Date of Publication :30th March 2018
Abstract: A Novel Image Contour technique to track and count the moving vehicles from the video streams of traffic scenes recorded by stationary cameras is proposed in this research work. The moving vehicles are first extracted from the traffic scene by applying the Adaptive Background Subtraction technique. After the background subtraction, using threshold and median filters, isolated image blobs are identified as individual vehicles. Once the blobs are identified, counting and classification of vehicles in a selected region are carried out. The preliminary results show that the developed system can efficiently and reliably track vehicles when the unobstructed view of the traffic scene can be obtained. For optimal camera calibration, accuracy is better than 80% in counting vehicles was observed. The present system performs better with video data in which the vehicles are moving away from the camera compared to the video data in which the vehicles are moving towards the camera. The results obtained through the developed system show that with further improvements the proposed technique can be used in real-time to count and classify the vehicles on busy traffic routes
Reference :
-
- P. Kumar, H. Weimin, I. U. Gu and Q. Tian, (2004) “Statistical modeling of complex backgrounds for foreground object detection”, IEEE Transaction on Image Processing, 43-53.
- Boyoon Jung and Gaurav S. Sukhatme, (2004) “A Generalized Region-based Approach for Multitarget Tracking in Outdoor Environments”, IEEE International Conference on Robotics and Automation, 2189-2195.
- D. Serby, E. K. Meier and L. V. Gool, (2004) "Probabilistic Object Tracking Using Multiple Features", IEEE Pattern Recognition Intelligent Transportation Systems, 43-53.
- Zhimin Fan, Jie Zhou, Dashan Gao and Zhiheng Li, (2002) “Contour Extraction And Tracking Of Moving Vehicles For Traffic Monitoring”, IEEE International Conference on Intelligent Transportation Systems, 84-87
- D. Magee, (2004) “Tracking multiple vehicles using foreground, background and motion models”. Image and Vision Computing, 22:143–155
- B. Maurin, O. Masoud, and N. P. Papanikolopoulos, (2005)“Tracking all traffic: computer vision algorithms for monitoring vehicles, individuals, and crowds”, Robotics & Automation Magazine, IEEE, 12(1):29–36.
- S. T. Birchfield, (1999) “Depth and Motion Discontinuities”, PhD thesis, Stanford University.
- N. K. Kanhere, S. J. Pundlik, and S. T. Birchfield, (2005) “Vehicle segmentation and tracking from a low-angle off-axis camera”, In IEEE Conference on Computer Vision and Pattern Recognition, San Diego, California.
- Dan Middleton, Deepak Gopalakrishna, and MalaRaman “Advances in traffic data collection and management” Texas Transportation Institute Cambridge Systematic, Inc. January, 2003.