| Developers: | Cornell University |
| Date of the premiere of the system: | November 2022 |
| Branches: | Pharmaceuticals, Medicine, Healthcare |
2022: Device Announcement
On November 8, 2022, Cornell University unveiled the first-of-its-kind wrist bracelet that tracks the position of the entire body in 3D. The device uses a miniature camera and a specialized deep neural network. The development has great prospects in terms of use in the field of monitoring physical activity.
The BodyTrak is the first wearable device to track the position of the whole body with a single camera. If integrated into future smartwatches, then BodyTrak could be a tipping point in tracking a user's body mechanics under exercise, where accuracy is very important, according to Cheng Zhang, assistant professor of computer science and senior author of the study.
 | With smartwatches already equipped with a camera, a technology like BodyTrak can understand a user's position and provide real-time feedback, Zhang said. This is convenient, accessible and does not limit the area of movement of the user. |  |
The main thing in BodyTrak is not only the camera on the wrist, but also a specially designed neural network behind it. This deep neural network - an artificial intelligence technique that trains a computer to learn from errors - reads rudimentary images or "silhouettes" of the user's body from the camera in motion and virtually recreates 14 body positions in 3D and real time.
| | Our study shows that determining body position does not require the body to be fully in the camera's field of view, "said Hyunchul Lim, a doctoral student in computer science and lead author of the work. If we can capture only a part of our body, then this is already a large amount of information for building a complete reconstruction of the body. | |
According to Zhang and Lim, maintaining privacy for outsiders near a person wearing such a sensor device is a legitimate problem in the development of such technologies. According to them, BodyTrak reduces privacy concerns for outsiders, since the camera is aimed at the user's body and collects only partial images of the user's body.
They also admit that modern smartwatches do not yet have enough small and powerful cameras and enough battery life to integrate full body scans, but this could happen in the future.[1][2]
Notes
| The site content is translated by machine translation software powered by PROMT. The machine-translated articles are not always perfect and may contain errors in vocabulary, syntax or grammar. Read original article If you find inaccuracies or errors in the results of machine translation, please write to editor@tadviser.ru. We will make every effort to correct them as soon as possible. |