Data Accumulation System of Obstacle Avoidance Behavior on Bicycle Trip for Transportation Engineering

摘要

This paper proposes a data accumulation system of obstacle avoidance behavior on bicycle trips in videos using gesture based on deep learning-based features. In the field of transportation engineering, realization of image/video processing-based methods for analyzing of various situations in transportation scenes has been expected. Therefore, many videos taken by CCTV and dashcams are accumulated in various transportation organizations. However, since these accumulates only raw videos which are huge size, that transmission, accumulate device and analysis of accumulated videos are very high cost as social infrastructures. Therefore, this paper constructs a system for accumulating small-sized videos, extracted features and analyzed results of the transportation scene, which is the obstacle avoidance behavior on bicycle trips. This system is constructed on a small size computer which can be worked by using the battery in order to equip on various structures. Also, an algorithm for detecting obstacle avoidance behavior on bicycle trips in videos are realized by utilizing deep learning-based features and support vector machines.