Vehicle Type Classification Using CNN

Computer Engineering

Vehicle classifier has important roles in intelligent traffic management and transportation. Identifying one vehicle type from another is a difficult task. Vehicle classification problem is essentially image classification problem for which Convolutional Neural Networks are best to work with as CNN require little image pre-processing as compared to other approaches. Convolutional neural network does not require handcrafted features for classification as opposed to traditional machine learning approaches. In this paper we use supervised approach to train Convolutional Neural Network. The Neural network output a probability vector for identifying vehicle type. A vehicle classifier is very useful in intelligent traffic management. It can classify an Emergency Vehicle like an Ambulance or a Fire Truck from other vehicle types and this information can be used to intelligently change traffic flow as needed.

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