Vehicle detection, counting and classification in various conditions

Abstract

Intelligent transportation systems have received a lot of attention in the last decades. Vehicle detection is the key task in this area and vehicle counting and classification are two important applications. In this study, the authors proposed a vehicle detection method which selects vehicles using an active basis model and verifies them according to their reflection symmetry. Then, they count and classify them by extracting two features: vehicle length in the corresponding time-spatial image and the correlation computed from the grey-level co-occurrence matrix of the vehicle image within its bounding box. A random forest is trained to classify vehicles into three categories: small (e.g. car), medium (e.g. van) and large (e.g. bus and truck). The proposed method is evaluated using a dataset including seven video streams which contain common highway challenges such as different lighting conditions, various weather conditions, camera vibration and image blurring. Experimental results show the good performance of the proposed method and its efficiency for use in traffic monitoring systems during the day (in the presence of shadows), night and all seasons of the year.