Deep Cascade Road Extraction Network:a Multi-task Method for Road Extraction

• Item type: SIG Technical Reports(1)
• 公開日: 2022-03-03
• タイトル: Deep Cascade Road Extraction Network:a Multi-task Method for Road Extraction
• タイトル / 言語: en
• タイトル: Deep Cascade Road Extraction Network:a Multi-task Method for Road Extraction
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: セッション1-A
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_18gh
• 資源タイプ: technical report
• 著者所属: Faculty of Engineering, Waseda University
• 著者所属: NTT Network Technologies Laboratories, NTT Corporation
• 著者所属: NTT Network Technologies Laboratories, NTT Corporation
• 著者所属: NTT Network Technologies Laboratories, NTT Corporation
• 著者所属: Japan Aerospace Exploration Agency
• 著者所属: Faculty of Engineering, Waseda University
• 著者所属(英): en
• 著者所属(英): Faculty of Engineering, Waseda University
• 著者所属(英): en
• 著者所属(英): NTT Network Technologies Laboratories, NTT Corporation
• 著者所属(英): en
• 著者所属(英): NTT Network Technologies Laboratories, NTT Corporation
• 著者所属(英): en
• 著者所属(英): NTT Network Technologies Laboratories, NTT Corporation
• 著者所属(英): en
• 著者所属(英): Japan Aerospace Exploration Agency
• 著者所属(英): en
• 著者所属(英): Faculty of Engineering, Waseda University
• 著者名: Yubo, Wang; Zhao, Wang; Yuusuke, Nakano; Ken, Nishimatsu; Katsuya, Hasegawa; Jun, Ohya
• 著者名(英): Yubo, Wang; Zhao, Wang; Yuusuke, Nakano; Ken, Nishimatsu; Katsuya, Hasegawa; Jun, Ohya
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: In this work, we present an end-to-end cascade neural network model called Deep Cascade Road Extraction Network to extract accurate road networks from aerial imagery. On the basis of the cascade structure consisting of three subnetworks (Surface Segmentation Network, Edge Detection Network, and Centreline Extraction Network) connected in a cascade manner, we simultaneously achieve the three tasks of the subnetworks for road extraction. Through comparison experiments, our method achieves state-of-the-art results for all the three subtasks. Meanwhile, our model demonstrates strong robustness to occlusions while accurately extracting complex road areas.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: In this work, we present an end-to-end cascade neural network model called Deep Cascade Road Extraction Network to extract accurate road networks from aerial imagery. On the basis of the cascade structure consisting of three subnetworks (Surface Segmentation Network, Edge Detection Network, and Centreline Extraction Network) connected in a cascade manner, we simultaneously achieve the three tasks of the subnetworks for road extraction. Through comparison experiments, our method achieves state-of-the-art results for all the three subtasks. Meanwhile, our model demonstrates strong robustness to occlusions while accurately extracting complex road areas.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AA11131797
• 書誌情報: 研究報告コンピュータビジョンとイメージメディア（CVIM）; 巻 2022-CVIM-229, 号 1, p. 1-6, 発行日 2022-03-03
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 2188-8701
• Notice: SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc.
• 出版者 / 言語: ja
• 出版者: 情報処理学会