통계적 특징 기반 SVM을 이용한 야간 전방 차량 검출 기법
Night Time Leading Vehicle Detection Using Statistical Feature Based SVM
2
조회
0
다운로드
3
인용
0
참고문헌
키워드
초록
A driver assistance system is critical to improve a convenience and stability of vehicle driving. Several systems have been already commercialized such as adaptive cruise control system and forward collision warning system. Efficient vehicle detection is very important to improve such driver assistance systems. Most existing vehicle detection systems are based on a radar system, which measures distance between a host and leading (or oncoming) vehicles under various weather conditions. However, it requires high deployment cost and complexity overload when there are many vehicles. A camera based vehicle detection technique is also good alternative method because of low cost and simple implementation. In general, night time vehicle detection is more complicated than day time vehicle detection, because it is much more difficult to distinguish the vehicle’s features such as outline and color under the dim environment. This paper proposes a method to detect vehicles at night time using analysis of a captured color space with reduction of reflection and other light sources in images. Four colors spaces, namely RGB, YCbCr, normalized RGB and Ruta-RGB, are compared each other and evaluated. A suboptimal threshold value is determined by Otsu algorithm and applied to extract candidates of taillights of leading vehicles. Statistical features such as mean, variance, skewness, kurtosis, and entropy are extracted from the candidate regions and used as feature vector for SVM(Support Vector Machine) classifier. According to our simulation results, the proposed statistical feature based SVM provides relatively high performances of leading vehicle detection with various distances in variable nighttime environments.
Abstract
A driver assistance system is critical to improve a convenience and stability of vehicle driving. Several systems have been already commercialized such as adaptive cruise control system and forward collision warning system. Efficient vehicle detection is very important to improve such driver assistance systems. Most existing vehicle detection systems are based on a radar system, which measures distance between a host and leading (or oncoming) vehicles under various weather conditions. However, it requires high deployment cost and complexity overload when there are many vehicles. A camera based vehicle detection technique is also good alternative method because of low cost and simple implementation. In general, night time vehicle detection is more complicated than day time vehicle detection, because it is much more difficult to distinguish the vehicle’s features such as outline and color under the dim environment. This paper proposes a method to detect vehicles at night time using analysis of a captured color space with reduction of reflection and other light sources in images. Four colors spaces, namely RGB, YCbCr, normalized RGB and Ruta-RGB, are compared each other and evaluated. A suboptimal threshold value is determined by Otsu algorithm and applied to extract candidates of taillights of leading vehicles. Statistical features such as mean, variance, skewness, kurtosis, and entropy are extracted from the candidate regions and used as feature vector for SVM(Support Vector Machine) classifier. According to our simulation results, the proposed statistical feature based SVM provides relatively high performances of leading vehicle detection with various distances in variable nighttime environments.
참고문헌 (15)
- A. Haselhoff, "Radar-Vision Fusion with an Application toCar-Following using an Improved AdaBoostDetection Algorithm", Proceedings onInternational IEEE Conference on IntelligentTransportation Systems, pp.854~858 (2007)
- S. Sivaraman, "Active Learning based Robust Monocular Vehicle detection for On-road Safety Systems", Proceedings on Intelligent Vehicles Symposium, pp.399~404 (2009)
- D. Acunzo, "Context-Adaptive Approach for VehicleDetection Under Varying Lighting Conditions", Proceedings on International IEEE Conferenceon Intelligent Transportation Systems, pp.654~660 (2007)
- L. Andreonet, "Vehicle detection and localization in infra-red images", Proceedings on Intelligent Transportation Systems Conference, pp.141~146 (2002)
- P.F. Alcantarilla, "Night Time Vehicle Detection for Driving Assistance LightBeam Controller", Proceedings on Intelligent Vehicles Symposium, pp.291~296 (2008)
- R. O’Malley, "Rear-Lamp Vehicle Detection and Tracking in Low-Exposure Color Video for Night Conditions", IEEE Transaction on Intelligent Transportation System, 11(2), pp.453~462 (2010)
- T. Zhang, "Statistical behavior and consistency of classification methods based on convex risk minimization", Annals of Statistics, 32(1), pp.56~85 (2004)
- H. Drucker, "Support Vector Regression Machines", Advances in Neural Information Processing Systems, 9, pp.155~161 (1996)
- D. Meyer, "The support vector machine under test", Neurocomputing, 55(1), pp.169~186 (2003)
- C.P. Papageorgiou, "A general framework for object detection", Proceedings on International Conference on Computer Vision, pp.555~562 (1998)
- 김현구, "적응형 헤드 램프 컨트롤을 위한 야간 차량 인식", 대한임베디드공학회논문지, 6(1), pp.8~15 (2011), 대한임베디드공학회
- A. Ruta, "A New Approach for In-Vehicle Camera Traffic Sign Detection and Recognition", Proceedings on IAPR Conference on Machine Vision Applications (2009)
- N. Otsu, "A Tlreshold Selection Method from Gray-Level Histograms", IEEE Transactions on Systems, Man and Cybernetics, 9(1), pp.61~66 (1979)
- R. Charette, "Real Time Visual Traffic Lights Recognition Based on Spot Light Detection and Adaptive Traffic Lights Templates", Proceedings on Intelligent Vehicles Symposium, pp.358~363 (2009)
- R. Charette, "Traffic Light Recognition using Image Processing Compared to Learning Processes", Proceedings on IEEE, 2009, 333~338