Method for detecting unstructured road on basis of Haar texture

A road detection, unstructured technology, applied in the direction of image data processing, instrument, character and pattern recognition, etc., can solve the problems of high computational complexity, difficult to meet the requirements of intelligent vehicle driving system, poor real-time performance, etc., to overcome excessive voting , to achieve rapidity, to achieve the effect of accuracy

Inactive Publication Date: 2013-02-06
HANGZHOU DIANZI UNIV
View PDF1 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when this method uses the multi-scale and multi-directional characteristics of Gabor wavelet for texture feature extraction, there are problems such as high computational complexity and poor real-time performance, which is difficult to meet the needs of intelligent vehicle driving systems

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
  • Method for detecting unstructured road on basis of Haar texture
  • Method for detecting unstructured road on basis of Haar texture
  • Method for detecting unstructured road on basis of Haar texture

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] The present invention will be further described below in conjunction with the accompanying drawings and specific examples.

[0047]The invention proposes an unstructured road detection method based on the design of a Haar rectangle template and the extraction of Haar texture features by using an integral map. It is proposed to construct the basic rectangular template in four directions, and adopt the method of orthogonal correction to obtain the filter response in any direction, so as to realize the extraction of texture features, reduce the calculation amount of the algorithm, and improve the real-time performance. On the basis of obtaining the texture direction, the estimation of the vanishing point of the road is realized by using the voting mechanism proposed by the present invention. Finally, based on the vanishing point constraint, combined with the OCR feature and the color difference of the adjacent area, the detection of the first main boundary is realized. At ...

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 relates to a method for quickly detecting an unstructured road on the basis of a Haar texture. The conventional method has the problems of high computation complexity, poor real-time performance and the like. According to the invention, a new method for extracting Haar textural features is provided, an idea of introducing an integral image is used for realizinv the quickness of Haar texture extracting, the accuracy of Haar feature representation is realized through orthogonal correction, and a new voting mechanism is proposed; and moreover, under the constraint of end points, the unstructured road is partitioned through utilizing optical character recognition (OCR) features and the color difference of the adjacent areas. The method can effectively detect the road end points of unstructured roads which do not have lane lines or marks and have unclear road boundaries, changeable road shapes and the like; and the method has a good function of detecting the unstructured roads.

Description

technical field [0001] The invention belongs to the field of lane detection, in particular to a Haar texture-based unstructured road detection method. Background technique [0002] Common unstructured roads such as country roads and wild environments. Unstructured roads generally have the following characteristics: no lane lines or markings, road boundaries are unclear, road shapes change, and shadows, water marks, and sand on the road change the surface characteristics of the road. It is much more complicated and difficult to identify than structured roads. In recent years, for the detection of unstructured roads, the well-known method is to use Gabor wavelet to extract road texture features, on this basis to obtain the coordinates of the vanishing point, and finally realize the segmentation of unstructured roads. However, when this method uses the multi-scale and multi-directional characteristics of Gabor wavelet for texture feature extraction, it has problems such as hi...

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): G06K9/46G06T7/00
Inventor 王永忠文成林骆光州王晓云汪圆圆
Owner HANGZHOU DIANZI UNIV
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