Accession number:20090911933939
Title: Design a support vector machine-based intelligent system for vehicle driving safety warning
Authors:Lin, Che-Chung (1); Lin, Chi-Wei (1); Huang, Dau-Chen (1);
Chen, Yung-Hsin (2)
Author affiliation:(1) Vehicle Electronics Department, Intelligent Mobility Technology Division, Industrial Technology Research Institute, Hsinchu, Taiwan; (2) Department of Business
Administration, Asia University, Taichung, Taiwan Corresponding author:Chen, Y.-H.
Source title:IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC
Abbreviated source title:IEEE Conf Intell Transport Syst Proc ITSC Monograph title:IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC
Issue date:2008
Publication year:2008 Pages:938-943
Article number:4732562 Language:English
Document type:Conference article (CA)
Conference name:11th International IEEE Conference on Intelligent Transportation Systems, ITSC 2008
Conference date:December 10, 2008 - December 12, 2008 Conference location:Beijing, China
Conference code:75378
Publisher:Institute of Electrical and Electronics Engineers Inc., 445 Hoes Lane / P.O. Box 1331, Piscataway, NJ 08855-1331, United States
Abstract:This paper reports the advancement of a research
extension. The outcome is a device installed in a long-haul bus for daily operation. The incumbent system features the combination of Lane Departure Warning (LDW) function and Forward Collision Warning (FCW) function employing the Support Vector Machine (SVM) as the classifier. LDW recognizes the environment as in daytime or in nighttime by detecting a vanishing point and applies
the appropriate thresholds for daytime and nighttime to enhance the detecting rate. The algorithmic components of LDW function include image overlapping, median filter, edge-enhancement filter and Hough Transform, while the FCW function identifies vehicles with a feature-based approach and verifies the vehicle candidates by the appearance-based approach. In addition, we propose a new detecting scheme by motion vector (MV) estimation, where the detection doesn't rely on the whole image inside the region of
interest (ROI) but on the detection range of three different ranges to concurrently secure high detecting rate and low computing power.
Besides, as distance estimation is the crucial part of FCW function, we create an innovative camera calibration algorithm working with an adjustment mechanism to enhance the accuracy of the distance estimation. The combination of refined LDW and FCW functions has successfully implemented in ADI-BF561 600MHz dual core DSP- based embedded system. © 2008 IEEE.
Number of references:25
Main heading:Support vector machines
Controlled terms:Automobile parts and equipment - Edge detection - Estimation - Hough transforms - Image retrieval - Integrated circuits - Intelligent systems - Intelligent vehicle highway systems - Machine design - Vehicle locating systems
Uncontrolled terms:Adjustment mechanisms - Appearance-based - Camera calibrations - Computing power - Detection ranges -
Distance estimations - Driving safeties - DSP-based - Dual cores - Edge enhancements - Feature-based - Forward collision warnings - Lane departure warnings - Long hauls - Median filters - Motion vectors - Region of interests - System features - Vanishing points Classification code:723.4 Artificial Intelligence - 723.5 Computer Applications - 741 Light, Optics and Optical Devices - 723.2 Data Processing and Image Processing - 741.1 Light/Optics - 921
Mathematics - 921.3 Mathematical Transformations - 751.1 Acoustic Waves - 723 Computer Software, Data Handling and Applications - 406.1 Highway Systems - 432.4 Highway Traffic Control - 601 Mechanical Design - 406 Highway Engineering - 662.4 Automobile and Smaller Vehicle Components - 714.2 Semiconductor Devices and Integrated Circuits - 716 Telecommunication; Radar, Radio and Television - 663.2 Heavy Duty Motor Vehicle Components
DOI:10.1109/ITSC.2008.4732562 Database:Compendex
Compilation and indexing terms, Copyright 2009 Elsevier Inc.
