[HN Gopher] Wrist-mounted camera captures entire body in 3D
___________________________________________________________________
Wrist-mounted camera captures entire body in 3D
Author : PaulHoule
Score : 30 points
Date : 2022-11-10 18:34 UTC (4 hours ago)
(HTM) web link (news.cornell.edu)
(TXT) w3m dump (news.cornell.edu)
| agarsev wrote:
| The press release contains a few errors and imprecisions. The
| abstract from the scientific article is more informative:
|
| In this paper, we present BodyTrak, an intelligent sensing
| technology that can estimate full body poses on a wristband. It
| only requires one miniature RGB camera to capture the body
| silhouettes, which are learned by a customized deep learning
| model to estimate the 3D positions of 14 joints on arms, legs,
| torso, and head. We conducted a user study with 9 participants in
| which each participant performed 12 daily activities such as
| walking, sitting, or exercising, in varying scenarios (wearing
| different clothes, outdoors/indoors) with a different number of
| camera settings on the wrist. The results show that our system
| can infer the full body pose (3D positions of 14 joints) with an
| average error of 6.9 cm using only one miniature RGB camera
| (11.5mm x 9.5mm) on the wrist pointing towards the body [...].
| chatterhead wrote:
| "BodyTrak is the latest body-sensing system from the SciFiLab..."
|
| Name checks out. This kind of tech isn't going to be used
| primarily in smartwatches it's going to be integrated into state-
| based surveillance.
| Avshalom wrote:
| "State-based" my ass
| https://www.theguardian.com/technology/2018/jan/31/amazon-wa...
| NavinF wrote:
| You can always count on HNers to point out that a neutral
| network designed to run realtime on devices that have a 1 watt-
| hour battery definitely "isn't going to be used primarily in
| smartwatches". The US gov't can't possibly afford to do offline
| pose estimation on a real GPU, am I right?
| system2 wrote:
| I love these extremely boring articles with zero pictures or
| videos.
| genpfault wrote:
| https://matthewdressa.github.io/Personal-Portfolio/assets/pd...
| idiotsecant wrote:
| Thanks for the link!
|
| The camera shots that are shown in that paper are _really_
| restricted in what they can see. How can the model possibly
| estimate the position of an arm that is not visible?
| Corazoor wrote:
| Probably by learning how humans have to balance their
| extremities to remain standing upright. The camera angle
| with respect to the enviroment is likely a factor too,
| since errors got larger when outdoors.
|
| Errors are also not exactly small, ~6cm average, although
| it's more like 1-2 or 5-12, depending on body part. I think
| this would very likely be noticeable in VR applications,
| but it is still very impressive accuracy overall.
|
| The question also nicely highlights the disadvantages of
| trained algorithms: No one knows for sure, and it certainly
| isn't obvious by looking at the network weights...
|
| On the other hand, when looking at the pictures, I felt
| like the authors: There should be enough information in
| there to get at least a good estimate. And it is extremely
| useful that one can nowadays "just" train a model to
| confirm such theories.
| PaulHoule wrote:
| Beats the animated GIF memes that cause seizures
| VikingCoder wrote:
| ...is there a video?
| RasmusWL wrote:
| https://www.scifilab.org/bodytrak has _something_ at least, but
| still very little :(
| Animats wrote:
| "ANONYMOUS AUTHOR(S)"?
|
| This is an interesting approach, but full body tracking with a
| few sensors is already much better than this at the $150 price
| point.[1] Because it will suffer badly from occlusion, it will
| probably do well in expected situations and terribly in
| unexpected and occluded situations.
|
| [1] https://www.youtube.com/watch?v=ImEKHrUp4QM
___________________________________________________________________
(page generated 2022-11-10 23:01 UTC)