Instance Segmentation of Buildings from High-Resolution Remote Sensing Images with Multitask Learning

被引：0
|
作者：
Hui J. [1 ,2 ]
Qin Q. [1 ,2 ,3 ]
Xu W. [1 ,2 ]
Sui J. [1 ]
机构：
[1] Institute of Remote Sensing and Geographic Information System, School of Earth and Space Sciences, Peking University, Beijing
[2] Beijing Key Lab of Spatial Information Integration and 3S Application, Beijing
[3] Geographic Information System Technology Innovation Center, Ministry of Natural Resources, Beijing
来源：
Beijing Daxue Xuebao (Ziran Kexue Ban)/Acta Scientiarum Naturalium Universitatis Pekinensis | 2019年 / 55卷 / 06期
关键词：
Building extraction; Deep neural network; Instance segmentation; Multitask learning;
D O I：
10.13209/j.0479-8023.2019.106
中图分类号：
学科分类号：
摘要：
At present, building extraction from high-resolution remote sensing images using deep neural network is viewed as a binary classification problem, which divides the pixels into two categories, building and non-building, but it cannot distinguish individual buildings. To solve this problem, the U-Net modified with Xception module and multitask learning are combined to apply to the instance segmentation of buildings, which both acquires the binary classification and distinguishes the individual buildings. Inria aerial imagery is used as the research dataset to validate the algorithm. The results show that the binary classification performance of U-Net modified with Xception outperforms U-Net by about 1.4%. The multitask driven deep neural network not only accomplishes the instance segmentation of buildings, but also improves the accuracy by about 0.5%. © 2019 Peking University.
引用
收藏
页码：1067 / 1077
页数：10
相关论文
共 28 条
  • [1] Szegedy C., Liu W., Jia Y., Et al., Going deeper with convolutions, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-9, (2015)
  • [2] Krizhevsky A., Sutskever I., Hinton G.E., Imagenet classification with deep convolutional neural networks, Advances in Neural Information Processing Systems, pp. 1097-1105, (2012)
  • [3] Mnih V., Machine learning for aerial image labeling, (2013)
  • [4] Alshehhi R., Marpu P.R., Woon W.L., Et al., Simulta-neous extraction of roads and buildings in remote sensing imagery with convolutional neural networks, ISPRS Journal of Photogrammetry and Remote Sensing, 130, pp. 139-149, (2017)
  • [5] Maggiori E., Tarabalka Y., Charpiat G., Et al., Convolu-tional neural networks for large-scale remote-sensing image classification, IEEE Transactions on Geosci-ence and Remote Sensing, 55, 2, pp. 645-657, (2017)
  • [6] Huang Z., Cheng G., Wang H., Et al., Building extraction from multi-source remote sensing images via deep de-convolution neural networks, Geoscience and Remote Sensing Symposium (IGARSS), 2016 IEEE International, pp. 1835-1838, (2016)
  • [7] Long J., Shelhamer E., Darrell T., Fully convolutional networks for semantic segmentation, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431-3440, (2015)
  • [8] Wu G., Shao X., Guo Z., Et al., Automatic building segmentation of aerial imagery using multi-constraint fully convolutional networks, Remote Sensing, 10, 3, (2018)
  • [9] Ronneberger O., Fischer P., Brox T., U-Net: convolu-tional networks for biomedical image segmentation, Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 234-241, (2015)
  • [10] Audebert N., Le Saux B., Lefevre S., Semantic segmen-tation of earth observation data using multimodal and multi-scale deep networks, Asian Conference on Computer Vision, pp. 180-196, (2016)
123