Enhanced and effective parallel optical flow method for vehicle detection and tracking

In the area of traffic flow monitoring, planning and controlling, a video based traffic detection and tracking plays an effective and significant role where effective traffic management and safety is the main concern. The goal of the project is to recognize moving vehicles and track them throughout their life spans. In this paper, we discuss and address the issue of detecting vehicle/traffic data from video frames with increased real time video processing. Although various researches have been done in this area and many methods have been implemented, still this area has room for improvements. With a view to do improvements, it is proposed to develop an unique algorithm for vehicle data recognition and tracking using Parallel Optical Flow method based on Lucas-Kanade algorithm. Here, Motion detection is determined by temporal differencing and template matching is done only on the locations as guided by the motion detection stage to provide a robust target-tracking method. The foreground optical flow detector detects the object and a binary computation is done to define rectangular regions around every detected object. To detect the moving object correctly and to remove the noise some morphological operations have been applied. Then the final counting is done by tracking the detected objects and their regions in a real time sequence. Results show no false object recognition in some tested frames, perfect tracking for the detected images and 98% tracked rate on the real video with an enhanced real time video processing.

[1]  Ravi Kumar Kota,et al.  Analysis Of Classification And Tracking In Vehicles Using Shape Based Features , 2013 .

[2]  Fei-Yue Wang,et al.  Visual vehicle tracking based on conditional random fields , 2014, 17th International IEEE Conference on Intelligent Transportation Systems (ITSC).

[3]  Keiichi Abe,et al.  Topological structural analysis of digitized binary images by border following , 1985, Comput. Vis. Graph. Image Process..

[4]  Jiann-Shiou Yang,et al.  An optical flow and hough transform based approach to a lane departure warning system , 2014, 11th IEEE International Conference on Control & Automation (ICCA).

[5]  Thomas Bräunl,et al.  A Reliability Point and Kalman Filter-based Vehicle Tracking Technique , 2012 .

[6]  Mohammad Farukh Hashmi,et al.  Analysis and monitoring of a high density traffic flow at T-intersection using statistical computer vision based approach , 2012, 2012 12th International Conference on Intelligent Systems Design and Applications (ISDA).

[7]  Hairong Qi,et al.  Real Time Multi-vehicle Tracking and Counting at Intersections from a Fisheye Camera , 2015, 2015 IEEE Winter Conference on Applications of Computer Vision.

[8]  Suvarna Nandyal,et al.  VEHICLE DETECTION AND TRAFFIC ASSESSMENT USING IMAGES , 2013 .

[9]  Larry S. Davis,et al.  A Robust Background Subtraction and Shadow Detection , 1999 .

[10]  Xiaogang Wang,et al.  Counting Vehicles from Semantic Regions , 2013, IEEE Transactions on Intelligent Transportation Systems.

[11]  Bodong Liang,et al.  Real-time moving vehicle detection, tracking, and counting system implemented with OpenCV , 2014, 2014 4th IEEE International Conference on Information Science and Technology.

[12]  M. Kalaiselvi Geetha,et al.  Traffic density estimation, vehicle classification and stopped vehicle detection for traffic surveillance system using predefined traffic videos , 2013 .

[13]  Sharath Pankanti,et al.  Large-Scale Vehicle Detection, Indexing, and Search in Urban Surveillance Videos , 2012, IEEE Transactions on Multimedia.

[14]  Jiann-Der Lee,et al.  Close range vehicle detection and tracking by vehicle lights , 2014, 2014 11th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS).

[15]  Sei-Wang Chen,et al.  Vehicle classification and counting system , 2014, 2014 International Conference on Audio, Language and Image Processing.

[16]  Shu-Chung Yi,et al.  Feature-Based Vehicle Flow Analysis and Measurement for a Real-Time Traffic Surveillance System , 2012, J. Inf. Hiding Multim. Signal Process..

[17]  S. M. Mahbubur Rahman,et al.  Detection and Classification of Vehicles From Video Using Multiple Time-Spatial Images , 2012, IEEE Transactions on Intelligent Transportation Systems.

[18]  Jacob Scharcanski,et al.  Tracking and counting vehicles in traffic video sequences using particle filtering , 2013, 2013 IEEE International Instrumentation and Measurement Technology Conference (I2MTC).

[19]  Chieh-Ling Huang,et al.  A Moving Object Detection Algorithm for Vehicle Localization , 2012, 2012 Sixth International Conference on Genetic and Evolutionary Computing.

[20]  Li-Chen Fu,et al.  Integrating Appearance and Edge Features for Sedan Vehicle Detection in the Blind-Spot Area , 2012, IEEE Transactions on Intelligent Transportation Systems.

[21]  Jacob Roll,et al.  Detecting and positioning overtaking vehicles using 1D optical flow , 2014, 2014 IEEE Intelligent Vehicles Symposium Proceedings.

[22]  Suet-Peng Yong,et al.  Image processing based vehicle detection and tracking method , 2014, 2014 International Conference on Computer and Information Sciences (ICCOINS).

[23]  Mohan M. Trivedi,et al.  Real-Time Video-Based Traffic Measurement and Visualization System for Energy/Emissions , 2012, IEEE Transactions on Intelligent Transportation Systems.