Actions

Download Analytics Citations

Export to: EndNote  |  Zotero  |  Mendeley

Collections

This file is not currently in any collections.

Real-time traversable surface detection by colour space fusion and temporal analysis - Evaluation Dataset Open Access

We present a real-time approach for traversable surface detection using a low-cost monocular camera mounted on an autonomous vehicle. The proposed methodology extracts colour and texture information from various channels of the HSL, YCbCr and L*A*B colour-spaces by temporal analysis in order to create a “traversability map”. On this map lighting and water artefacts are eliminated including shadows, reflections and water prints. Additionally, camera vibration is compensated by temporal filtering leading to robust path edge detection in blurry images. The performance of this approach is extensively evaluated over varying terrain and environmental conditions and the effect of colour-space fusion on the system’s precision is analysed. The results show a mean accuracy of 97% over this comprehensive test set.

Descriptions

Resource type

Dataset

Contributors

Contact person: Breckon, Toby P. ¹
Creator: Breckon, Toby P. ¹
Creator: Katramados, Ioannis ²

¹ Durham University, UK
² Cranfield University, UK

Funder

Engineering and Physical Sciences Research Council

Research methods

Computer vision and image processing applied to robotic vision and autonomous vehicle guidance.

Other description

Data set from research paper: Real-Time Traversable Surface Detection by Colour Space Fusion and Temporal Analysis (I. Katramados, S. Crumpler, T.P. Breckon), In Proc. International Conference on Computer Vision Systems, Springer, Volume 5815, pp. 265-274, 2009. Previously released (2009-2015) as zip file download from personal web page of the authors (Katramados / Breckon).

Keyword

computer vision
image processing
image analysis
robotics
path detection
robot guidance
traversable pathway
terrain classification
road following
robotic navigation

Subject

Engineering
Computer Science

Location

United Kingdom

Language

English

Cited in

doi:10.1007/978-3-642-04667-4_27

Identifier

doi:10.15128/jd472w44j
ark:/32150/jd472w44j

Rights

All rights reserved All rights reserved

Publisher

Durham University

Date Created

2009

File Details

Depositor

T. Breckon

Date Uploaded

3 December 2015, 16:12:39

Date Modified

17 May 2016, 14:05:56

Audit Status

Audits have not yet been run on this file.

Characterization

File format: zip (ZIP Format)

Mime type: application/zip

File size: 238498858

Last modified: 2015:12:03 16:56:12+00:00

Filename: pathwaydetection09.zip

Original checksum: 33952d38ceb03fe9f4c76f75ae774983