FUSION OF WAVELET TRANSFORM AND COLOR INFORMATION FEATURES FOR AUTOMATIC VEHICLE REIDENTIFICATION IN INTELLIGENT TRANSPORTATION SYSTEMS
This paper presents a fusion-based vehicle reidentification system algorithm that uses 4 different features to achieve high accuracy: 1) the wavelet transform of the inductive signature vector acquired from loop detectors; 2) vehicle velocity; 3) traversal time; and 4) color information based on images acquired from video cameras. A nearest neighbor approach classifies the features, and linear feature fusion is shown to improve performance. With the fusion of 4 features, more than a 92% accuracy was obtained on real data collected from a parkway in California. Also, it was found that the wavelet transform improves performance and reduces the dimension of the feature vector when compared to the raw vehicle signatures.
-
Availability:
- Find a library where document is available. Order URL: http://worldcat.org/isbn/0780384849
-
Corporate Authors:
Institute of Electrical and Electronics Engineers (IEEE)
3 Park Avenue, 17th Floor
New York, NY United States 10016-5997 -
Authors:
- Arr, G A
- Sun, Chao
- Ramachandran, R R
-
Conference:
- 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing
- Location: Montreal, Canada
- Date: 2004-5-17 to 2004-5-19
- Publication Date: 2004
Language
- English
Media Info
- Features: References;
- Pagination: p. 285-288
-
Serial:
- Volume: 5
Subject/Index Terms
- TRT Terms: Algorithms; Automated highways; Character recognition; Image analysis; Image processing; Integral transforms; Intelligent transportation systems; Tracking systems; Traffic data; Traffic density; Traffic engineering; Travel time; Wavelets
- Uncontrolled Terms: Nearest neighbor approach; Vehicle tracking
- Subject Areas: Highways; Operations and Traffic Management; I73: Traffic Control;
Filing Info
- Accession Number: 00979121
- Record Type: Publication
- ISBN: 0780384849
- Files: TRIS
- Created Date: Sep 20 2004 12:00AM