Deep Learning based Pollution Detection in Intelligent Transportation System

摘要

Vehicle pollution is a major concern in the current world. The technologies are improving day by day to reduce the pollution caused by the car. However, we are still lagging from addressing this critical issue completely. Therefore, road surveillance should be made stringent to capture those vehicles causing this serious problem. In this article, we have proposed a deep learning based framework which will identify the vehicle pollution from the images captured by the on-road surveillance camera. We have prepared an enriched large data set with significant variations which has been used in the training phase while deploying the deep model. The experiment has dealt with three base line Deep Learning CNN models, i.e. Inception-V3, MobileNet-V2 and InceptionResNet-V2. Transfer learning concept has been exploited to identify the on-road polluting vehicle. The experimental outcome has demonstrated the supremacy of the proposed approach in the traffic surveillance domain.