You Only Look Once - Object Detection Models: A Review

Object detection is the task of detecting instances of particular classes in an image. The You Only Look Once (YOLO) object detection algorithms have become popular in recent years due to their high accuracy and fast inference speed. In this review, an overview of YOLO variants, including YOLOv2, YOLOv3, YOLOv4, YOLOv5, YOLOv6 and YOLOv7, is performed and compared on the basis of evaluation metrics. We begin by discussing the basic principles and architecture of YOLO, which involves a single network architecture that predicts bounding boxes and class probabilities directly from full images. In addition, the changes made in each version of YOLO, such as incorporating skip connections, feature pyramid networks, and anchor boxes to improve accuracy and speed is discussed. A critical comparative analysis of YOLO variants is performed, highlighting the trade-offs between accuracy and speed. Finally, we highlight some of the future research directions for YOLO variants, such as improving their robustness to different environmental conditions like motion blur, lighting condition and integrating them with other computer vision tasks like image segmentation, image classification and object tracking. This work will help a researcher to select a version that is best suited for a given application.