University of Illinois Urbana-Champaign

Remote Visual Inspection Of The Track And Right-of-way Project: Verification Hemispherical Camera Output For Computer Vision Processing

Qian, Yongbo

This item is only available for download by members of the University of Illinois community. Students, faculty, and staff at the U of I may log in with your NetID and password to view the item. If you are trying to access an Illinois-restricted dissertation or thesis, you can request a copy through your library's Inter-Library Loan office or purchase a copy directly from ProQuest.

Permalink

https://hdl.handle.net/2142/72641

Description

Title
Remote Visual Inspection Of The Track And Right-of-way Project: Verification Hemispherical Camera Output For Computer Vision Processing
Author(s)
Qian, Yongbo
Contributor(s)
Ahuja, Narendra
Issue Date
2014-08
Keyword(s)
  • machine vision
  • track inspection
  • camera testing
  • resolution
  • computer vision
Abstract
According to the Federal Railroad Administration (FRA) regulations, periodic track inspections are required in order to guarantee the safe and efficient operation of the railroad track. In modern transportation, increased usage on the same track often requires more frequent inspection and maintenance but with less time for completion. The conventional method of walking the track and conducting visual inspection by maintenance-of-way inspectors, is time consuming and subjective. Developing and implementing new inspection technologies to deliver instant, accurate and automated monitoring of the track conditions is highly desired. This research project aims to develop a video acquisition system for automated track inspection. It involves the use of a Hemispherical Camera design for image acquisition of the track and the entire area surrounding. The Hemispherical Camera is comprised of multiple camera sensors to provide the large field of view entire area under inspection. It will be initially used for visual inspections at remote locations and future automated visual inspection using computer vision techniques. This thesis will show the work accomplished towards the goal of developing a custom designed Hemispherical Camera for track inspection consists of three parts. The first part is the creation of a motor control module for the Video Track Cart (VTC), which will assist in testing the Hemispherical Camera placement and orientation for obtaining a proper view of the components in different speed settings. The second part, is to investigate the quantitative relationship between the application criteria and specific camera parameters, this is achieved by deriving and updating camera equations and verifying them on the railway under different conditions. The last part is to analyze the required camera capture properties for selecting suitable camera sensors for the new Hemispherical Camera design and to also test the resolution required and blur limits for identifying the railway components. This work will ensure that the new Hemispherical Camera will produce track images suitable for computer vision component inspection.
Type of Resource
text
Language
en
Permalink
http://hdl.handle.net/2142/72641

Owning Collections

Senior Theses - Electrical and Computer Engineering PRIMARY
The best of ECE undergraduate research