TRAFFIC PERCEPTION BASED ON WEATHER CONDITION

Traffic accidents are particularly serious on the rainy days,the dark nights, the rainy nights, the foggy day, and many other times with low visibility conditions. Existing vision driver assistance systems are designed to perform under good-natured weather conditions. Classification is a type of methodology to identify the optical characteristics for vision enhancement algorithms to make them more efficient. To improve the machine vision at bad weather situations, a multi-class weather classification method has been presented based on multiple weather features and supervised learning. Priorly underlying visual features are extracted from multi-traffic scene images.Then secondly, five supervised learning algorithms are used to train classifiers. The analysis shows about how extracted features can accurately describe the image semantics, and classifiers have high recognition accuracy rate and adaptive ability. The proposed method will be providing the basis for further enhancing the detection of anterior vehicle detection during the night time illumination changes, and enhancing the driver’s field of vision on a foggy day.