Browse > Article

Abnormal Traffic Behavior Detection by User-Define Trajectory  

Yoo, Haan-Ju (Seoul National University)
Choi, Jin-Young (Seoul National University)
Publication Information
Abstract
This paper present a method for abnormal traffic behavior, or trajectory, detection in static traffic surveillance camera with user-defined trajectories. The method computes the abnormality of moving object with a trajectory of the object and user-defined trajectories. Because of using user-define based information, the presented method have more accurate and faster performance than models need a learning about normal behaviors. The method also have adaptation process of assigned rule, so it can handle scene variation for more robust performance. The experimental results show that our method can detect abnormal traffic behaviors in various situation.
Keywords
traffic surveillance; abnormal behavior detection;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Ivanov.Y and Bobick.A "Recognition of multi-agent interaction in video surveillance", The Proc. of the Seventh IEEE International Conf. on Computer Vision, pp. 169-176, Kerkyra, Greece, September 1999.
2 Sultani.W, and Jin Young.C, "Abnormal traffic detection using intelligent driver model", The Proc. of the 2010 20th International Conf. on Pattern Recognition, pp. 324-327, Istanbul, Turkey, August 2010.
3 Saleemi.I, Hartung.L, and Shah.M, "Scene Understanding by Statistical Modeling of Motion Patterns", The Proc. of the 2010 20th International Conf. on Pattern Recognition, pp. 2069-2076, San Francisco, CA, USA, June 2010.
4 Basharat.A, Gritai.A, and Shah.M, "Learning object motion patterns for anomaly detection and improved object detection", The Proc. of the 2010 20th International Conf. on Pattern Recognition, pp. 1-8, San Francisco, CA, USA, June 2010.
5 최정환, 백영민, 나진희, 최진영. "감시 시스템을 위한 효과적인 움직이는 물체 탐지 알고리즘", 2007 CICS 정보 및 제어 학술대회 논문집, pp. 457-458, 제천, 대한민국, 2007 11월.
6 변문섭 외, "탐지 갈라짐과 물체 겹침 상황에 강인한 실시간 다개체 추적", 대한전자공학회 추계종합학술대회 논문집, 367-368쪽, 서울, 대한민국, 2010년 11월.