Evaluating R-CNN and YOLO V8 for megalithic monument detection in satellite images

Abstract

Over recent years, archaeologists have started to use object detection methods in satellite images to search for potential archaeological sites. Within image object recognition, due to its ability to recognize objects with great accuracy, convolutional neural networks (CNN) are becoming increasingly popular. This study compares the performance of existing deep-learning algorithms for the detection of small megalithic monuments in satellite imagery, namely RCNN (Region-based Convolutional Neural Networks) and YOLO (You Only Look Once). Using a satellite image dataset and after adequate preprocessing, results showed that this is a feasible approach for archaeological image prospection, with RCNN achieving a remarkable precision of 93% in detecting these small monuments.