Files in this item



application/pdfECE499-Su2014-qian.pdf (1MB)Restricted to U of Illinois
(no description provided)PDF


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
Subject(s):machine vision
track inspection
camera testing
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.
Issue Date:2014-08
Date Available in IDEALS:2014-12-19

This item appears in the following Collection(s)

Item Statistics