In this work we tackle traffic analysis problems for Phnom Penh roads. Unlike in most developed countries such as Australia and USA, the traffic conditions in developing countries such as Cambodia pose unique challenges. For instance, motorcycles are ...
In this work we tackle traffic analysis problems for Phnom Penh roads. Unlike in most developed countries such as Australia and USA, the traffic conditions in developing countries such as Cambodia pose unique challenges. For instance, motorcycles are popular vehicles. This means, during peak hours, where the traffic for cars is congested, the traffic for motorcycles could still be flowing. Thus, any approaches using the whole video to determine the traffic condition are not suitable. To that end, this work provides the first stepping-stone by addressing the Phnom Penh vehicle classification problem. We propose a novel dataset capturing CCTV of Phnom Penh roads in 5 locations from 7am until 5pm on five sunny days. Then, we perform the study by proposing a baseline method comprising three steps: (1) background subtraction; (2) bag-of-word histogram feature extraction; and (3) classification using Support Vector Machine (SVM). Evaluation results show promising results with accuracy 0.76, 0.63 and 0.40 for light, medium and heavy traffic.