Pixel matching search algorithm for counting moving vehicle in highway traffic videos
- PDF / 1,442,864 Bytes
- 20 Pages / 439.642 x 666.49 pts Page_size
- 69 Downloads / 202 Views
Pixel matching search algorithm for counting moving vehicle in highway traffic videos Harikrishnan P. M.1 · Anju Thomas1 · Nisha J. S.1 · Varun P. Gopi1
· P. Palanisamy1
Received: 8 December 2019 / Revised: 10 July 2020 / Accepted: 18 August 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Traffic monitoring through video processing is one of the hot research areas in the Intelligent Transportation System (ITS). Vehicle counting systems should be simple enough to be applied in real-time circumstances. A novel and fast algorithm for vehicle counting from a traffic video sequence is proposed in this paper where the vehicle tracking step is not necessary. A reference model is only created in the video frames for a narrow area. When going through this narrow area, the moving vehicles are identified as foreground objects. Detection of moving vehicles is achieved by integrating approximated median filter based background subtraction with binary integral projection. The detected candidates are counted as a vehicle using a novel pixel matching search algorithm. The proposed algorithm does not rely on every video frame. It only requires every third frame for processing and thus increases the computation speed by three times compared to existing techniques. The proposed algorithm is tested and validated on a standard data set as well as a custom data set. Two parameters such as accuracy and processing time are used for the system evaluation where an overall accuracy of 96.84% is achieved. The processing time results show that the proposed system can perform in real-time with an average real-time processing speed of 93.92%. Keywords Approximated median filter · Integral projection · Vehicle counting · Vehicle detection · Intelligent transportation systems Varun P. Gopi
[email protected] Harikrishnan P. M. [email protected] Anju Thomas [email protected] Nisha J. S. [email protected] P. Palanisamy [email protected] 1
National Institutte of Technology Tiruchirapalli, Tamilnadu, India
Multimedia Tools and Applications
1 Introduction One of the fundamental requirements in an intelligent transportation system (ITS) is the estimation of traffic density on roadways which can be directly measured by detecting and counting the number of Moving Vehicles (MV) traveling. The detection of MV can be achieved using different techniques. In hanging position over the lane, electromagnetic detectors such as microwave [2] and ultrasonic [14] can be deployed. When the vehicle reaches the detection zone, the count is noted. This type of MV detector is cheap and easy to mount, but the main drawback is that its detection range is much smaller and cannot handle occluded vehicles simultaneously. It is possible to deploy intrusive sensors such as inductive loops, micro-loop tests, magnetometers, piezoelectric cables, and pneumatic road tubes directly under the road to count the MV [22]. The downside of their use is that these sensors can only be mounted and maintained promptly [19]. Vision-based
Data Loading...