PCL–PTD Net: Parallel Cross-Learning-Based Pixel Transferred Deconvolutional Network for Building Extraction in Dense Building Areas With Shadow

Abstract

Urban building segmentation from remote sensed imageries is challenging due to there usually existing a variety of building features. Furthermore, very high spatial resolution imagery can provide many details of the urban building, such as styles, small gaps among buildings, building shadows, etc. Hence, satisfactory accuracy in detecting and extracting urban features from highly detailed images still remains. Deep learning semantic segmentation using baseline networks works well on building extraction, however their ability in building extraction in shadows area, unclear building feature, and narrow gaps among buildings in dense building zone is still limited. In this paper, we propose parallel cross learning based pixel transferred deconvolutional network (PCL-PTD net), and then is used to segment urban buildings from aerial photographs. The proposed method is evaluated and intercompared with traditional baseline networks.In PCL-PTD net, it is composed of parallel network, cross learning functions, residual unit in encoder part, and pixel transferred deconvolution in decoder part. The performance is applied to three datasets (Inria aerial dataset, ISPRS Potsdam dataset, UAV building dataset), to evaluate its accuracy and robustness. As a result, we found that PCL-PTD net can improve learning capacities of the supervised learning model in differentiating buildings in dense area and extracting buildings covered by shadows. As compared to the baseline networks, we found that proposed network shows superior performance compared to all eight networks (SegNet, U-net, PSPnet, PixelDCL, DeeplabV3+, U-Net++, CFENet, IRU-Net). The experiments on three datasets also demonstrate the ability of proposed framework and indicating its performance.