Energy-efficient aquatic environment monitoring using smartphone-based robots

Yu Wang, Rui Tan, Guoliang Xing, Jianxun Wang, Xiaobo Tan, Xiaoming Liu

    Research output: Research - peer-reviewArticle

    Abstract

    Monitoring aquatic environment is of great interest to the ecosystem, marine life, and human health. This article presents the design and implementation of Samba-an aquatic surveillance robot that integrates an off-the-shelf Android smartphone and a robotic fish to monitor harmful aquatic processes such as oil spills and harmful algal blooms. Using the built-in camera of the smartphone, Samba can detect spatially dispersed aquatic processes in dynamic and complex environment. To reduce the excessive false alarms caused by the nonwater area (e.g., trees on the shore), Samba segments the captured images and performs target detection in the identified water area only. However, a major challenge in the design of Samba is the high energy consumption resulted from continuous image segmentation. We propose a novel approach that leverages the power-efficient inertial sensors on smartphones to assist image processing. In particular, based on the learned mapping models between inertial and visual features, Samba uses real-time inertial sensor readings to estimate the visual features that guide image segmentation, significantly reducing the energy consumption and computation overhead. Samba also features a set of lightweight and robust computer vision algorithms, which detect harmful aquatic processes based on their distinctive color features. Last, Samba employs a feedback-based rotation control algorithm to adapt to spatiotemporal development of the target aquatic process. We have implemented a Samba prototype and evaluated it through extensive field experiments, lab experiments, and trace-driven simulations. The results show that Samba can achieve a 94% detection rate, a 5% false alarm rate, and a lifetime up to nearly 2 months.

    LanguageEnglish (US)
    Article number25
    JournalACM Transactions on Sensor Networks
    Volume12
    Issue number3
    DOIs
    StatePublished - Jul 1 2016

    Profile

    Smartphones
    Robots
    Monitoring
    Image segmentation
    Energy utilization
    Sensors
    Experiments
    Aquatic ecosystems
    Oil spills
    Target tracking
    Fish
    Computer vision
    Robotics
    Image processing
    Cameras
    Health
    Color
    Feedback
    Water
    Android (operating system)

    Keywords

    • Computer vision
    • Inertial sensing
    • Object detection
    • Robotic sensor
    • Smartphone

    ASJC Scopus subject areas

    • Computer Networks and Communications

    Cite this

    Energy-efficient aquatic environment monitoring using smartphone-based robots. / Wang, Yu; Tan, Rui; Xing, Guoliang; Wang, Jianxun; Tan, Xiaobo; Liu, Xiaoming.

    In: ACM Transactions on Sensor Networks, Vol. 12, No. 3, 25, 01.07.2016.

    Research output: Research - peer-reviewArticle

    @article{22afd1187e89478eabba2e1fb6616214,
    title = "Energy-efficient aquatic environment monitoring using smartphone-based robots",
    abstract = "Monitoring aquatic environment is of great interest to the ecosystem, marine life, and human health. This article presents the design and implementation of Samba-an aquatic surveillance robot that integrates an off-the-shelf Android smartphone and a robotic fish to monitor harmful aquatic processes such as oil spills and harmful algal blooms. Using the built-in camera of the smartphone, Samba can detect spatially dispersed aquatic processes in dynamic and complex environment. To reduce the excessive false alarms caused by the nonwater area (e.g., trees on the shore), Samba segments the captured images and performs target detection in the identified water area only. However, a major challenge in the design of Samba is the high energy consumption resulted from continuous image segmentation. We propose a novel approach that leverages the power-efficient inertial sensors on smartphones to assist image processing. In particular, based on the learned mapping models between inertial and visual features, Samba uses real-time inertial sensor readings to estimate the visual features that guide image segmentation, significantly reducing the energy consumption and computation overhead. Samba also features a set of lightweight and robust computer vision algorithms, which detect harmful aquatic processes based on their distinctive color features. Last, Samba employs a feedback-based rotation control algorithm to adapt to spatiotemporal development of the target aquatic process. We have implemented a Samba prototype and evaluated it through extensive field experiments, lab experiments, and trace-driven simulations. The results show that Samba can achieve a 94% detection rate, a 5% false alarm rate, and a lifetime up to nearly 2 months.",
    keywords = "Computer vision, Inertial sensing, Object detection, Robotic sensor, Smartphone",
    author = "Yu Wang and Rui Tan and Guoliang Xing and Jianxun Wang and Xiaobo Tan and Xiaoming Liu",
    year = "2016",
    month = "7",
    doi = "10.1145/2932190",
    volume = "12",
    journal = "ACM Transactions on Sensor Networks",
    issn = "1550-4859",
    publisher = "Association for Computing Machinery (ACM)",
    number = "3",

