Acta Geodaetica et Cartographica Sinica ›› 2023, Vol. 52 ›› Issue (5): 808-817.doi: 10.11947/j.AGCS.2023.20210691

• Photogrammetry andRemote Sensing • Previous Articles     Next Articles

SER-UNet algorithm for building extraction from high-resolution remote sensing image combined with multipath

HU Minghong, LI Jiatian, YAO Yanji, A Xiaohui, LU Mei, LI Wen   

  1. Faculty of Land and Resources Engineering, Kunming University of Science and Technology, Kunming 650093, China
  • Received:2021-12-14 Revised:2022-09-15 Published:2023-05-27
  • Supported by:
    The National Natural Science Foundation of China (No. 41561082)

Abstract: Aiming at the problems of inaccurate edges and loss of small buildings in the extracted buildings due to the inability of deep convolution to take into account global features and local features, the SER-UNet algorithm is proposed based on attention mechanism and skip connection. SER-UNet algorithm couples SE_ResNet and max pooling layers in the encoder stage, and the SE_ResNet structure and deconvolution are used in the decoder stage. The feature map is output after fusing the shallow features extracted by the encoder and the deep features extracted by the decoder through skip connections. In order to analyze the effectiveness of the method, the SER-UNet is used to replace the feature extraction structure in the original network in the parallel multi-path feature extraction stage of the MAP-Net network. Finally, the method proposed is experimentally evaluated on the WHU dataset and the Inria dataset, and the IoU and precision reach 91.46%, 82.61% and 95.67%, 92.75%, compared with UNet, PSPNet, ResNet101, and MAP-Net Networks, the IoU is increased by 0.49%, 0.14%, 1.89%, and 1.57%, and the precision is increased by 0.14%, 1.06%, 2.42% and 1.09%, respectively. To further analyze the validity of the SER-UNet algorithm, the edge integrity and small extraction verification IoU and precision reached 85.32% and 94.13% on the AerialImage dataset. The experiment results show that the MAP-Net parallel multipath network combined with SER-UNet algorithm shows good generalization ability. In addition, the SER-UNet algorithm can be effectively embedded in PSPNet, ResNet101, HRNetv2 and other Networks to improve the ability of Network feature representation.

Key words: high-resolution remote sensing image, building extraction, parallel multipath, attention mechanism, skip connection

CLC Number: