随着微软kinect(natal)的发展，深度摄像头吸引越来越多人的目光，深度摄像头可以用在人体跟踪，三维重建，人机交互，SLAM等等领域。但是深度摄像头的高昂的价格实在是让一般人望而却步，我所知道的primesense
的一个摄像头要5000美元。。。而kinect的出现会不会带动民用（相对廉价）的深度摄像头的发展呢（传闻kinect定价199美元）？
cvchina曾经介绍过两种深度摄像头，下面再转一个最近看到的几种深度摄像头的简介：
看到一则关于微软Natal的小道消息，全文照抄如下：
Yesterday, I was invited to a private Project Natal sneak peek. The event was held at the beautiful EZ Studios in New York City. I met with a member of the Project Natal product team. She gave us a brief explanation of the Natal vision and gave us only a few technical details:
- RBG camera
- depth camera
- Current games will not be compatible with Natal
- “Project Natal” is a code name and will not be the final name of the product
- [Work in progress] Use voice commands to control services i.e. music, videos, movies
- [Work in progress] Facial recognition
- [Work in progress] Use gesturing to navigate the XBOX menu structure
- [Work in progress] Distinguishing between the primary player and a spectator
- [Work in progress] Suppressing background noise
Once we were briefed — we were given the opportunity to play a dodge ball (like) game. It was a great experience. There I was (without a controller) standing, kicking, swatting, jumping and working up a sweat. The responsiveness of the Natal system was incredible and very accurate. If I physically moved forward, back, swung faster or slower my dodge ball avatar responded in kind.
“Our advances in computer vision and audio-signal processing,” Malvar notes, “have enabled the development of Project Natal, a new level of experience for Xbox, in which user gestures and voice take the place of the standard game controller.– Rico Malvar, managing director of Microsoft Research Redmond
语音识别可以多国语言么？可以自定义么？
搞了这么久，终于要上市了。
突然有个疑问，natal能同时追踪多人么？
据这篇报道，natal不光有手势，姿态识别，还有语音识别，表情识别（当玩家表情厌烦的时候，游戏难度会降低么？）。
The key aspect of Project Natal is its ability to recognize gestures, but the system also includes the ability to respond to voice commands and facial or object recognition. These last two technologies are well established at this point. Despite some consistency issues and a literal learning curve, voice recognition is commonly found in cell phones and speech-to-text typing applications. Facial recognition, often viewed with trepidation for its big-brother security implications, is now widely available in consumer point-and-shoot cameras.
微软natal的lead developer（怎么翻译？）Alex Kipman 在CES2010透露natal将可以30fps的速度运行，占用10-15%的cpu资源。
We think input using existing controllers is the barrier, and by erasing that we can realistically say: all you need to play is life experience. — Alex Kipman
最新评论