Fast two dimensional object localization based on oriented edges

A target positioning and edge technology, applied in image enhancement, image analysis, data processing applications, etc., can solve problems such as unstable illumination changes

Inactive Publication Date: 2005-10-19
西门子共同研究公司
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the above method is unstable to illumination changes

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
  • Fast two dimensional object localization based on oriented edges
  • Fast two dimensional object localization based on oriented edges
  • Fast two dimensional object localization based on oriented edges

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] Detailed description of the preferred embodiment

[0022] A method for feature-based two-dimensional object localization in grayscale images, which may be based on the determination of oriented edge representations of one or more objects (edge ​​images). For a given edge image, in the sub-sampling preprocessing stage, smoothing and edge filtering can be performed. Edges can be refined. Edge orientations and lengths of edge segments may be determined for the edge image. A distance transform may be determined on the edge image. A matching method that considers point distances and edge orientations to determine the orientation and location of one or more objects in a grayscale image, even in heavily cluttered grayscale images.

[0023] In contrast to area-based algorithms, according to one embodiment of the invention, the object search is not performed based on gray-value images, but based on edge features. Edges are more stable relative to changes in illumination in g...

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

A method for object localization comprises defining an edge model for object localization, and searching an image for an object matching the edge model. Searching comprises defining a region of interest, including a portion of the object, sub-sampling the region of interest, and extracting an edge image comprising edges from the region of interest. Searching further comprises thinning at least one edge of the edge image, determining a distance map between the image and the edge image according to a distance transformation, and matching the edge model to the edge image within a search area defined according to the distance map.

Description

Background of the invention [0001] 1. Technical field [0002] The present invention relates to computer vision, and more particularly to a feature-based two-dimensional object localization method. [0003] 2. Background technology [0004] Fast target location is an important part of a surveillance (inspection) system. Localization methods mainly rely on standardized template matching of gray value patterns. Gray value pattern matching suffers from several disadvantages. For example, template matching is relatively slow, and the slowdown is exacerbated if the search range is large or the method needs to tolerate target rotation. Furthermore, template matching is sensitive to illumination variations that cannot be compensated by normalization for brightness and contrast. [0005] There are several ways to speed up matching operations in the gray-scale domain by using multi-resolution techniques or hierarchical search methods. However, the above methods are not stable ...

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): G06K9/64G06T5/00G06T7/00
CPCG06T7/0046Y10S707/99936G06T2207/20132G06T2207/20041G06T2207/30164G06T7/0091G06T7/0083G06K9/6204G06T7/75G06T7/12G06T7/155G06V10/752
Inventor C·纽鲍尔M·方
Owner 西门子共同研究公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap