Land Cover Change Detection Based on Lenet-5 by Using Very-High-Resolution Remote Sensing Images

Abstract

On the basis of remote sensing images, land cover change detection (LCCD) has gained popularity. Even though several techniques have been promoted lately, their effectiveness and usability still need to be improved. To assist urban sustainable development, evaluate natural disasters, and analyze the environment, very high-resolution (VHR) remote sensing images can be used to detect land cover change. Planning professionals can evaluate changes in land cover using remote sensing and geographic information systems, which have a reputation for excellence. A fully convolutional two-stream architecture is used in this paper to first extract highly representative deep features from bi-temporal images. After that, a Lenet5 is given the deep features to segment the land changes and detect changes. With the help of Faster-RCNN the land change classes are classified. We implement the proposed model in Python and conduct experiments on the land cover dataset. The outcomes of the experiments demonstrate that the proposed method outperformed previous deep learning algorithms, achieving the best accuracy, precision, recall, and F1-score.