增强视觉 | 计算机视觉 增强现实

微软正在进行一个名为KinectFusion的项目。目标是利用一台围绕物体移动的kinect实时重建物体的三维模型。（是不是可以理解为Kinect版本的SLAM？）不同于的简单的三维点云的拼接，该项目的另外的吸引人的特性在于：如果对物体进行持续的扫描，三维重建精度可以由粗到细的逐渐提高。（类似superresolution？）演示视频（必看！！！）很给力。

阅读全文…

到处都是kinect的新闻，凑个热闹，转几个链接：

1： 有了Kinect，你也可以在家自己拍3D影片

2： Key Kinect Technology Devised in Cambridge Lab

3：How Kinect tracks people

据链接2里面内容，kinect算法核心的研发跟Jamie Shotton关系甚大。期待内幕帝。

1999年由Cyrus Bamji, Abbas Rafii, and Nazim Kareemi 创立的Canesta公司被无情的资本大鳄微软公司收购了。

这个公司主要干的事情是3D的手势识别，恩，自己造3D摄像头的，这个简单的来说就是用3D摄像头识别手势，应该会比2维的简单很多了，准确率也会提高很多了。恩，所以硬件为王了。来看一段他们公司的视频吧。

阅读全文…

响应站长号召，写SIGGRAPH2010的文章，这篇是微软研究院的去模糊的一套算法

去模糊是个欠定的问题，在这里MS的研究人员用惯性测量传感器作为prior来去模糊，最后出来的效果很给力啊

阅读全文…

还记得cvchina以前报道过的微软的sensecamera么？现在已经有产品，名字是Revue了，是由ViconRevue这家公司出品的。除了一个vga(640*480)的相机,还装备了多种传感器，比如罗盘，温度计啥的。目前的市场定位是医学研究方向。

下面是官方介绍和spec,这规格好像有点弱啊，还卖这么贵。
阅读全文…

佩戴一个便携式的摄像头，录音仪，gps来记录身边发生的一切已经不是个新鲜玩意了。但是如何有效的挖掘，浏览，总结这海量的数据，却是个新鲜可挖掘的课题。

SenseCamera是微软研发的这种设备，有摄像头，光学传感器，红外传感器，加速仪等等。目前研究者致力于如何有效的组织采集到的影像等数据，来帮助记忆有困难的人来了解过去究竟发生了什么，从而不用像memento（记忆碎片）里那个可怜的家伙一样把自己全身刺满纹身了。

下面是相关研究的介绍引文，没时间翻了。

To find the best memory cues for Mr. Reznick’s experiences, the researchers — Anind K. Dey, a computer science professor at Carnegie Mellon University, and Matthew Lee, a graduate student — considered the types of images that had proved the most effective in previous SenseCam studies.

They soon realized that the capriciousness of memory made answers elusive. For one subject, a donkey in the background of a barnyard photo brought back a flood of recollections. For another, an otherwise unremarkable landscape reminded the subject of a snowfall that had not been expected.

Still, the researchers came up with some broad rules for identifying and retrieving images likely to serve as memory triggers. For a people-based experience like a family reunion, the system selects photographs in which faces are clearly discernible; for a location-based experience like a visit to a museum, it uses geographical positions provided by GPS and accelerometer data to judge what images might be most salient — for example, when a subject might be hovering at one spot, like in front of a painting.

Research groups elsewhere are experimenting with other techniques to summarize and make use of SenseCam data. Alan Smeaton and colleagues at Dublin City University in Ireland are comparing images to categorize them by activity — shopping, for example — so the system can put together a visual summary of the day. At the University of Toronto, a group led by Ronald M. Baecker is investigating the usefulness of complementing SenseCam images with an audio narrative created by a loved one.

Once the system selects some photos from the hundreds taken, the caregiver winnows down the candidates, adding cues like audio from the voice recorder, verbal narration and brief text captions. The final product is a multimedia slide show on a tablet computer that allows the patient to dig deeper into highlighted parts of some images by tapping on the screen. The first tap plays audio, the second shows captions.

“The design is intended to give the patient the ability to engage actively with the experience instead of simply flipping through some pictures,” said Mr. Lee, the graduate student. Testing the system with the Reznicks and two other couples, he and Dr. Dey found that it helped patients recall events more vividly and with greater confidence than when they simply went through all of the images.

Other SenseCam studies — also financed by Microsoft — have produced encouraging results, but plans to market the device as a memory aid have not been announced.

媒体来源

前面cvchina报道过微软新一代bing地图上的街景缝合，现在google也在自家的street view上加入了该技术。

根据这里的报道（可能要翻墙），还有这里的报道，google会用自家的图像匹配技术，将用户的照片匹配到街景上。浏览者可以点击街景上一字排开的缩略图，观看不同用户不同时间，不同角度拍摄的照片。点击街景上的银色的小圆点，还可以近距离观看细节。

注意右下角的提示符

注意上面一排用户自拍图片

现在只有有限的地点有这个功能，多数是旅游景点。可去巴塞罗那Sagrada Familia，巴黎凯旋门围观。

记得building rome in one day项目的背后既有微软，又有google，现在看来两家都推出街景照片缝合，也不奇怪吧。

但是目前还是微软略胜一筹，那个TED talk上展示的实时街景缝合是在是太牛逼了啊。

natal

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？

来源