다중-클래스 SVM 기반 야간 차량 검출
Night-time Vehicle Detection Based On Multi-class SVM
2
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Vision based night-time vehicle detection has been an emerging research field in various advanced driver assistance systems(ADAS) and automotive vehicle as well as automatic head-lamp control. In this paper, we propose night-time vehicle detection method based on multi-class support vector machine(SVM) that consists of thresholding, labeling, feature extraction, and multi-class SVM. Vehicle light candidate blobs are extracted by local mean based thresholding following by labeling process. Seven geometric and stochastic features are extracted from each candidate through the feature extraction step. Each candidate blob is classified into vehicle light or not by multi-class SVM. Four different multi-class SVM including one-against-all(OAA), one-against-one(OAO), top-down tree structured and bottom-up tree structured SVM classifiers are implemented and evaluated in terms of vehicle detection performances. Through the simulations tested on road video sequences, we prove that top-down tree structured and bottom-up tree structured SVM have relatively better performances than the others.
Abstract
Vision based night-time vehicle detection has been an emerging research field in various advanced driver assistance systems(ADAS) and automotive vehicle as well as automatic head-lamp control. In this paper, we propose night-time vehicle detection method based on multi-class support vector machine(SVM) that consists of thresholding, labeling, feature extraction, and multi-class SVM. Vehicle light candidate blobs are extracted by local mean based thresholding following by labeling process. Seven geometric and stochastic features are extracted from each candidate through the feature extraction step. Each candidate blob is classified into vehicle light or not by multi-class SVM. Four different multi-class SVM including one-against-all(OAA), one-against-one(OAO), top-down tree structured and bottom-up tree structured SVM classifiers are implemented and evaluated in terms of vehicle detection performances. Through the simulations tested on road video sequences, we prove that top-down tree structured and bottom-up tree structured SVM have relatively better performances than the others.
참고문헌 (14)
- J. Rebut, "A monocular Vision Based Advanced Lighting Automation System for Driving Assistance", Proceedings of IEEE International Symposium on Industrial Electronics, pp.311~316 (2009)
- "Mobileye, Adaptive Headlight Control"[URL]
- 정정은, "통계적 특징 기반 SVM을 이용한 야간 전방 차량 검출 기법", 대한임베디드공학회논문지, 7(4), pp.163~172 (2012), 대한임베디드공학회
- H. Lee, "Nighttime Vehicle Detection Based on SVM with Geometric Features", Proceedings of IEMEK Fall Conference, pp.88~91 (2014)
- P. F. Alcantarilla, "Night Time Vehicle Detection for Driving Assistance Light Beam Controller", Proceedings of IEEE Intelligent Vehicles Symposium, pp.291~296 (2008)
- P. F. Alcantarilla, "Automatic LightBeam Controller for Driver Assistance", Machine Vision and Application, 22(5), pp.819~835 (2011)
- V. B. Sutar1, "Night Time Vehicle Detection and Classification Using Support Vector Machine", IOSR Journal of VLSI and Signal Processing, 1(4), pp.1~9 (2012)
- A. López, "Nighttime vehicle detection for intelligent headlight control", Proceedings of the 10th International Conference on Advanced Concepts for Intelligent Vision Systems (2008)
- T. Schamm, "On-Road Vehicle Detection during Dusk and at Night", Proceedings of IEEE Intelligent Vehicles Symposium, pp.418~423 (2010)
- H. Byun, "Applications of Support Vector Machines for Pattern Recognition : A Survey", Lecture Notes in Computer Science, 2388, pp.213~236 (2002)
- C. -W. Hsu, "A Comparison of Methods for Multiclass Support Vector Machines", IEEE Transactions on Neural Networks, 13(2), pp.415~425 (2001)
- B. Zhao, "Support vector machines and its application in handwritten numerical recognition", Proceedings of 15th International Conference on Pattern Recognition, 2, pp.720~723 (2000)
- J. Platt, "Large margin DAGs for multiclass classification", pp.547~553 (2000), Advances in Neural Information Processing Systems
- H. Lee, "Efficient thresholding for Night-time Vehicle Candidate Detection", Proceedings of International Conference on Green and Human Information Technology, pp.118~121 (2015)