Adaptive Vehicle Detection and Classification Scheme for Urban Traffic Scenes Using Convolutional Neural Network

Abstract

A large number of digital cameras have been installed at intersections in urban areas to help monitor traffic conditions. Making better use of scenes captured by these traffic surveillance cameras facilitates the construction of advanced Intelligent Transportation Systems (ITS). This research aims at developing an adaptive vehicle detection and classification scheme for urban traffic scenes, which collects roadside surveillance videos from publicly available sources. The proposed scheme consists of two main phases; the first phase is to collect some traffic surveillance images for training a general model using Faster R-CNN. The second phase utilizes background subtraction to extract vehicle proposals. A sufficient number of vehicles are collected by comparing proposals with the detection results by the general model. Collected vehicles are superimposed on the constructed background in an appropriate order to achieve semiautomatic generation of annotated training data. The training data are used to acquire a second-phase adaptive model. The experimental results show that the proposed scheme performs well and can handle vehicle occlusion problems.