YOLOv4 Vs YOLOv5: Object Detection on Surveillance Videos

Now-a-days, Object detection algorithms becomes more popular because of their significant contribution to the field of computer vision. Object detection algorithms are divided into two approaches i) region-based approach and ii) region-free approach. In this paper, we implemented YOLOv4 and YOLOv5 techniques of region-free approach due to their high detection speed and accuracy. The objective of this paper is to identify the relevant and non-relevant parts of surveillance videos as watching entire video footage is a time-consuming process. The use case for this research work is ATM surveillance footage, where the dataset is publicly not available, to train the network we developed our data set and then train and compare the proposed models. After experimental results, it is observed that YOLOv5 archives 84% accuracy and give better results than YOLOv4 which achieve 56% accuracy only.