2020 年 61 巻 2 号 p. 109-113
In Japan, there are around 33,000 level crossings and over 90% are equipped with automatic barriers. Despite of all the efforts made by government and railway operators, every year more than 200 people are injured due to accidents inside level crossings. In order to detect pedestrians trapped inside level crossings, we propose a new Obstacle Detector (OD) using infrared camera and image processing algorithm. Evaluation result of the proposed method shows no false negative output and by applying filtering methods, probability of false operation of the OD can be reduced more than 10 times, leading to stable operation.