Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/67750
Title: Negative obstacle detection using stereo vision
Authors: You, Zhiyong
Keywords: DRNTU::Engineering::Electrical and electronic engineering
Issue Date: 2016
Abstract: Concepts of Binocular Stereo Vision come from our human vision system. When human eyes looking at certain objects, the reflection of light from the objects received by the eyes form images at the left and right retina. The images formed would be slightly different, there would be a shift in the horizontal axis known as disparity. Our brain would then compute the depth of the objects with the disparity, eventually, 3D scenes are constructed. Computer Binocular Vision make use of this theory, use two cameras to capture images from same scene, obtained the images with disparity. Then, according to the concept of Binocular Stereo Vision, a 3D space can be reconstructed. [1] Unmanned guided vehicles also known as intelligence vehicles are vehicles which can run autonomously and continuously on road. They are able to detect obstacles and avoid them accordingly without human intervention. In order to achieve such ability, they need to have perception on their surroundings. Computer Binocular Stereo Vision is one of the ways to help the machines to perceive their surroundings and make appropriate decisions upon it. A stereo vision system consist of following processes camera calibration, image rectification, stereo matching and triangulation. In this article, we would discuss the background and significant this the binocular stereo vision system, then the different steps of the systems would be further discuss and elaborate. Finally, we would discuss on the refinements that help to improve the systems.
URI: http://hdl.handle.net/10356/67750
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
FYP_Final_Report.docx.pdf
  Restricted Access
1.32 MBAdobe PDFView/Open

Page view(s)

120
Updated on Jun 21, 2021

Download(s)

10
Updated on Jun 21, 2021

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.