Journal
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
Volume 151, Issue -, Pages 91-105Publisher
ELSEVIER
DOI: 10.1016/j.isprsjprs.2019.02.019
Keywords
Building extraction; Deep learning; Convolutional neural networks; Image classification; Semantic segmentation
Categories
Funding
- National Natural Science Foundation of China [41431178, 41801351, 41671453, 41875122]
- Natural Science Foundation of Guangdong Province, China [2016A030311016]
- National Administration of Surveying, Mapping and Geoinformation of China [GZIT2016-A5-147]
- Research Institute of Henan Spatio-Temporal Big Data Industrial Technology [2017DJA001]
- Key Projects for Young Teachers at Sun Yat-sen University [171gzd02]
Ask authors/readers for more resources
Automated extraction of buildings from remotely sensed data is important for a wide range of applications but challenging due to difficulties in extracting semantic features from complex scenes like urban areas. The recently developed fully convolutional neural networks (FCNs) have shown to perform well on urban object extraction because of the outstanding feature learning and end-to-end pixel labeling abilities. The commonly used feature fusion or skip-connection refine modules of FCNs often overlook the problem of feature selection and could reduce the learning efficiency of the networks. In this paper, we develop an end-to-end trainable gated residual refinement network (GRRNet) that fuses high-resolution aerial images and LiDAR point clouds for building extraction. The modified residual learning network is applied as the encoder part of GRRNet to learn multi-level features from the fusion data and a gated feature labeling (GFL) unit is introduced to reduce unnecessary feature transmission and refine classification results. The proposed model - GRRNet is tested in a publicly available dataset with urban and suburban scenes. Comparison results illustrated that GRRNet has competitive building extraction performance in comparison with other approaches. The source code of the developed GRRNet is made publicly available for studies.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available