ROOF SUPERSTRUCTURE DETECTION FROM AERIAL IMAGERY

被引：2

作者：

Li, Qingyu ^{[1
]}

Krapf, Sebastian ^{[2
]}

Mou, Lichao ^{[1
]}

Shi, Yilei ^{[3
]}

Zhu, Xiao Xiang ^{[1
]}

机构：

[1] Tech Univ Munich TUM, Data Sci Earth Observat, Munich, Germany

[2] Tech Univ Munich TUM, Inst Automot Technol, Munich, Germany

[3] Tech Univ Munich TUM, Remote Sensing Technol, Munich, Germany

来源：

IGARSS 2023 - 2023 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM | 2023年

关键词：

roof superstructures; semantic segmentation; multi-task learning; aerial imagery;

D O I：

10.1109/IGARSS52108.2023.10283139

中图分类号：

P [天文学、地球科学];

学科分类号：

07 ;

摘要：

Identifying suitable building roofs for the installation of photovoltaic (PV) systems is important to sustainable energy planning. However, most existing approaches neglect roof superstructures that can obstruct the installation of PV systems. In this research, we propose a novel method, which can help to deal with this issue by detecting roof superstructures from aerial imagery. Considering that semantic information about roof masks is also informative, we propose to first learns roof segmentation maps that are further used to learn roof superstructure maps. Experiments are conducted on Roof Information Dataset (RID). Our method outperforms the state-of-the-art methods both quantitatively and qualitatively.

引用

页码：6855 / 6858

页数：4

共 11 条

[1] Eff-UNet: A Novel Architecture for Semantic Segmentation in Unstructured Environment [J].

Baheti, Bhakti ;

Innani, Shubham ;

Gajre, Suhas ;

Talbar, Sanjay .

2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW 2020), 2020, :1473-1481

[2] DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs [J].

Chen, Liang-Chieh ;

Papandreou, George ;

Kokkinos, Iasonas ;

Murphy, Kevin ;

Yuille, Alan L. .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2018, 40 (04) :834-848

[3] Building Roof Segmentation from Aerial Images Using a Line-and Region-Based Watershed Segmentation Technique [J].

El Merabet, Youssef ;

Meurie, Cyril ;

Ruichek, Yassine ;

Sbihi, Abderrahmane ;

Touahni, Raja .

SENSORS, 2015, 15 (02) :3172-3203

[4] Deep Residual Learning for Image Recognition [J].

He, Kaiming ;

Zhang, Xiangyu ;

Ren, Shaoqing ;

Sun, Jian .

2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778

[5] The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation [J].

Jegou, Simon ;

Drozdzal, Michal ;

Vazquez, David ;

Romero, Adriana ;

Bengio, Yoshua .

2017 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW), 2017, :1175-1183

[6] RID-Roof Information Dataset for Computer Vision-Based Photovoltaic Potential Assessment [J].

Krapf, Sebastian ;

Bogenrieder, Lukas ;

Netzler, Fabian ;

Balke, Georg ;

Lienkamp, Markus .

REMOTE SENSING, 2022, 14 (10)

[7] SolarNet: A convolutional neural network-based framework for rooftop solar potential estimation from aerial imagery [J].

Li, Qingyu ;

Krapf, Sebastian ;

Shi, Yilei ;

Zhu, Xiao Xiang .

INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION, 2023, 116

[8] Assessment of rooftop photovoltaic potentials at the urban level using publicly available geodata and image recognition techniques [J].

Mainzer, Kai ;

Killinger, Sven ;

McKenn, Russell ;

Fichtner, Wolf .

SOLAR ENERGY, 2017, 155 :561-573

[9] U-Net: Convolutional Networks for Biomedical Image Segmentation [J].

Ronneberger, Olaf ;

Fischer, Philipp ;

Brox, Thomas .

MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION, PT III, 2015, 9351 :234-241

[10]

Zhang AG, 2018, CHIN CONT DECIS CONF, P801, DOI 10.1109/CCDC.2018.8407240

← 1 2 →