A High Efficient System for Traffic Mean Speed Estimation from MPEG Video

In this paper, we present a vision-based traffic measurement system, allowing automatic traffic flow segmentation, camera calibration and traffic information estimation. The system quickly estimates mean vehicle speed directly from MPEG Motion Vectors. Although extensive work has been done in extracting and using motion information from MPEG video data in compressed domain, to our best knowledge, only few works have been dedicated to the use of MPEG motion vector for traffic analysis. The proposed system is stable and handles camera vibrations and illumination changes. The paper describes the main principles of our system together with qualitative and quantitative representative results.

[1]  A.B. Chan,et al.  Classification and retrieval of traffic video using auto-regressive stochastic processes , 2005, IEEE Proceedings. Intelligent Vehicles Symposium, 2005..

[2]  F. Porikli,et al.  Traffic congestion estimation using HMM models without vehicle tracking , 2004, IEEE Intelligent Vehicles Symposium, 2004.

[3]  Young Cho,et al.  Estimating Velocity Fields on a Freeway From Low-Resolution Videos , 2006, IEEE Transactions on Intelligent Transportation Systems.

[4]  N. H. C. Yung,et al.  A Novel Algorithm for Estimating Vehicle Speed from Two Consecutive Images , 2007, 2007 IEEE Workshop on Applications of Computer Vision (WACV '07).

[5]  Shamik Sural,et al.  Object Tracking Using Background Subtraction and Motion Estimation in MPEG Videos , 2006, ACCV.

[6]  Fatih Porikli.  Real-time video object segmentation for MPEG-encoded video sequences , 2004, IS&T/SPIE Electronic Imaging.

[7]  Daniel J. Dailey,et al.  Dynamic camera calibration of roadside traffic management cameras for vehicle speed estimation , 2003, IEEE Trans. Intell. Transp. Syst..

[8]  Li Bai,et al.  Computer vision techniques for traffic flow computation , 2004, Pattern Analysis and Applications.

[9]  Zehang Sun,et al.  On-road vehicle detection: a review , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Daniel J. Dailey,et al.  Dynamic camera calibration of roadside traffic management cameras , 2002, Proceedings. The IEEE 5th International Conference on Intelligent Transportation Systems.

[11]  Wang Guoyou,et al.  Vehicle flow detection statistic algorithm based on optical flow , 2005, Proceedings of the Fifth IEEE International Symposium on Signal Processing and Information Technology, 2005..

[12]  Sei-Wang Chen,et al.  Vision-based traffic measurement system , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[13]  Qi Tian,et al.  Robust moving video object segmentation in the MPEG compressed domain , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[14]  Serge P. Hoogendoorn,et al.  State-of-the-art of vehicular traffic flow modelling , 2001 .

[15]  Qi Tian,et al.  Highway traffic information extraction from Skycam MPEG video , 2002, Proceedings. The IEEE 5th International Conference on Intelligent Transportation Systems.

[16]  A. Oostveen,et al.  A new incident detection scheme developed in the Netherlands , 2005, Proceedings. 2005 IEEE Intelligent Transportation Systems, 2005..

[17]  Qi Tian,et al.  An algorithm to estimate mean vehicle speed from MPEG Skycam video , 2007, Multimedia Tools and Applications.

[18]  Donald J Dailey,et al.  CCTV Technical Report--Phase 3 , 2006 .

[19]  Daniel J. Dailey,et al.  Algorithms for estimating mean vehicle speed using uncalibrated traffic management cameras , 2003 .