VISION BASED SAFETY SPACE IDENTIFICATION FOR MOTORCYCLES
Albert Y. Chen1 and Meng-Hsiu Hsieh2
1) Assistant Professor, Department of Civil Engineering, National Taiwan University, Taipei, Taiwan. 2) Graduate Research Assistant, Department of Civil Engineering, National Taiwan University, Taipei, Taiwan.
Abstract: Individual motorcycle behavior depends on the surrounding environment such as the geometric design of the road. For their own safety, motorcyclists react to the distance and velocity of other vehicles. Especially at the peak hours, the traffic condition changes rapidly. By setting up a camera at the intersection to record traffic flow video clips, the safety space and the motorcycles’ velocity are measured by analyzing the data. The motorcycle behavior at the intersection is observed and analyzed through computer vision and image processing methods. The Histogram of Gradients (HOG) descriptor is adapted for the detection of motorcycles utilizing a Support Vector Machine (SVM), and the Kalman Filter is employed for the tracking of the motorcycles’ trace. The motorcycles’ safety space and traffic characteristics are observed such as: (1) the rate of invasion into the safety space at different location (intersection, road with traffic sign, road without traffic sign), (2) The angle of other vehicles from the vehicle being observed in the safety space, and (3) the rate of different vehicles that invade into the safety space. We have taken video clips in Taipei, and the results of this study can serve as a reference for traffic safety guidance for motorcyclists and can potentially be applied for detection of danger road geometries.
Keywords: image processing, histogram of oriented gradient, support vector machine, Kalman Filter.
Albert Y. Chen and Meng-Hsiu Hsieh. “VISION BASED SAFETY SPACE IDENTIFICATION FOR MOTORCYCLES.” In Proceedings of International Conference on Civil and Building Engineering Informatics (ICCBEI 2015), 105. Tokyo, Japan, 2015.