Method for detecting target protruding from plane based on double viewing fields without calibration

A technology for calibrating plane and target detection, which is applied in image data processing, instruments, computing and other directions, and can solve the problems that it is difficult to meet the requirements of accuracy and real-time performance of 3D vision system.

Inactive Publication Date: 2012-05-09
XIAN UNIV OF TECH
View PDF4 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a non-calibration plane protruding target detection method based on dual-field of view, which solves the problem that it is difficult to meet the accuracy and real-time requirements of the three-dimensional vision system for target detection in the prior art

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 target protruding from plane based on double viewing fields without calibration
  • Method for detecting target protruding from plane based on double viewing fields without calibration
  • Method for detecting target protruding from plane based on double viewing fields without calibration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0072] The present invention will be described in detail below with reference to the drawings and specific embodiments.

[0073] The present invention proposes a method for detecting non-calibrated planar protrusion targets without camera calibration based on dual fields of view. By homography transformation between two images, the pixels on the same plane are matched, and the pixels on different surfaces are A certain aberration is generated, and the planar protrusion target is determined according to the aberration. The method is implemented according to the following steps:

[0074] Step 1. Setting of scene marker

[0075] Before the image is collected, four simple markers 3 are set on the plane 1 (such as the ground, desktop) of the target to be detected. The markers 3 to be set are thin white paper strips with different brightness from the plane. The marker 3 is set in the largest possible range of the effective field of view of the shooting scene, such as figure 1 a. figure...

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 a target protruding from a plane based on double viewing fields without calibration. The method is carried out in the following steps: setting a scene marker; collecting images; detecting and working out four corresponding point pairs of the marker; solving a homography matrix according to the four corresponding marking point pairs; carrying out homography transformation for a right view; adjusting illumination brightness, and then carrying out registration and superposition; and judging the object protruding from the plane, thus obtaining the final judgment result. By using the method provided by the invention, the object protruding form the plane in a three-dimensional space can be obtained from a binocular viewing field, or two viewing fields with transformed attitudes in a monocular camera, without calibrating the camera; and the detection method has a reasonable operational method, high computing speed, and can meet the requirement of a three-dimensional vision system on accuracy and instantaneity of target detection.

Description

Technical field [0001] The invention belongs to the technical field of three-dimensional target detection, and specifically relates to a method for detecting an uncalibrated planar protrusion target based on a dual field of view. Background technique [0002] Three-dimensional target detection is an important link in the detection of obstacles for driverless cars, and target positioning and recognition in robot vision. For three-dimensional stereo vision, due to the large amount of processed data, it is difficult to accurately and quickly detect Three-dimensional target. [0003] For autonomous vehicles or robots, the detection of three-dimensional obstacles protruding from the ground in the environment is generally achieved by reducing the resolution and performing three-dimensional reconstruction. The purpose of reducing the resolution is to reduce the amount of data and increase the calculation speed. For more complex scenes, the computational time cost of this type of algorith...

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): G06T7/00G06T7/70
Inventor 朱虹王栋程松王斌康凯俞帅男
Owner XIAN 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