Obstacle detection method and device in indoor shadow environment based on binocular vision

An obstacle detection and binocular vision technology, applied in the field of computer vision, can solve problems such as large amount of calculation, large error and redundant information, and inability to accurately extract obstacles, and achieve accurate, fast and accurate parallax calculation methods. Accurately obtained effect

Active Publication Date: 2020-01-14
SOUTH CHINA UNIV OF TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to uneven illumination and object occlusion, shadows will be generated around obstacles, which will affect the extraction of obstacle contours and subsequent measurement work.
The traditional shadow elimination algorithm reduces the gray level difference between the ground and obstacles when eliminating shadows, so that subsequent obstacles cannot be accurately extracted, and the algorithm parameters need to be manually set and lack of adaptability to the environment
The disparity calculation method based on dense matching has a large amount of calculation and large errors and redundant information when measuring obstacles, which cannot meet the real-time and accuracy requirements

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
  • Obstacle detection method and device in indoor shadow environment based on binocular vision
  • Obstacle detection method and device in indoor shadow environment based on binocular vision
  • Obstacle detection method and device in indoor shadow environment based on binocular vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0024] The present invention is based on a binocular vision-based obstacle detection method in an indoor shadow environment. A binocular vision system is used to detect ground obstacles in an indoor shadow environment. The specific implementation steps are as follows:

[0025] Such as figure 1 As shown, a method for detecting obstacles in an indoor shadow environment based on binocular vision, using a binocular vision system, includes steps:

[0026] (1) Eliminate shadows through the single-scale Retinex algorithm, extract the color saturation of the original image, and fuse it with the image information that eliminates shadows. Adaptively adjust and enhance the gray level difference between the ground and obstacles through the ambient brightness information to distinguish obstacles come out;

[0027] (2) Use the seed filling algorithm to fill the ground area of ​​the fused image, and then obtain the obstacle area through threshold segmentation, erosion, and expansion operati...

Embodiment 2

[0046] A binocular vision-based obstacle detection device in an indoor shadow environment, using a binocular vision system, including:

[0047] The shadow elimination module is used to eliminate shadows through the single-scale Retinex algorithm, extract the color saturation of the original image, and fuse with the image information for shadow elimination, and adaptively adjust and enhance the gray level difference between the ground and obstacles through the ambient brightness information, and Obstacles are distinguished;

[0048] The obstacle detection module is used to use the seed filling algorithm to fill the ground area of ​​the fused image, and then obtain the obstacle area through threshold segmentation, erosion, and expansion operations, and obtain its circumscribed rectangle;

[0049] The obstacle measurement module is used to use the binocular vision system to use the obtained obstacle area as a template to match and calculate the parallax of the center point in the...

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 method for detecting obstacles in an indoor shadow environment based on binocular vision, which adopts a binocular vision system and includes the steps of: (1) eliminating shadows, extracting the color saturation of the original image, and merging with image information for eliminating shadows , adjust and enhance the gray level difference between the ground and obstacles adaptively through the ambient brightness information; (2) Use the seed filling algorithm to fill the ground area of ​​the fused image, and then obtain the obstacle area through threshold segmentation, erosion, and expansion operations; (3) Using the binocular vision system, the obtained obstacle area is used as a template to match and calculate the parallax of the center point in the right camera image, and calculate the three-dimensional coordinates of the center point and the width and distance of the obstacle. The invention also discloses a binocular vision-based obstacle detection device in an indoor shadow environment. The present invention can completely extract obstacles in an indoor shadow environment, is simple and efficient, has good real-time performance and precision, and is suitable for navigation and obstacle avoidance of mobile robots.

Description

technical field [0001] The invention belongs to the field of computer vision, mainly relates to obstacle detection and binocular measurement, in particular to a method and device for detecting obstacles in an indoor shadow environment based on binocular vision. Background technique [0002] In recent years, with the development of computer and robot technology, machine vision has been widely used in intelligent manufacturing, artificial intelligence and industrial production. The autonomous navigation of mobile robots based on visual guidance has become a hot research topic, and the detection and measurement of ground obstacles is the key and basis for autonomous navigation and obstacle avoidance of robots. However, due to uneven illumination and object occlusion, shadows will be generated around obstacles, which will affect the extraction of obstacle contours and subsequent measurement work. The traditional shadow elimination algorithm reduces the gray level difference bet...

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 Patents(China)
IPC IPC(8): G06K9/00G01B11/02G01C3/00
CPCG01B11/02G01C3/00G06V20/20
Inventor 翟敬梅刘坤
Owner SOUTH CHINA UNIV OF TECH
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