Shared more. Cited more. Safe forever.
    • advanced search
    • submit works
    • about
    • help
    • contact us
    • login
    View Item 
    •   MOspace Home
    • University of Missouri System
    • Missouri Summits
    • Missouri Regional Life Sciences Summit 2010
    • Abstracts (Missouri Regional Life Sciences Summit 2010)
    • View Item
    •   MOspace Home
    • University of Missouri System
    • Missouri Summits
    • Missouri Regional Life Sciences Summit 2010
    • Abstracts (Missouri Regional Life Sciences Summit 2010)
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.
    advanced searchsubmit worksabouthelpcontact us

    Browse

    All of MOspaceCommunities & CollectionsDate IssuedAuthor/ContributorTitleIdentifierThesis DepartmentThesis AdvisorThesis SemesterThis CollectionDate IssuedAuthor/ContributorTitleIdentifierThesis DepartmentThesis AdvisorThesis Semester

    Statistics

    Most Popular ItemsStatistics by CountryMost Popular AuthorsStatistics by Referrer

    Motion Tracking for Smart Home Care

    Moiz, Fahad
    Leon-Salas, Walter D. (Walter Daniel)
    Lee, Yugyung, 1960-
    View/Open
    [PDF] MotionTrackingSmartHomeCare[abstract].pdf (20.42Kb)
    [PDF] MotionTrackingSmartHomeCare.pdf (395.8Kb)
    Date
    2010-03
    Contributor
    University of Missouri (System)
    Format
    Poster
    Metadata
    [+] Show full item record
    Abstract
    Human body motion capture has a wide range of applications and is being extensively investigated. Areas of application include virtual and augmented reality, biomechanics, sign language translation, gait analysis and graphics in movies and video games. The goal of this work is to develop an electronic device to translate arms motion and hand gestures into computer commands for smart home applications. This device is expected to improve the communication and lifestyle of elderly and disable people. We envision a device that is wearable, seamless and easy to use. Current state-of-the-art body motion capture employs high-speed and high-resolution cameras. Although this method is accurate and useful in laboratory settings, it requires the user to be inside the field of view of the cameras, a condition that is not always feasible during everyday activities. Instead, our approach relies on small sensors nodes that are worn on the wrists and around the waist. Inertial sensors such as accelerometers and gyroscopes have been employed before to develop wearable motion-tracking sensors due to their small size. However, they suffer from drift which causes the position estimations to have large errors. Ultrasonic sensors have also been employed to track motion. Although more accurate, ultrasonic sensors are affected by intermittent signal blockage produced by the body. Our approach is to combine these two sensing modalities in a way that the position estimation error is reduced. To that end, the outputs of the inertial and ultrasonic sensors are fused using a Kalman filter. The sensor nodes implement a multilateration algorithm that calculates the position of body-mounted sensors by measuring the time of travel of ultrasound bursts traveling between the sensor nodes. An electronic board for the sensor nodes have been designed, fabricated and programmed. The board measures 3.2 cm x 4.8 cm and includes a low-power microcontroller, a radio unit, a three-axis accelerometer, a two-axis gyroscope, an ultrasonic transmitter and an ultrasonic receiver. Our ongoing activities include the development of a 3D virtual simulation of a smart home. In the virtual smart home, various electronic devices such as computers, cell phones and household appliances like microwaves and televisions are networked for ubiquitous services. The wearable sensors capture the limb movements and relay this data to a central controller where it is interpreted to adjust the home environment. The sensors can also be used for emergency care by detecting any abnormal movements. Our approach will significantly improve current motion capture systems that are too cumbersome to wear or require the subject to be confined to a controlled environment or within the view range of the camera. Besides their use in smart home scenarios, the proposed wearable motion-tracking sensors can be used in biomechanic studies, virtual reality and interactive games.
    URI
    http://hdl.handle.net/10355/6321
    Part of
    Abstracts (Missouri Regional Life Sciences Summit 2010)
    Collections
    • Posters (Missouri Regional Life Sciences Summit 2010)
    • Abstracts (Missouri Regional Life Sciences Summit 2010)
    • Computer Science and Electrical Engineering Presentations (UMKC)

    Send Feedback
    hosted by University of Missouri Library Systems
     

     


    Send Feedback
    hosted by University of Missouri Library Systems