A fast ranging method for targets in the region of interest in complex scenes

A technology of area of ​​interest and ranging method, which is applied in the field of fast ranging of targets in the area of ​​interest, can solve the problem of difficult matching of points with the same name in the left and right images, and achieve the effect of improving accuracy

Active Publication Date: 2022-07-08
北京理工雷科电子信息技术有限公司
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the above-mentioned technical problems, the present invention proposes a method for fast ranging of objects in the region of interest in complex scenes, which can well solve the problem that the same-named points in the left and right images are difficult to match due to the existence of parallax in binocular stereo vision ranging. question

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
  • A fast ranging method for targets in the region of interest in complex scenes
  • A fast ranging method for targets in the region of interest in complex scenes
  • A fast ranging method for targets in the region of interest in complex scenes

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0033] Generally speaking, one of the key problems for the automatic obstacle avoidance system to realize the obstacle avoidance function is the distance perception of obstacles. The present invention provides a method for rapid ranging of targets in the area of ​​interest in complex scenes, which can quickly and accurately perceive obstacles. distance of things. The overall flow chart of the present invention is as follows figure 1 As shown, the present invention is described in further detail below in conjunction with the accompanying drawings and examples:

[0034] 1) Click on the area of ​​interest in the left image, and capture the image img of the area of ​​interest:

[0035] In the left image, take the point clicked by the person as the center, and intercept the image img of the area of ​​interest of m*n size.

[0036] 2) Perform region segmentation on all region-of-interest images img, and extract the centroid coordinates of all segmented regions:

[0037] 21) In or...

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 fast ranging of objects in a region of interest in complex scenes. The method performs the following processing on a binocular image obtained by a binocular camera: firstly, the region of interest is selected in the left image, and the selected point is The image img of the region of interest is intercepted in the center; Gaussian filtering is performed on the region of interest, the gradient map is obtained for the filtered image, and the watershed segmentation operation is performed on the basis of the gradient map. Domain centroid point; using the normalized cross-correlation matching principle, the centroid point extracted in the left image is matched with the same name point in the right image; finally, the matched point pair with the same name is brought into the distance calculation formula, respectively, to calculate the target distance; By repeating the above steps, the real-time distance measurement can be performed on the moving target object in the area of ​​interest. The invention adopts the technology of combining watershed segmentation and normalized cross-correlation matching, and realizes the ranging function of moving targets in the area of ​​interest.

Description

technical field [0001] The invention belongs to the technical field of image processing and stereo vision, and in particular relates to a method for fast ranging of objects in a region of interest in complex scenes. Background technique [0002] Vision is an important means for humans to observe the world and recognize the world. About 80% of the information is obtained by vision. Machine vision is a science and technology that studies the use of computers to simulate biological appearance or visual functions. Binocular stereo vision is one of the important forms of machine vision. The premise and basis of distance measurement as obstacle detection and path planning is binocular stereo vision. One of the important applications of ranging. [0003] The binocular stereo vision ranging method has the advantages of rich information and wide detection distance. It can accurately recover the three-dimensional information in the field of view through the image information provided...

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): G06T7/33G06T7/11G06T7/66
CPCG06T7/11G06T7/344G06T7/66G06T2207/20104G06T2207/10012
Inventor 高立宁张俊青梁小伟章菲菲
Owner 北京理工雷科电子信息技术有限公司
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