Video Analysis of Vehicle and Pedestrian Using Neural Network

Abstract

In this paper, we suggest an algorithm for detection and tracking analysis of vehicles, pedestrians in video frames. The extracted features function for visual perception tasks and are used to address a tracking problem. The algorithm can be split into 2 sections the first part is classification algorithm, which is predicted on convolutional neural networks. The CNN model is implemented using the You Only Look Once (YOLO) algorithm in deep learning. And the second part is algorithm for tracking regions. Using this algorithm, we suggest an idea of detecting, counting of vehicles and pedestrian.