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

Road image segmentation method based on normal feature

An image segmentation and frame image technology, applied in the field of computer vision, can solve problems such as the inability to effectively segment road plane images, and achieve a wide range of applications

Active Publication Date: 2017-09-29
SHANDONG UNIV
View PDF7 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This image segmentation method may not be able to effectively segment the road plane image

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 image segmentation method based on normal feature
  • Road image segmentation method based on normal feature
  • Road image segmentation method based on normal feature

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] A road surface image segmentation method based on normal features, which is used to segment the image in the straight road plus shadow experimental environment, includes the following steps:

[0052]1) Obtain the RGB-D image through the camera, decompose the RGB-D image into frame images, and obtain the internal parameter K of the camera;

[0053]

[0054] Among them, d x and d y Respectively represent the number of length units occupied by a pixel point in the horizontal direction and vertical direction, u 0 and v 0 is the center of the plane where the frame image is located, and γ is the tilt parameter of the coordinate axis in the camera coordinate system with the camera optical center as the origin;

[0055] 2) The two-dimensional depth image I d The pixels in are converted from the image coordinate system to the camera coordinate system, where the conversion relationship is shown in formula (1):

[0056]

[0057] Among them, x and y are coordinates in th...

Embodiment 2

[0064] The road surface image segmentation method based on normal features as described in Embodiment 1, the difference is that the image in the experimental environment of the straight road plus shadow plus the left side and the vehicle in front is segmented; γ=0.

[0065] Such as Figure 5-8 As shown, the road surface image segmentation method based on normal features can clearly and accurately segment the safe driving area and the collision avoidance area for the images in the experimental environment of straight road plus shadow plus left and front cars.

Embodiment 3

[0067] The road surface image segmentation method based on normal features as described in embodiment 1, the difference is that the image under the experimental environment with cars on both sides is added to the straight road plus shadow; the camera in the step 1) is a vehicle-mounted dual camera. The same binocular camera can simultaneously acquire color images and two-dimensional depth images.

[0068] Such as Figure 9-12 As shown, the road surface image segmentation method based on normal features segmented the image in the experimental environment of straight road plus shadow and cars on both sides, and clearly and accurately segmented the safe driving area and the collision avoidance area.

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 present invention relates to a road image segmentation method based on a normal feature. A binocular camera is used to obtain a depth image which, in combination with the internal reference of the camera, is converted into a planar normal image. A road plane is determined on the planar normal image by using the normal characteristics to complete the road plane segmentation processing. The segmented road plane is marked as a safe driving area, and the remaining area is marked as an anti-collision area.

Description

technical field [0001] The invention relates to a road surface image segmentation method based on normal features, belonging to the technical field of computer vision technology. Background technique [0002] Thanks to the rapid development of artificial intelligence technology, the automobile, one of the great inventions of the industrial age, is also marching towards a new era. Google, Tesla, Baidu and other companies are all developing self-driving cars. In the future, the competition for self-driving cars will become extremely fierce. [0003] Google's self-driving car uses cameras, radar sensors and laser range finders to judge traffic conditions around the vehicle, and uses GPS and high-precision digital maps for navigation. Although the U.S. Department of Motor Vehicles has issued legal license plates for Google's self-driving cars and allowed them to go on the road, there is still a certain distance from the popularity of self-driving cars. It's not just because th...

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
IPC IPC(8): G06K9/00G06K9/34G06K9/46G06T7/11G06T7/80
CPCG06T7/11G06T7/80G06V20/52G06V20/588G06V10/267G06V10/56
Inventor 陈辉肖志光
Owner SHANDONG 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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com