The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLIII-B2-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B2-2020, 731–735, 2020
https://doi.org/10.5194/isprs-archives-XLIII-B2-2020-731-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B2-2020, 731–735, 2020
https://doi.org/10.5194/isprs-archives-XLIII-B2-2020-731-2020

  12 Aug 2020

12 Aug 2020

BUILDING OUTLINE DELINEATION: FROM VERY HIGH RESOLUTION REMOTE SENSING IMAGERY TO POLYGONS WITH AN IMPROVED END-TO-END LEARNING FRAMEWORK

W. Zhao, I. Ivanov, C. Persello, and A. Stein W. Zhao et al.
  • Dept. of Earth Observation Science, ITC, University of Twente, Enschede, The Netherlands

Keywords: Building Outline Delineation, Polygon Prediction, Convolutional Neural Networks, Recurrent Neural Networks

Abstract. Deep learning methods based on Fully convolution networks (FCNs) have shown an impressive progress in building outline delineation from very high resolution (VHR) remote sensing (RS) imagery. Common issues still exist in extracting precise building shapes and outlines, often resulting in irregular edges and over smoothed corners. In this paper, we use PolyMapper, a recently introduced deep-learning framework that is able to predict object outlines in a vector representation directly. We have introduced two main modifications to this baseline method. First, we introduce EffcientNet as backbone feature encoder to our network, which uses compound coefficient to scale up all dimensions of depth/width/resolution uniformly, to improve the processing speed with fewer parameters. Second, we integrate a boundary refinement block (BRB) to strengthen the boundary feature learning and to further improve the accuracy of corner prediction. The results demonstrate that the end-to-end learnable model is capable of delineating polygons of building outlines that closely approximate the structure of reference labels. Experiments on the crowdAI building instance segmentation datasets show that our model outperforms PolyMapper in all COCO metrics, for instance showing a 0.13 higher mean Average Precision (AP) value and a 0.60 higher mean Average Recall value. Also qualitative results show that our method segments building instances of various shapes more accurately.