Simultaneous extraction of roads and buildings in remote sensing imagery with convolutional neural networks

Rasha Alshehhi, Prashanth Reddy Marpu, Wei Lee Woon, Mauro Dalla Mura

    Research output: Contribution to journalArticle

    Abstract

    Extraction of man-made objects (e.g., roads and buildings) from remotely sensed imagery plays an important role in many urban applications (e.g., urban land use and land cover assessment, updating geographical databases, change detection, etc). This task is normally difficult due to complex data in the form of heterogeneous appearance with large intra-class and lower inter-class variations. In this work, we propose a single patch-based Convolutional Neural Network (CNN) architecture for extraction of roads and buildings from high-resolution remote sensing data. Low-level features of roads and buildings (e.g., asymmetry and compactness) of adjacent regions are integrated with Convolutional Neural Network (CNN) features during the post-processing stage to improve the performance. Experiments are conducted on two challenging datasets of high-resolution images to demonstrate the performance of the proposed network architecture and the results are compared with other patch-based network architectures. The results demonstrate the validity and superior performance of the proposed network architecture for extracting roads and buildings in urban areas.

    Original languageEnglish (US)
    Pages (from-to)139-149
    Number of pages11
    JournalISPRS Journal of Photogrammetry and Remote Sensing
    Volume130
    DOIs
    StatePublished - Aug 1 2017

    Fingerprint

    Network architecture
    roads
    imagery
    neural network
    remote sensing
    Remote sensing
    building
    road
    Neural networks
    performance
    image resolution
    Image resolution
    change detection
    Land use
    asymmetry
    land use
    high resolution
    void ratio
    land cover
    urban area

    Keywords

    • Adjacent regions
    • Convolutional neural network
    • Extraction
    • Low-level features

    ASJC Scopus subject areas

    • Geography, Planning and Development
    • Atomic and Molecular Physics, and Optics
    • Engineering (miscellaneous)
    • Computer Science Applications
    • Computers in Earth Sciences

    Cite this

    Simultaneous extraction of roads and buildings in remote sensing imagery with convolutional neural networks. / Alshehhi, Rasha; Marpu, Prashanth Reddy; Woon, Wei Lee; Mura, Mauro Dalla.

    In: ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 130, 01.08.2017, p. 139-149.

    Research output: Contribution to journalArticle

    Alshehhi, Rasha ; Marpu, Prashanth Reddy ; Woon, Wei Lee ; Mura, Mauro Dalla. / Simultaneous extraction of roads and buildings in remote sensing imagery with convolutional neural networks. In: ISPRS Journal of Photogrammetry and Remote Sensing. 2017 ; Vol. 130. pp. 139-149.
    @article{93430dc6439c4f4d95776af9d1a4ce88,
    title = "Simultaneous extraction of roads and buildings in remote sensing imagery with convolutional neural networks",
    abstract = "Extraction of man-made objects (e.g., roads and buildings) from remotely sensed imagery plays an important role in many urban applications (e.g., urban land use and land cover assessment, updating geographical databases, change detection, etc). This task is normally difficult due to complex data in the form of heterogeneous appearance with large intra-class and lower inter-class variations. In this work, we propose a single patch-based Convolutional Neural Network (CNN) architecture for extraction of roads and buildings from high-resolution remote sensing data. Low-level features of roads and buildings (e.g., asymmetry and compactness) of adjacent regions are integrated with Convolutional Neural Network (CNN) features during the post-processing stage to improve the performance. Experiments are conducted on two challenging datasets of high-resolution images to demonstrate the performance of the proposed network architecture and the results are compared with other patch-based network architectures. The results demonstrate the validity and superior performance of the proposed network architecture for extracting roads and buildings in urban areas.",
    keywords = "Adjacent regions, Convolutional neural network, Extraction, Low-level features",
    author = "Rasha Alshehhi and Marpu, {Prashanth Reddy} and Woon, {Wei Lee} and Mura, {Mauro Dalla}",
    year = "2017",
    month = "8",
    day = "1",
    doi = "10.1016/j.isprsjprs.2017.05.002",
    language = "English (US)",
    volume = "130",
    pages = "139--149",
    journal = "ISPRS Journal of Photogrammetry and Remote Sensing",
    issn = "0924-2716",
    publisher = "Elsevier",

    }

    TY - JOUR

    T1 - Simultaneous extraction of roads and buildings in remote sensing imagery with convolutional neural networks

    AU - Alshehhi, Rasha

    AU - Marpu, Prashanth Reddy

    AU - Woon, Wei Lee

    AU - Mura, Mauro Dalla

    PY - 2017/8/1

    Y1 - 2017/8/1

    N2 - Extraction of man-made objects (e.g., roads and buildings) from remotely sensed imagery plays an important role in many urban applications (e.g., urban land use and land cover assessment, updating geographical databases, change detection, etc). This task is normally difficult due to complex data in the form of heterogeneous appearance with large intra-class and lower inter-class variations. In this work, we propose a single patch-based Convolutional Neural Network (CNN) architecture for extraction of roads and buildings from high-resolution remote sensing data. Low-level features of roads and buildings (e.g., asymmetry and compactness) of adjacent regions are integrated with Convolutional Neural Network (CNN) features during the post-processing stage to improve the performance. Experiments are conducted on two challenging datasets of high-resolution images to demonstrate the performance of the proposed network architecture and the results are compared with other patch-based network architectures. The results demonstrate the validity and superior performance of the proposed network architecture for extracting roads and buildings in urban areas.

    AB - Extraction of man-made objects (e.g., roads and buildings) from remotely sensed imagery plays an important role in many urban applications (e.g., urban land use and land cover assessment, updating geographical databases, change detection, etc). This task is normally difficult due to complex data in the form of heterogeneous appearance with large intra-class and lower inter-class variations. In this work, we propose a single patch-based Convolutional Neural Network (CNN) architecture for extraction of roads and buildings from high-resolution remote sensing data. Low-level features of roads and buildings (e.g., asymmetry and compactness) of adjacent regions are integrated with Convolutional Neural Network (CNN) features during the post-processing stage to improve the performance. Experiments are conducted on two challenging datasets of high-resolution images to demonstrate the performance of the proposed network architecture and the results are compared with other patch-based network architectures. The results demonstrate the validity and superior performance of the proposed network architecture for extracting roads and buildings in urban areas.

    KW - Adjacent regions

    KW - Convolutional neural network

    KW - Extraction

    KW - Low-level features

    UR - http://www.scopus.com/inward/record.url?scp=85020312124&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85020312124&partnerID=8YFLogxK

    U2 - 10.1016/j.isprsjprs.2017.05.002

    DO - 10.1016/j.isprsjprs.2017.05.002

    M3 - Article

    VL - 130

    SP - 139

    EP - 149

    JO - ISPRS Journal of Photogrammetry and Remote Sensing

    JF - ISPRS Journal of Photogrammetry and Remote Sensing

    SN - 0924-2716

    ER -