    }

    TY - JOUR

    T1 - Energy-efficient aquatic environment monitoring using smartphone-based robots

    AU - Wang,Yu

    AU - Tan,Rui

    AU - Xing,Guoliang

    AU - Wang,Jianxun

    AU - Tan,Xiaobo

    AU - Liu,Xiaoming

    PY - 2016/7/1

    Y1 - 2016/7/1

    N2 - Monitoring aquatic environment is of great interest to the ecosystem, marine life, and human health. This article presents the design and implementation of Samba-an aquatic surveillance robot that integrates an off-the-shelf Android smartphone and a robotic fish to monitor harmful aquatic processes such as oil spills and harmful algal blooms. Using the built-in camera of the smartphone, Samba can detect spatially dispersed aquatic processes in dynamic and complex environment. To reduce the excessive false alarms caused by the nonwater area (e.g., trees on the shore), Samba segments the captured images and performs target detection in the identified water area only. However, a major challenge in the design of Samba is the high energy consumption resulted from continuous image segmentation. We propose a novel approach that leverages the power-efficient inertial sensors on smartphones to assist image processing. In particular, based on the learned mapping models between inertial and visual features, Samba uses real-time inertial sensor readings to estimate the visual features that guide image segmentation, significantly reducing the energy consumption and computation overhead. Samba also features a set of lightweight and robust computer vision algorithms, which detect harmful aquatic processes based on their distinctive color features. Last, Samba employs a feedback-based rotation control algorithm to adapt to spatiotemporal development of the target aquatic process. We have implemented a Samba prototype and evaluated it through extensive field experiments, lab experiments, and trace-driven simulations. The results show that Samba can achieve a 94% detection rate, a 5% false alarm rate, and a lifetime up to nearly 2 months.

    AB - Monitoring aquatic environment is of great interest to the ecosystem, marine life, and human health. This article presents the design and implementation of Samba-an aquatic surveillance robot that integrates an off-the-shelf Android smartphone and a robotic fish to monitor harmful aquatic processes such as oil spills and harmful algal blooms. Using the built-in camera of the smartphone, Samba can detect spatially dispersed aquatic processes in dynamic and complex environment. To reduce the excessive false alarms caused by the nonwater area (e.g., trees on the shore), Samba segments the captured images and performs target detection in the identified water area only. However, a major challenge in the design of Samba is the high energy consumption resulted from continuous image segmentation. We propose a novel approach that leverages the power-efficient inertial sensors on smartphones to assist image processing. In particular, based on the learned mapping models between inertial and visual features, Samba uses real-time inertial sensor readings to estimate the visual features that guide image segmentation, significantly reducing the energy consumption and computation overhead. Samba also features a set of lightweight and robust computer vision algorithms, which detect harmful aquatic processes based on their distinctive color features. Last, Samba employs a feedback-based rotation control algorithm to adapt to spatiotemporal development of the target aquatic process. We have implemented a Samba prototype and evaluated it through extensive field experiments, lab experiments, and trace-driven simulations. The results show that Samba can achieve a 94% detection rate, a 5% false alarm rate, and a lifetime up to nearly 2 months.

    KW - Computer vision

    KW - Inertial sensing

    KW - Object detection

    KW - Robotic sensor

    KW - Smartphone

    UR - http://www.scopus.com/inward/record.url?scp=84979915841&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84979915841&partnerID=8YFLogxK

    U2 - 10.1145/2932190

    DO - 10.1145/2932190

    M3 - Article

    VL - 12

    JO - ACM Transactions on Sensor Networks

    T2 - ACM Transactions on Sensor Networks

    JF - ACM Transactions on Sensor Networks

    SN - 1550-4859

    IS - 3

    M1 - 25

    ER -