#depth camera

[prostheticknowledge]

Nose Zone

Smartphone game by Brad Dwyer utilizes the iPhone X Truedepth camera to turn your face into a controller:

Using the power of the new TrueDepth 3d camera, Nose Zone makes your face the controller. Destroy the targets by pointing at them with your nose! Make it to the bonus round before the timer runs out to earn more time and compete for the highest score. 

Official website here

[prostheticknowledge]

Real-time Holographic Communication

Telecommunication startup Mimesys announce realtime 3D capture over internet connection using consumer depth cameras:

We demonstrate real-time, true 3D video reconstruction and transmission using consumer electronics and a regular internet connection. 

Link

[prostheticknowledge]

What We Once Were

Music video for track by Emmit Fenn put together by Patrick Jean has been mostly captured with a Microsoft Kinect depth camera:

WWOW is a collaboration with artist Emmit Fenn. Most of it was short with a Kinect camera (the rest with a drone). It took two months to post-produce with home-made tools. Full credits at the end of the video! 

Link

[prostheticknowledge]

Holographic communication on ARKit

Demo from Mimesys shows live communication from VR using Kinect depth camera to iPad in AR using ARKit over data network:

We have been playing with ARKit and our software Mimesys this summer to define the next step in collaboration. Here is an example of a remote medical session between a Vive and an iPad running on 4G. 

Link

[prostheticknowledge]

cube!

Insight from Keiichi Matsuda (responsible for the fantastic Hyper-Reality short film) has been sharing updates on his twitter profile of work with Leap Motion. Most notable is this apparently seemless example of interaction and gesture tracking, handling a virtual cube with depth understanding.

Not much official info on the work, but you can follow the thread of updates here

[pauljacobevans]

Intel’s Vision for Single Board Computers is to Have Better Vision

At the Bay Area Maker Faire last weekend, Intel was showing off a couple of sexy newcomers in the Single Board Computer (SBC) market. It’s easy to get trapped into thinking that SBCs are all about simple boards with a double-digit price tag like the Raspberry Pi. How can you compete with a $35 computer that has a huge market share and a gigantic community? You compete by appealing to a crowd not satisfied with these entry-level SBCs, and for that Intel appears to be targeting a much higher-end audience that needs computer vision along with the speed and horsepower …read more http://pje.fyi/PFxlP6

[crafty-as-a-fox]

ROSを使ったSLAM構築-備忘録8

キーワード：デプスカメラ、Depth Camera

前回デプスカメラでIRイメージが真っ黒になってしまっていたが、これが結構厄介なことになっていた。どう厄介かというと、何も表示されないのが原因でIRカメラのキャリブレーションができないのである（●｀ε´●）。カメラキャリブレーションについてはROS Wikiを参照されたし。

ネットでちょっと調べてみたところ、同じような現象が起きてる人がいるようで、ROS questionのページに詳細が載っていた。ROS questionによると、どうやらIRイメージは16ビットフォーマットでチェッカーボードDetectorに渡され、チェッカーボードDetectorは16bitの内、最上位8bitを使って画像を生成しているらしい。そして、最上位8bitの画像に256を乗算し、コントラスト上げることでチェッカーボードDetectorが検出できるようになるとのこと。256を乗算するソースも公開されていたので使わせていただきます(｡-∀-)。ついでなので少しアレンジさせていただきました。コントラスト乗算値をParamとして設定できるようにしてます。ソースコードはGitHubを見てください。Param名は「contrast_value」です。

まずはopenni2_launchを起動し、

roslaunch openni2_launch openni2.launch

今回作成したコントラスト増幅ノードを起動。

rosrun camera contrast_augmenter

正常に起動できると以下のTopicがPublishされているはずです。

/camera/ir_augmented/image

これがコントラスト乗算後のIR画像である。ちなみに、contrast_value初期値は256になってます。変更したい場合は以下のコマンドで。

rosparam set contrast_value (乗算値)

こうして得られたIR画像はこのようになります。

見づらいですがなんとか表示できるようになりました。あとはカメラ・キャリブレーション時に適当にコントラスト乗算値をいじってあげれば良いはずｗ

[yi-jong-in]

단 한번 목소리를 낼 수 있다면 딸에게 처음으로 노래를 불러주고 싶었던 은주씨! 1만여 명의 목소리와 엄마의 노력으로 만든 기적, 엄마의 첫 번 째 노래

Eunjoo is a mother who would love to sing to her daughter if she could just speak only once. The miracle, a mother’s first song, was made possible through some 10,000 vocal donations and Eunjoo’s hard work.

Advertising Agency: The Creamunion Creative Director: Big Choi (Executive Creative Director), Jae Ki Lee (Creative Director) Technical Directing and Interaction Planning: Lifethings, Kayip Device Design: Lifethings Voice Synthesis: Kayip Sign Language Recognition System: Jongin Lee, Sungsil Kim, Euna Jung