BEGIN:VCALENDAR VERSION:2.0 PRODID:Linklings LLC BEGIN:VTIMEZONE TZID:Australia/Melbourne X-LIC-LOCATION:Australia/Melbourne BEGIN:DAYLIGHT TZOFFSETFROM:+1000 TZOFFSETTO:+1100 TZNAME:AEDT DTSTART:19721003T020000 RRULE:FREQ=YEARLY;BYMONTH=4;BYDAY=1SU END:DAYLIGHT BEGIN:STANDARD DTSTART:19721003T020000 TZOFFSETFROM:+1100 TZOFFSETTO:+1000 TZNAME:AEST RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=1SU END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20240214T070248Z LOCATION:Meeting Room C4.8\, Level 4 (Convention Centre) DTSTART;TZID=Australia/Melbourne:20231214T151500 DTEND;TZID=Australia/Melbourne:20231214T152500 UID:siggraphasia_SIGGRAPH Asia 2023_sess158_papers_588@linklings.com SUMMARY:Hand Pose Estimation with Mems-Ultrasonic Sensors DESCRIPTION:Technical Papers\n\nQiang Zhang, Yuanqiao Lin, Yubin Lin, and Szymon Rusinkiewicz (Princeton University)\n\nHand tracking is an importan t aspect of human-computer interaction and has a wide range of application s in extended reality devices. However, current hand motion capture method s suffer from various limitations. For instance, visual-based hand pose es timation is susceptible to self-occlusion and changes in lighting conditio ns, while IMU-based tracking gloves experience significant drift and are n ot resistant to external magnetic field interference. To address these iss ues, we propose a novel and low-cost hand-tracking glove that utilizes sev eral MEMS-ultrasonic sensors attached to the fingers, to measure the dista nce matrix among the sensors. Our lightweight deep network then reconstruc ts the hand pose from the distance matrix. Our experimental results demons trate that this approach is both accurate, size-agnostic, and robust to ex ternal interference. We also show the design logic for the sensor selectio n, sensor configurations, circuit diagram, as well as model architecture.\ n\nRegistration Category: Full Access\n\nSession Chair: Jae-Ho Nah (Sangmy ung University) URL:https://asia.siggraph.org/2023/full-program?id=papers_588&sess=sess158 END:VEVENT END:VCALENDAR