Vehicle Detection and Counting Using Adaptive Background Model Based on Approximate Median Filter and Triangulation Thre
- PDF / 1,255,110 Bytes
- 12 Pages / 612 x 792 pts (letter) Page_size
- 12 Downloads / 256 Views
ehicle Detection and Counting Using Adaptive Background Model Based on Approximate Median Filter and Triangulation Threshold Techniques M. A. El-Khorebya, b, *, S. A. R. Abu-Bakarb, M. Mohd Mokjib, and S. N. Omarc a
Department of Electronics and Communications, Arab Academy for Science Technology and Maritime Transport, Alexandria, Egypt b School of Electrical Engineering, Faculty of Engineering Universiti Teknologi Malaysia, Johor Bahru, 81310 Malaysia c Faculty of Science and Technology Universiti Sains Islam Malaysia, Nilai, 71800 Malaysia *e-mail: [email protected] Received October 1, 2019; revised December 30, 2019; accepted January 28, 2020
Abstract—Background subtraction method is widely used for vehicle detection. One of the issues in this method is to find a suitable and accurate background model that works in all conditions. Moreover, setting an appropriate threshold value to discriminate between the moving objects and stationary background plays a crucial role in increasing the detection performance. In this paper, an adaptive background model combined with an adaptive threshold method is proposed. It is demonstrated that the proposed method can efficiently differentiate between moving vehicles and background in urban roads under different weather conditions (i.e., normal, rainy, foggy, and snowy). Comparisons between the proposed method and other methods, such as the adaptive local threshold (ALT) and the three frame-differencing methods show the potential of our approach. The experimental results show that the proposed method increases the average recall value by 16.4% and the average precision value by 21.7% in comparison to the ALT method with a negligible increase in the processing time. Keywords: vehicle counting, background subtraction, thresholding DOI: 10.3103/S0146411620040057
1. INTRODUCTION Intelligent Transportation Systems (ITS) can be defined as an application of new information and communication technologies of vehicles and roads for monitoring and managing traffic flow, decreasing congestion, improving security, and optimizing the use of roads and transportation. Additionally, it also provides information to the drivers about the best routes and the travel time for their destination in realtime [1]. Consequently, the development of ITS that extracts information from the traffic surveillance systems plays a paramount role in ensuring better safety, directing smoother traffic flow, improving better traffic control in congested urban areas, and maintaining law and order of traffic and traffic signals [1, 2]. One of the important features for reliable ITS is the ability to accurately estimating the number of vehicles based on traffic video sequences. This is a crucial task as it guarantees sustainable information for traffic management and control [3]. Vehicle counting can be used for analyzing the traffic status, such as road-traffic intensity, lane occupancy, and congestion level, which helps the drivers to avoid traffic congestion and spend less time in traffic. Such information
Data Loading...
