| Summary: | 碩士 === 元智大學 === 電機工程學系 === 101 === Given the rapid expansion of car ownership worldwide, vehicle safety is an increasingly critical issue in the automobile industry. The reduced cost of cameras and optical devices has made it economically feasible to deploy front-mounted intelligent systems for visual-based event detection for forward collision avoidance and mitigation. While driving at night, vehicles in front are generally visible by their tail lights. The indicator lights are particularly important because they signal lane change and potential collision. Therefore, in this paper, we propose a novel visual-based approach, based on the Nakagami-m distribution, for detecting indicator lights at night by modeling scattering of tail lights. In addition, to recognize the direction of indicator light, reflectance is decomposed from original image. Rather than using the knowledge of the heuristic features, such as the symmetry, position and size of the rear-facing vehicle, we focus on finding the invariant features to model indicator light scattering by Nakagami imaging and therefore conduct the detection process in a part-based manner. Experiments on an extensive dataset show that our proposed system can effectively detect vehicle indicator light under different lighting and traffic conditions, and thus demonstrates its feasibility in real-world environments.
|
|---|
