Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Leap: A new gesture based interface for devices

leapmotion.com

Post reply on HN
Print view View original

91–100 of 187 posts

Re: Leap: A new gesture based interface for devices

#91

Post by acgourley »

dmvaldman wrote: post #79
ChrisFornof wrote: post #73

Dev Kits (free) Ship international within 1-3 months. Pre-orders ($70) only ship domestic (for now) around winter. 20,000 dev kits are being made. We want to ensure this tech becomes ubiquitous. We're getting slammed with launch response. But if you guys have questions, we'll try to answer them here shortly. -Chris Community Builder

Waiting for the load to drop so I can try to get a preorder! Question: How can you render the "other side" of the hand at the 51+ second mark? If this is indeed possible, that's quite a remarkable technology you have.

I suspect it's an illusion and that does not represent their true 3d point cloud. It's probably a skinned 3d mesh of a hand which is then moving in sync with the detected hand.

Re: Leap: A new gesture based interface for devices

#92

Post by iandanforth »

I'm sad the word 'robot' hasn't appeared in this thread yet. Let's correct that.

Visual slam is great for medium distances, but pointclouds aren't really that dense and are slow to update. Also the lidar to make the point clouds is stupid expensive.

Add one of these guys onto your robot and you've got a really cool set of 'wiskers.' Short range, highly sensitive, super fast update. I'd love to put several of these on a robot and use that to give it a sensitive field surrounding its body.

Depending on how open the software and hardware are this will be a great addition to the robotics community.

Re: Leap: A new gesture based interface for devices

#93

Post by kylebrown »

chime wrote: post #66
kylebrown wrote: post #63

Wow.. I would love to develop for this. I dropped out of state U. after my 3rd year (math major), but that was years ago. At my current start-up, I have recently been forced to learn much more than I was expecting to about probabilistic graphical models and curve similarity measures (gladly though; always been interested in pattern recognition). Anyone with a vision for this, consider dropping me a line. I might be a…

I'd love to integrate it with my KType application ( http://ktype.net ) or build a new software that converts hand gestures / ASL to speech. I think it's totally doable and would be a lot of fun technically too. What do you think?

Well, off the top of my head I don't see a straightforward way to integrate with KType (nice work btw!). Just because there would be so many possibilities for mapping hand gestures to the KType actions/commands.

On the other hand, converting sign language to text/speech seems like it should be quite straightforward. Not knowing anything about sign language, I'm assuming signs map (more or less) one-to-one with words. The input from LEAP appears to be extremely high resolution, so if the sign gestures are properly normalized (and judging from the demo video, it looks like the LEAP SDK itself already does a good degree of input normalization), you should be able to just train your classifier (neural network, SVM, etc.) right out of the box.

Of course, things are never as easy as they look so in all likelihood there are plenty of complications I'm completely overlooking at first glance. But I agree with you 100% that it sounds totally doable.

Re: Leap: A new gesture based interface for devices

#94

Post by ChrisFornof »

huhtenberg wrote: post #64
acgourley wrote: post #47

Let's have a constructive comment thread. Instead conveying love or hate for it, how about listing the cases it's good and bad for. good * Fruit Ninja - made for single finger input, short gameplay * Pinching and zooming maps - good because it's usually a short activity * CAD camera interactions - good for periodic strange rotation needs or showing a client that doesn't understand the normal movement hotkeys * Period…

> Periodic writing with pencil tool Very very inconvenient. Writing on air is completely different and considerably more tricky that writing on paper. Physically more demanding too. It's one of those things that sound nice in theory, but not really practical.

Writing in air is flashier for press videos, but we understand this bit well. We can track your pen as you write on normal paper too. We'll post a video of this sometime shortly.

-Chris

Re: Leap: A new gesture based interface for devices

#95

Post by georgieporgie »

acgourley wrote: post #67
huhtenberg wrote: post #64

Earlier quoted context omitted.

> Periodic writing with pencil tool Very very inconvenient. Writing on air is completely different and considerably more tricky that writing on paper. Physically more demanding too. It's one of those things that sound nice in theory, but not really practical.

You're right. I just tried it (not with the leap hardware) - the inability to "lift up" off the paper without leaving the sensor zone is weird. No haptic feedback when you're on the "paper" and not.

