{"id":20473,"date":"2020-07-21T15:49:19","date_gmt":"2020-07-21T14:49:19","guid":{"rendered":"https:\/\/www.recantha.co.uk\/blog\/?p=20473"},"modified":"2020-07-21T15:49:19","modified_gmt":"2020-07-21T14:49:19","slug":"3d-hand-sensing-wristband-uses-a-raspberry-pi-for-machine-learning","status":"publish","type":"post","link":"https:\/\/www.recantha.co.uk\/blog\/?p=20473","title":{"rendered":"3D hand-sensing wristband uses a Raspberry Pi for machine learning"},"content":{"rendered":"

\"\"Researchers from Cornell and the University of Wisconsin, Madison, have designed a wrist-mounted device that tracks the entire human hand in 3D. The device (pictured) uses the contours from the wearer’s wrist to create an abstraction of 20 finger joint positions. The FingerTrak bracelet uses low-resolution thermal cameras that read the wrist contours and a tethered Raspberry Pi 4 and machine learning to teach itself what the hand is doing based on these readings.<\/p>\n

Cheng Zhang, assistant professor of information science and director of Cornell\u2019s new\u00a0SciFi Lab<\/a>, where FingerTrak was developed said:<\/p>\n

\u201cThe most novel technical finding in this work is discovering that the contours of the wrist are enough to accurately predict the entire hand posture,\u201d Zhang said. \u201cThis finding allows the reposition of the sensing system to the wrist, which is more practical for usability.\u201d<\/p><\/blockquote>\n

You can purchase the paper written by the team here<\/a> (there is some supplemental material available for free). VentureBeat have covered the story here<\/a> and the Cornell Chronicle covered it here<\/a>. You can view a video<\/a> about the project below:<\/p>\n