Object Detection and Tracking Using Yolo

Abstract

Artificial Intelligence is being adapted by the world since past few years and deep learning played a crucial role in it. This paper focuses on deep learning and how it is applied to detect and track the objects. Deep learning works with the algorithms influenced by the layout and functionalities of the brain. The advantage of working with such algorithms is that the performance increases with increase in data which isn't the case for traditional learning algorithms whose performance stabilizes even with increase in the amount data. Real time object tracking has been at the forefront of some of the most sought out research topics in computer vision applications. Regardless of the tremendous progress made in this area, effectiveness and fidelity of accuracy in tracking the objects in real time at a substantial level still remains a grave challenge. Detection and tracking algorithms are specified in terms of extricating the features of images and videos for security and scrutiny applications. Popular algorithms of object detection include You Only Look Once (YOLO), Region-based Convolutional Neural Networks (RCNN), Faster RCNN (F-RCNN). RCNN has better accuracy compared to other algorithms but YOLO surpasses when speed is considered over accuracy. In YOLO, Object detection is implemented as a regression problem and class probabilities are provided for detected images.