Objects tracking from video

Abstract

Object tracking is the process via which computers are able to detect, understand, and keep an eye on objects across still images or videos. It is one of the most widespread applications of artificial intelligence (AI) and computer vision (CV). With object tracking solutions, we can perform meaningful actions on visual data obtained via different types of cameras. Using suitable object detection algorithms coupled with tracking models, we can train a machine to not just recognize one or more unique objects or persons in a particular image, but also identify them in subsequent frames and follow their trajectory in a video stream. In this project report, our the aim is to track Objects across the frames using YOLOv3 and Simple Online Real Time Tracking (SORT) on traffic surveillance video. We usually locate the target by drawing the smallest rectangle possible (the “bounding box”) in which it is included. Also in this project work efficient detection and tracking on vehicle dataset is witnessed. The algorithms give real-time, accurate, precise identifications suitable for real-time traffic applications.