An Image Processing Based Method For Vehicle Speed Estimation

Vehicle flow estimation is an important part of traffic management system. It plays an important role in tracking systems, automatic video surveillance and also to avoid collision. This paper proposes a method to estimate the speed of vehicles on the highways and city areas. The proposed method can be effectively implemented to control the over speed vehicles and to found guilty in leading to traffic accidents. Each vehicle in the video recorded by the camera is identified. A bounding box is created on the identified vehicle and its centroid coordinates are marked. The analysis of speed is done using mathematical formulae which are embedded in the software. The existing research in this field has certain limitations. The first limitation is consumption of a lot of memory to store videos in the hard drive. The second limitation is inaccuracy of the system in unpleasant weather conditions such fog, haze, rain, and heavy winds, etc. Some systems failed to crate proper bounding box as it is necessary for accurate analysis of the motion of the vehicle and its speed. Another disadvantage is that shadow produced by vehicles on the different lanes of the road creates a fuss and the system detects the shadow too as a different object and creates a bounding box over it. There are other hardware based methods such as radar gun also. Cosine errors occurred when the direction of the vehicle and the radar gun doesn’t match. The objective of the proposed work is to develop a system which can provide the alternative to the radar based systems which can detect multiple vehicles at the same time. We have evaluated the proposed method on various traffic videos and found that the proposed method accurately detect the speed of a vehicle and outperforms many state-of-the-art

[1]  Bashirahamad F. Momin,et al.  Vehicle detection and attribute based search of vehicles in video surveillance system , 2015, 2015 International Conference on Circuits, Power and Computing Technologies [ICCPCT-2015].

[2]  Rodrigo Minetto,et al.  A Video-Based System for Vehicle Speed Measurement in Urban Roadways , 2017, IEEE Transactions on Intelligent Transportation Systems.

[3]  Rajesh Rajamani,et al.  Portable Roadside Sensors for Vehicle Counting, Classification, and Speed Measurement , 2014, IEEE Transactions on Intelligent Transportation Systems.

[4]  Fengqi Yu,et al.  A Cross-Correlation Technique for Vehicle Detections in Wireless Magnetic Sensor Network , 2016, IEEE Sensors Journal.

[5]  Wang Jian,et al.  A Novel Vehicle Detection Method Based on Wireless Magneto-resistive Sensor , 2009, 2009 Third International Symposium on Intelligent Information Technology Application.

[6]  Changxu Wu,et al.  A novel 2D-3D hybrid approach to vehicle trajectory and speed estimation , 2014, 17th International IEEE Conference on Intelligent Transportation Systems (ITSC).

[7]  Bo Yang,et al.  Vehicle Detection and Classification for Low-Speed Congested Traffic With Anisotropic Magnetoresistive Sensor , 2015, IEEE Sensors Journal.

[8]  Byung-Geun Lee,et al.  Background subtraction based on Gaussian mixture models using color and depth information , 2014, The 2014 International Conference on Control, Automation and Information Sciences (ICCAIS 2014).

[9]  Doo-Kwon Baik,et al.  Model for accurate speed measurement using double-loop detectors , 2006, IEEE Transactions on Vehicular Technology.

[10]  Bo Yang,et al.  Adaptable Vehicle Detection and Speed Estimation for Changeable Urban Traffic With Anisotropic Magnetoresistive Sensors , 2017, IEEE Sensors Journal.

[11]  Mats I. Pettersson,et al.  Vehicle speed measurement model for video-based systems , 2019, Comput. Electr. Eng..

[12]  Hong Li,et al.  Measurement of Absolute Vehicle Speed With a Simplified Inverse Model , 2010, IEEE Transactions on Vehicular Technology.

[13]  W. Eric L. Grimson,et al.  Adaptive background mixture models for real-time tracking , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[14]  Hazem El-Gendy,et al.  Speed Detection Camera System using Image Processing Techniques on Video Streams , 2011 .

[15]  Jozef Gerát,et al.  Vehicle speed detection from camera stream using image processing methods , 2017, 2017 International Symposium ELMAR.