 This research paper examines the potential of using deep learning algorithms to detect oil storage tanks in remote sensing images. Five algorithms, faster RCNN, YOLOV5, YOLOV7, Retininet and SSD, were tested on 3,568 remote sensing images from five different data sets. The results showed that the SSD algorithm had the highest average accuracy of 0.897 and the highest F1 score of 0.80, while the lowest average accuracy was achieved by Retininet at 0.639. The training results of the five algorithms were validated on three images containing differently sized oil storage tanks and complex backgrounds, and the validation results obtained were better than those obtained in the training phase, indicating that these algorithms can be used to accurately detect oil storage tanks in remote sensing images. This article was authored by Lu Fan, Xiaoying Chen, Yang Yuan, and others. We are article.tv, links in the description below.