Building detection from remote sensing images using yolo

Abstract

Building detection system through the remote sensing of images has been widely studied. In this thesis, we propose a model for detecting buildings at airports in Asia through different levels of remote sensing image. The proposed model is improved using the You Only Look Once (YOLO) algorithm based on the convolutional neural network (CNN). We also adjust an inputted image to our model using the Jet Saliency Map. The buildings to be detected in this study are the passenger terminals, the control towers, the cargo buildings, and the hangars. The data set has been collected from 322 different airports in Asia. Furthermore, our improved model is also examined for efficiency and accuracy. The results show that it can detect the intended objects efficiently and provides higher accuracy than the original model.