Road detection method with image edge and region features integrated

A technology of road detection and regional features, applied in image enhancement, image analysis, image data processing, etc., to achieve the effects of uniform area, precise and smooth edges, good real-time and robustness

Inactive Publication Date: 2017-07-21
南宁市正祥科技有限公司
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, lidar can only obtain depth information, and the detection of color information on the road is actually the key to safe automatic driving, such as road lane lines, arrow signs, traffic lights, etc.
Existing road color information detection methods are mainly obtained by vehicle cameras, however, extracting from vehicle video images is a challenging task

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
  • Road detection method with image edge and region features integrated
  • Road detection method with image edge and region features integrated

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The following specific examples further illustrate the present invention, but are not intended to limit the present invention.

[0031] A road detection method that fuses image edge and region features, including the following steps:

[0032] S1: Convert the color channel image into a grayscale image, and perform histogram equalization and filtering preprocessing;

[0033] S2: Use the custom difference operator and the region growing method to further segment the processed grayscale image, and obtain the edge and region features of the image respectively;

[0034] S3: Combine the complementary characteristics of region and edge segmentation, and fuse the two kinds of information to perform image segmentation on vehicle-mounted videos obtained under different conditions to realize road detection.

[0035] The method for converting the color channel image into a grayscale image in step S1:

[0036] Use the following formula to convert the color channel image obtained by...

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 road detection method with image edge and region features integrated. The method comprises the following steps: S1, a color channel image is converted to a gray image, and histogram equalization and filtering preprocessing are carried out; S2, a self-defined difference operator and a region growing method are used for further segmenting the processed gray image, and edge and region features of the image are acquired respectively; and S3, in combination of region and edge segmentation complementary features, the two kinds of information are integrated to carry out image segmentation on a vehicle-mounted video obtained in a different condition, and road detection is realized. The method of the invention can acquire road segmentation with accurate and smooth edges and uniform regions, and has good real-time performance and robustness.

Description

technical field [0001] The present invention specifically relates to a road detection method for fusing image edge and regional features. Background technique [0002] Smart car is an important platform for the research and final application of vehicle autonomous driving technology. The premise of realizing autonomous driving is that the vehicle can detect and utilize road information quickly and effectively. To this end, lidar devices are often used to detect various dynamic and static obstacle information in the environment. However, lidar can only obtain depth information, and the detection of color information on the road is actually the key to safe automatic driving, such as road lane lines, arrow signs, traffic lights, etc. Existing methods for road color information detection are mainly obtained by vehicle-mounted cameras, however, extraction from vehicle-mounted video images is a challenging task. SUMMARY OF THE INVENTION [0003] The technical problem to be sol...

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): G06T7/11G06T7/12G06T7/44G06T7/174G06K9/00
CPCG06T2207/20221G06T2207/30256G06T2207/10024G06T2207/20032G06V20/588
Inventor 不公告发明人
Owner 南宁市正祥科技有限公司
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