A Bluetooth 'dumb' stylus with a button or slide sensor could give a pretty convincing airbrush effect in a paint app.

I don't see traditional writing being a realistic application, though perhaps cursive signatures could work.

Re: Leap: A new gesture based interface for devices

#96

Post by georgieporgie »

davydka wrote: post #52
jasonwatkinspdx wrote: post #42

Earlier quoted context omitted.

What's the hardware? Two infrared cameras and a laser dot pattern of some sort?

2 normal digital cameras and a uv or infrared dot pattern. I think the glass is a uv filter. I got to play around with one at work.

So, this is somewhat similar to the Kinect, right?

http://www.microsoft.com/en-us/kinectforwindows/

Re: Leap: A new gesture based interface for devices

#97

Post by ChrisFornof »

davydka wrote: post #52
jasonwatkinspdx wrote: post #42

Earlier quoted context omitted.

What's the hardware? Two infrared cameras and a laser dot pattern of some sort?

2 normal digital cameras and a uv or infrared dot pattern. I think the glass is a uv filter. I got to play around with one at work.

Close enough.

Re: Leap: A new gesture based interface for devices

#98

Post by egypturnash »

cturner wrote: post #88
JackC wrote: post #49

Earlier quoted context omitted.

I think there will be some things it's great at and some it's terrible at. Here's one for free: how about using this to create the Rosetta Stone of sign language? Or a portable sign-to-speech translator? (These are hard problems for other reasons, but this thing brings you a lot closer.) Think of it like this: Alan Kay isn't wrong, but you could say the same thing about any input. The mouse is a very bad input device…

(I like the idea of a pressure-sensitive keyboard. Could be useful for music. Probably hard to engineer in a way that would be useful and which wouldn't compromise button input. Blue-switch cherry keyboards are annoying to type on. Still, interesting idea.) You're papering over the problems with relativism. The keyboard is rapid to use and flexible. Although it has the possibility of physical health problems with RSI…

I don't think it's one or the other. Has the mouse replaced the keyboard? It's an additional way to interact.

Hell, I could have used it a little earlier today - I was bleaching my hair and realized my machine wasn't playing any music. Currently my options for remedying this are (1) poking at the media keys on my keyboard (and getting bleach all over them), or (2) picking up my Wacom stylus, going to the Dock to bring up iTunes, and hitting its play button, thus smearing bleach EVERYWHERE. With one of these sitting on my desk and wired into some global hotkeys, I'd have had the additional option of waving my hand in a particular way.

I'm also thinking I totally want to incorporate one of these into the media PC I'm working on based on a Raspberry Pi, a pico projector, and half of a rubber cat[1]. Slouch on the couch, wave my hands in precise gestures to control it instead of having to bring up a mouse somehow.

Using it for long, sustained periods? Nah. Using it now and they? Oh yeah.

[1] the whole thing is disguised as Nyan Cat, with the projector poking out of its snarling mouth and the plaque it's mounted on painted like a Pop-tart.

Re: Leap: A new gesture based interface for devices

#99

Post by ChrisFornof »

chime wrote: post #66
kylebrown wrote: post #63

Wow.. I would love to develop for this. I dropped out of state U. after my 3rd year (math major), but that was years ago. At my current start-up, I have recently been forced to learn much more than I was expecting to about probabilistic graphical models and curve similarity measures (gladly though; always been interested in pattern recognition). Anyone with a vision for this, consider dropping me a line. I might be a…

I'd love to integrate it with my KType application ( http://ktype.net ) or build a new software that converts hand gestures / ASL to speech. I think it's totally doable and would be a lot of fun technically too. What do you think?

Chime, email us (community (at) leapmotion (dot) com) . We'd love to do what we can to encourage your research.

-Chris

Re: Leap: A new gesture based interface for devices

#100

Post by georgieporgie »

ChrisFornof wrote: post #73

Dev Kits (free) Ship international within 1-3 months. Pre-orders ($70) only ship domestic (for now) around winter. 20,000 dev kits are being made. We want to ensure this tech becomes ubiquitous. We're getting slammed with launch response. But if you guys have questions, we'll try to answer them here shortly. -Chris Community Builder

Please give us some technical details to satisfy our curiosity. Perhaps I missed it on the website, but I didn't notice any mention of how it functions (IR? Sound waves?), what sort of range of distances it works in, etc.
Post reply on HN