Faster R-CNN and YOLOv3: a general analysis between popular object detection networks

Abstract

Computer vision is developing really fast in recent years, and object detection is now one of the hottest topics. faster region-based convolutional neural network (faster R-CNN) and You Only Look Once (YOLOv3) are two popular modules to solve object detection problems, but they are implemented in different ways and thus have different performance in practice. This article is going to introduce these two modern modules and make a few experiments to compare the performance of each module with various datasets. This analysis will focus on speed, accuracy and the performances in different situations. Two specific studies will be mentioned as two typical examples of object detection application: face mask detection and greenhouse detection from satellite images. At last, the article will draw out a conclusion, make some suggestions for the choice of faster R-CNN and YOLOv3 and make a prospect for the future. It turns out that generally faster R-CNN fits tasks that require high accuracy better and YOLOv3 can realize real-time detection tasks.