Automatic vehicle counting using background subtraction method on gray scale images and morphology operation

• Published in: Journal of physics. Conference series 2018-05, Vol.1025 (1), p.12025
• Main Authors: Adi, K, Widodo, A P, Widodo, C E, Pamungkas, A, Putranto, A B
• Format: Article
• Language: English
• Subjects: Gray scale; Highway transportation; Image acquisition; Image processing; Morning; Morphology; Physics; Subtraction; Toll roads; Transportation management; Vehicles; Video
• ISSN: 1742-6588; 1742-6596
• DOI: 10.1088/1742-6596/1025/1/012025

Traffic monitoring on road needs to be done, the counting of the number of vehicles passing the road is necessary. It is more emphasized for highway transportation management in order to prevent efforts. Therefore, it is necessary to develop a system that is able to counting the number of vehicles automatically. Video processing method is able to counting the number of vehicles automatically. This research has development a system of vehicle counting on toll road. This system includes processes of video acquisition, frame extraction, and image processing for each frame. Video acquisition is conducted in the morning, at noon, in the afternoon, and in the evening. This system employs of background subtraction and morphology methods on gray scale images for vehicle counting. The best vehicle counting results were obtained in the morning with a counting accuracy of 86.36 %, whereas the lowest accuracy was in the evening, at 21.43 %. Differences in morning and evening results are caused by different illumination in the morning and evening. This will cause the values in the image pixels to be different.