BuildMapper: A Fully Learnable Framework for Vectorized Building Contour Extraction
Preprint
Abstract
Deep learning based methods have significantly boosted the study of automatic building extraction from remote sensing images. However, delineating vectorized and regular building contours like a human does remains very challenging, due to the difficulty of the methodology, the diversity of building structures, and the imperfect imaging conditions. In this paper, we propose the first end-to-end learnable building contour extraction framework, named BuildMapper, which can directly and efficiently delineate building polygons just as a human does. BuildMapper consists of two main components: 1) a contour initialization module that generates initial building contours; and 2) a contour evolution module that performs both contour vertex deformation and reduction, which removes the need for complex empirical post-processing used in existing methods. In both components, we provide new ideas, including a learnable contour initialization method to replace the empirical methods, dynamic predicted and ground truth vertex pairing for the static vertex correspondence problem, and a lightweight encoder for vertex information extraction and aggregation, which benefit a general contour-based method; and a well-designed vertex classification head for building corner vertices detection, which casts light on direct structured building contour extraction. We also built a suitable large-scale building dataset, the WHU-Mix (vector) building dataset, to benefit the study of contour-based building extraction methods. The extensive experiments conducted on the WHU-Mix (vector) dataset, the WHU dataset, and the CrowdAI dataset verified that BuildMapper can achieve a state-of-the-art performance, with a higher mask average precision (AP) and boundary AP than both segmentation-based and contour-based methods.Keywords
All Related Versions
This publication has 30 references indexed in Scilit:
- Sparse Instance Activation for Real-Time Instance Segmentation2022
- E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation2022
- High-resolution population estimation using household survey data and building footprintsNature Communications, 2022
- Building outline delineation: From aerial images to polygons with an improved end-to-end learning frameworkISPRS Journal of Photogrammetry and Remote Sensing, 2021
- An end-to-end shape modeling framework for vectorized building outline generation from aerial imagesISPRS Journal of Photogrammetry and Remote Sensing, 2020
- A scale robust convolutional neural network for automatic building extraction from aerial and satellite imageryInternational Journal of Remote Sensing, 2018
- Microsoft COCO: Common Objects in Context2014
- Automated detection of buildings from single VHR multispectral images using shadow information and graph cutsISPRS Journal of Photogrammetry and Remote Sensing, 2013
- Active contours without edgesIEEE Transactions on Image Processing, 2001
- Snakes: Active contour modelsInternational Journal of Computer Vision, 1988