Designing Electronic Traffic Information Acquisition System Using Deep Learning and Internet of Things

In implementing the Intelligent Traffic Monitoring System (ITMS), timely and effective access to road traffic information is an essential link. It requires Information Acquisition (IAS) collect real-time data transmit collected background for processing. Therefore, this paper studies on-road vehicle recognition based on Deep Learning (DL). Firstly, a framework of IAS proposed. Then, improved MT-GooGleNet model Convolutional Neural Network (CNN) proposed locate recognize vehicles in images. Finally, performance analyzed by simulation. The experimental results position show that classification accuracy Multi-Task (MT)-GooGleNet after fine-tuning 99.5%. Compared with other models, best recognition, its positioning very high. identification enhancement pre-training, testing set 79.96%. model’s has been dramatically research provides reference establishing future.