An innovative vehicle detection approach based on background subtraction and morphological binary operations methods

This paper proposes a new method of detecting moving vehicles in traffic videos using the background subtraction method, morphological binary operations, and new detection zone technique. Firstly, this method extracts a background image from the video frames using the mode statistical method, wherein the background will be subtracted from subsequent frames to distinguish the foreground objects by using the background subtraction method. Secondly, the morphological binary dilation and erosion operations are used to refine the boundaries and the regions of the detected moving vehicles (foregrounds), and unwanted small objects will be removed from the background respectively. Finally, we adopt the concept of a switch electric circuit design SPST (Single-Pole Single-Throw) as a new method to detect and count the moving vehicles. Performance evaluation of the experimental results is encouraging in that it shows that the proposed detection method has an average precision of more than 0.92, an average recall of more than 0.97, an average f-measure of more than 0.94 and average accuracy of more than 0.99.

[1]  Hani S. Mahmassani,et al.  Evaluation of Incident Detection Methodologies , 1999 .

[2]  Yoichiro Iwasaki,et al.  Real-time Vehicle Detection Using Information of Shadows Underneath Vehicles , 2007 .

[3]  Chung-Lin Huang,et al.  A vision-based vehicle identification system , 2004, ICPR 2004.

[4]  Weihua Wang Reach on Sobel Operator for Vehicle Recognition , 2009, 2009 International Joint Conference on Artificial Intelligence.

[5]  Jitendra Malik,et al.  Robust Multiple Car Tracking with Occlusion Reasoning , 1994, ECCV.

[6]  S. T. Birchfield,et al.  Vision-based detection, tracking and classification of vehicles using stable features with automatic camera calibration , 2008 .

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

[8]  Jun-Wei Hsieh,et al.  Automatic traffic surveillance system for vehicle tracking and classification , 2006, IEEE Transactions on Intelligent Transportation Systems.

[9]  Tony Lindeberg Kth Scale-space: A framework for handling image structures at multiple scales , 1996 .

[10]  Mark E Hallenbeck,et al.  Extracting Roadway Background Image , 2006 .

[11]  King Hann LIM,et al.  Lane-Vehicle Detection and Tracking , .

[12]  Wei Zhang,et al.  Multilevel Framework to Detect and Handle Vehicle Occlusion , 2008, IEEE Transactions on Intelligent Transportation Systems.

[13]  Bing Han,et al.  Motion-segmentation-based change detection , 2007, SPIE Defense + Commercial Sensing.

[14]  Michalis E. Zervakis,et al.  A survey of video processing techniques for traffic applications , 2003, Image Vis. Comput..

[15]  Chris T. Kiranoudis,et al.  A background subtraction algorithm for detecting and tracking vehicles , 2011, Expert Syst. Appl..

[16]  Bing-Fei Wu,et al.  Real-time vision-based multiple vehicle detection and tracking for nighttime traffic surveillance , 2009, 2009 IEEE International Conference on Systems, Man and Cybernetics.

[17]  Fatih Murat Porikli,et al.  Changedetection.net: A new change detection benchmark dataset , 2012, 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[18]  Logesh Vasu,et al.  An effective step to real-time implementation of accident detection system using image processing , 2010 .

[19]  Cathleen Shamieh Electronics for dummies, a Wiley brand , 2015 .

[20]  Ghazali Sulong,et al.  Vehicle Detection and Tracking Techniques: A Concise Review , 2014, ArXiv.

[21]  H. Niemann,et al.  Adaptive change detection for real-time surveillance applications , 2000, Proceedings Third IEEE International Workshop on Visual Surveillance.

[22]  D. Koller,et al.  Towards robust automatic traffic scene analysis in real-time , 1994, Proceedings of 1994 33rd IEEE Conference on Decision and Control.

[23]  Wu-Chih Hu,et al.  Reliable moving vehicle detection based on the filtering of swinging tree leaves and raindrops , 2012, J. Vis. Commun. Image Represent..

[24]  Gc De Silva,et al.  Automation of traffic flow measurement using video images , 2002 .

[25]  Osama Masoud,et al.  Detection and classification of vehicles , 2002, IEEE Trans. Intell. Transp. Syst..

[26]  Wei Zhang,et al.  Moving vehicles detection based on adaptive motion histogram , 2010, Digit. Signal Process..

[27]  Stanley T. Birchfield,et al.  Real-Time Incremental Segmentation and Tracking of Vehicles at Low Camera Angles Using Stable Features , 2008, IEEE Transactions on Intelligent Transportation Systems.