Real Time Road Traffic Detection Using Computer Vision

Abstract

Object detection using Machine learning has achieved very good performance but there are many problems with images in real-world shooting such as noise, blurring or rotating jitter, etc. These problems effects the object detection. The main objective is to detect objects using You Only Look Once (YOLO) algorithm. The YOLO method has several advantages when compared to other object detection algorithms. In other algorithms like Convolutional Neural Network (CNN), Fast-Convolutional Neural Network the algorithm will not look at the image completely, but in YOLO, the algorithm looks the image completely by predicting the bounding boxes using convolutional network and finds class probabilities for these boxes and also detects the image faster as compared to other algorithms. We have used this algorithm for detecting different types of objects.