Automatic 3D Multiple Building Change Detection Model Based on Encoder–Decoder Network Using Highly Unbalanced Remote Sensing Datasets

Abstract

3D building change detection (CD) methods detect more accurate multiple change maps than 2D ones. Recent technologies such as unmanned aerial vehicle (UAV) systems and dense image matching have made it much easier to obtain 3D data nowadays. Developing a solution which produces an accurate map of multiple building changes, including <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Unclassified, No building change, Newly built, Demolished</i> , and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Taller</i> , at an acceptable speed is a challenging issue. In this study we address a novel 3D building CD method based on an Encoder-Decoder network to detect accurate multiple changes maps automatically, in the presence of highly unbalanced remote sensing datasets. The proposed method consists of three main parts: the pre-processing and mixed augmentation (MA) step, the Encoder-Decoder network training, and finally the prediction step. The data are augmented by the MA method to manipulate highly unbalanced datasets. The Encoder-Decoder network is constructed by the Yolov7 network as the encoder path and the decoder path equipped with the convolutional layers of modified Unet (CLMUnet). Two datasets are used in this study. The first dataset is the point clouds and orthophotos obtained from the UAV of Mashhad City in 2011 and 2016. The second dataset consists of stereo images of the GeoEye-1 satellite and the point clouds obtained from dense image matching of Tehran city in 2009 and 2013. The results show that the proposed method achieved accuracy and kappa coefficients above 94% and 0.90 for both datasets, respectively.

Topics & Concepts