to explain the present invention, not to limit the present invention.

[0038] In this implementation example, set the sliding step size δ 1 is 50, the sliding step δ 2 is 3, the sliding step size δ3 is 3, the rotation angle step α is 1°, and the intersection ratio threshold σ is 0.1. Setting parameters is just an example, not limited thereto, the polygon target segmentation method based on Hough transform and template matching, such as figure 1 As shown, it specifically includes the following steps:

[0039] 1) Perform Canny edge detection on polygonal objects that are adjacent to each other or overlapped in a small range, and record the set of edge points as P={P 1 ,P 2 …P ...

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 polygon target segmentation method based on Hough transform and template matching. The method comprises the following steps: firstly carrying out edge detection on polygon objects in a scene image, and through Hough transform, screening out a cluster of straight lines which are corresponding to reference edges of the objects and are similar in slope ; carrying out contour extraction on an edge image, calculating a number of the objects by combining contour areas of a single object template, and through a K-means clustering algorithm, obtaining straight lines which are in one-to-one correspondence with the objects and represent object direction features; sliding the template sequentially along each straight line by adopting a sparse and then dense strategy in the sliding process, wherein strategy is that a sliding step length is set to be large before a target is found so as to accelerate the matching speed, the sliding step length is set to be small after the target is found, and the template is rotated and translated in a small range at the same time so as to further improve the matching precision, until the optimal matching of each object is found to realize the target segmentation. The method provided by the invention can ensure high recognition and segmentation accuracy while improving the calculation efficiency.

Description

technical field [0001] The invention relates to a polygon target segmentation method based on Hough transform and template matching, which belongs to the field of pattern recognition and image processing. Background technique [0002] In industrial automation manufacturing and daily production and life scenarios, there are many problem scenarios of target recognition and image segmentation that take objects with relatively regular geometric features as the research object, such as parts recognition and detection in the field of intelligent manufacturing, and traffic in the field of intelligent transportation. Logo recognition, etc. Due to the relatively complex surrounding environment, such as lighting factors, viewing angle restrictions, objects adjacent to each other or irregular overlapping placement, etc., it is difficult to realize the recognition and segmentation of this type of object. To solve this problem, the geometric feature detection method and template matchin...

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): G06T7/12G06T7/62G06T7/33
CPCG06T7/12G06T7/13G06T7/62G06T2207/20061G06T2207/20104
Inventor 刘山周彦宏应永康
Owner ZHEJIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products