MSBR-GNet: A High-Resolution Imagery Generative Optimization Model for Building Rooftop Boundary Guided by Interpretable Statistical Model in Spatial and Spectral Domain
Open Access
- 28 March 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17 (19391404) , 8164-8188
Abstract
Automated extraction of building rooftop information is of great significance in remote sensing of land resources and other related applications. In this paper, a building roof boundary generating optimization model called multi-scale boundary regulation generative net (MSBR-GNet), guided by interpretability statistical model in the spatial and spectral domains, is proposed to solve the problem of inaccurate boundary segmentation caused by mixed pixel transition region of remote sensing images. Incorporate the boundary loss function guided by statistical models in the spatial and spectral domains into the generator loss calculation of MSBR-GNet, precisely constrain the regularized generation of building rooftop contours by interpretable mechanism. The experiments show that MSBR-GNet can extract more regular building rooftop contours, and the precision values in the INRIA, WHU and Massachusetts public datasets reached 0.9275, 0.9228 and 0.8779, respectively, which can ensure the accuracy of building extraction while achieving optimal results in the boundary morphology evaluation index. The code of this paper is open source at https://github.com/GHLJH/MSBR-GNet .Keywords
Funding Information
- Beijing Key Laboratory of Urban Spatial Information Engineering
- Beijing Institute of Surveying and Mapping Design (20220112)
- Beijing Association of Higher Education (ZD202244)
- Beijing University of Civil Engineering and Architecture Education Scientific Research (Y2111)
This publication has 38 references indexed in Scilit:
- MS-CNN: multiscale recognition of building rooftops from high spatial resolution remote sensing imageryInternational Journal of Remote Sensing, 2022
- Corner Proposal Network for Anchor-Free, Two-Stage Object Detection2020
- Boundary Loss for Remote Sensing Imagery Semantic Segmentation2019
- Scale computation on high spatial resolution remotely sensed imagery multi-scale segmentationInternational Journal of Remote Sensing, 2017
- SSD: Single Shot MultiBox Detector2016
- Building extraction in satellite images using active contours and colour featuresInternational Journal of Remote Sensing, 2016
- What is an object?2010
- Expert system classification of urban land use/cover for Delhi, IndiaInternational Journal of Remote Sensing, 2008
- Rapid object detection using a boosted cascade of simple features2005
- Histograms of Oriented Gradients for Human Detection2005