Nighttime vehicle detection,counting and classification

Electronics and Communication Engineering

Intelligent transportation systems have received lot of attention in the last decades. Vehicle detection is the important task in this area and vehicle counting and classification are two important applications . In proposed system for nighttime vehicle detection, counting and classification we process the frames with different feature methods like background subtraction algorithm (identifying objects), track the object using tracking algorithm (blob analysis) and count the vehicles through ROI sensing line and classifying the vehicle using correlation matching process. The vehicles are tracked by creating bounding boxes around them. The vehicles can be effectively detected by using morphological processing techniques and the unwanted regions can be filtered using kalman filtering. Each time when the vehicle crosses the region of interest list the count will be updated for each frame. Different types of templates are used to classify vehicles into three categories as small (e.g. car), medium (e.g. van) and large (e.g. bus and truck). The templates used are different types of headlamps taken and matched with the vehicles present in each frame. The type of vehicle can be identified based on the distance between the two headlamps of the vehicle. The results obtained are such that it reduces the complexity of analysis and it improves the detection by avoiding other movable objects.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.