Semantic Segmentation of Urban Buildings from VHR Remote Sensing Imagery Using a Deep Convolutional Neural Network

• Published in: Remote sensing (Basel, Switzerland) Vol. 11; no. 15; p. 1774
• Main Authors: Yi, Yaning, Zhang, Zhijie, Zhang, Wanchang, Zhang, Chuanrong, Li, Weidong, Zhao, Tian
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 28.07.2019
• Subjects: aerial photography; artificial intelligence; Artificial neural networks; Buildings; Classification; deep convolutional neural network; Deep learning; Detection; Feature extraction; Feature maps; Image processing; Image reconstruction; Image segmentation; Neural networks; Pattern recognition; quantitative analysis; Remote sensing; Sampling; Semantic segmentation; Semantics; Spatial discrimination; Spatial resolution; Training; U-Net; urban building extraction; VHR remote sensing imagery; Beijing China; United States > US; China

Urban building segmentation is a prevalent research domain for very high resolution (VHR) remote sensing; however, various appearances and complicated background of VHR remote sensing imagery make accurate semantic segmentation of urban buildings a challenge in relevant applications. Following the b...