Vehicle Classification and Detection using Deep Learning

Abstract

Intelligent transportation systems have acknowledged a ration of attention in the last decades. In this area vehicle classification and localization is the key task. In this task the biggest challenge is to discriminate the features of different vehicles. Further, vehicle classification and detection is a hard problem to identify and locate because wide variety of vehicles don’t follow the lane discipline. In this article, to identify and locate, we have created a convolution neural network from scratch to classify and detect objects using a modern convolution neural network based on fast regions. In this work we have considered three types of vehicles like bus, car and bike for classification and detection. Our approach will use the entire image as input and create a bounding box with probability estimates of the feature classes as output. The results of the experiment have shown that the projected system can considerably improve the accuracy of the detection.