DOI QR코드

DOI QR Code

사각지역경보시스템을 위한 실시간 측후방 차량검출 알고리즘

Real-Time Side-Rear Vehicle Detection Algorithm for Blind Spot Warning Systems

  • 강현우 (한국전자통신연구원 스마트비전연구실) ;
  • 백장운 (한국전자통신연구원 스마트비전연구실) ;
  • 한병길 (한국전자통신연구원 스마트비전연구실) ;
  • 정윤수 (한국전자통신연구원 스마트비전연구실)
  • 투고 : 2017.01.03
  • 심사 : 2017.05.16
  • 발행 : 2017.07.15

초록

본 논문에서는 주행 중 사각지역내의 차량을 빠르고 정확하게 실시간으로 검출하는 측후방 차량 검출 알고리즘을 제안한다. 제안 알고리즘은 실시간 처리를 위해 MCT(Modified Census Transformation) 특징벡터를 기반으로 에이다부스트 학습을 통해 생성되는 캐스케이드 분류기를 사용한다. MCT 분류기는 검출윈도우가 작을수록 처리속도가 빠르고, 검출윈도우가 클수록 정확도가 증가한다. 제안 알고리즘은 이러한 특징을 이용하여 검출윈도우가 작은 분류기로 차량후보를 빠르게 생성한 후 보다 큰 사이즈의 검출윈도우를 가지는 분류기로 생성된 차량후보에 대해 정확하게 차량인지 검증한다. 또한, 차량분류기와 바퀴분류기를 동시에 사용하여 사각지역내로 진입하는 차량과 사각지역내의 인접차량을 효과적으로 검출한다.

This paper proposes a real-time side-rear vehicle detection algorithm that detects vehicles quickly and accurately in blind spot areas when driving. The proposed algorithm uses a cascade classifier created by AdaBoost Learning using the MCT (modified census transformation) feature vector. Using this classifier, the smaller the detection window, the faster the processing speed of the MCT classifier, and the larger the detection window, the greater the accuracy of the MCT classifier. By considering these characteristics, the proposed algorithm uses two classifiers with different detection window sizes. The first classifier quickly generates candidates with a small detection window. The second classifier accurately verifies the generated candidates with a large detection window. Furthermore, the vehicle classifier and the wheel classifier are simultaneously used to effectively detect a vehicle entering the blind spot area, along with an adjacent vehicle in the blind spot area.

키워드

과제정보

연구 과제번호 : 상황인지 스마트카 퓨전플랫폼 개발 및 지역 부품업체 지원사업

연구 과제 주관 기관 : 한국전자통신연구원

참고문헌

  1. National Transportation Safety Board, Special Investigation Report - Highway Vehicle - and Infrastructure- based Technology For the Prevention of Rear-end Collisions. NTSB Number SIR-01/01, May 2001.
  2. ISO 17387:2008 Intelligent transport systems - Lane change decision aid systems (LCDAS) - Performance requirements and test procedures.
  3. SAE J2803-2010 Blind Spot Monitoring System (BSMS): Operating Characteristics and User Interface.
  4. W. Chang and K. Hsu, "Vision-Based Side Vehicle Detection from a Moving Vehicle," Proc. of International Conference on System Science and Engineering 2010, Jul. 2010.
  5. J. Alonso, E. Vidal, A. Rotter, and M. Muhlenberg, "Lane-Change Decision Aid System Based on Motion- Driven Vehicle Tracking," IEEE Transactions on Vehicular Technology, Feb. 2008.
  6. P. Viola and M. Jones, "Rapid Object Detection using a Boosted Cascade of Simple Features," Proc. of Conference on Computer Vision and Pattern Recognition 2001, Vol. 1, pp. 511-518, Dec. 2001.
  7. N. Dalal and B. Triggs, "Histograms of Oriented Gradients for Human Detection," Proc. of Conference on Computer Vision and Pattern Recognition 2005, Vol. 1, pp. 886-893, 2005.
  8. Y. Lee, J. Ko, J. Suk, T. Roh, and J. Shim, "Pedestrian Recognition using Adaboost Algorithm based on Cascade Method by Curvature and HOG," Journal of KIISE: Computing Practices and Letters, Vol. 16, No. 6, pp. 654-662. Jun. 2010. (in Korean)
  9. M. Choi, J. Lee, T. Roh, and J. Shim, "Vehicle Detection Scheme Based on a Boosting Classifier with Histogram of Oriented Gradient (HOG) Features and Image Segmentation," Journal of KIISE: Computing Practices and Letters, Vol. 16, No. 10, pp. 955-961, Oct. 2010. (in Korean)
  10. S. Liao, X. Zhu, Z. Lei, L. Zhang, and S. Z. Li, "Learning Multi-scale Block Local Binary Patterns for Face Recognition," Proc. of International Conference on Biometrics 2007, pp. 828-837, Aug. 2007.
  11. J. Baek, E. Lee, M. Park, and D. Seo, "Mono- Camera Based Side Vehicle Detection for Blind Spot Detection Systems," Proc. of International Conference on Ubiquitous and Future Networks 2015, pp. 147-149, Jul. 2015.
  12. J. Redmon, S. Divvals, R. Girshick, and A. Parhadi, "You Only Look Once: Unified, Real-Time Object Detection," Proc. of International Conference on Computer Vision and Pattern Recognition 2016, pp. 779-788, Jun. 2016.
  13. W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C. Fu, and A. Berg, "SSD: Single Shot Multi- Box Detector," Proc. of the European Conference on Computer Vision 2016, Oct. 2016.
  14. S. Ren, K. He, R. Girshick, and J. Sun, "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks," IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol. 39, pp. 1137-1149, 2016.
  15. C. Kublbeck and A. Ernst, "Face detection and tracking in video sequence using the modified census transformation," Image and Vision Computing, Vol. 24, pp. 564-572, 2006. https://doi.org/10.1016/j.imavis.2005.08.005
  16. D. Blome, J. Beveridge, B. Draper, and Y. Lui, "Visual Object Tracking using Adaptive Correlation Filters," Proc. of Computer Vision and Pattern Recognition 2010, pp. 2544-2550, Jun. 2010.