The perceptoscope is an augmented reality device for fixed locations. Before getting too much into the specifics, imagine that you could walk up to a perceptoscope placed near the Empire State building. You look through the eye pieces and you see the city as it was before the building was constructed. At the flip of a switch you can watch the building take shape right in front of you. All this, with true 3D vision and motion tracking.
The perceptoscope is an augmented reality device for fixed locations. Before getting too much into the specifics, imagine that you could walk up to a perceptoscope placed near the Empire State building. You look through the eye pieces and you see the city as it was before the building was constructed. At the flip of a switch you can watch the building take shape right in front of you. All this, with true 3D vision and motion tracking.
LiveLights is an automated system for summarizing unedited video and was developed by researchers in Carnegie Mellon University's Machine Learning Department. Without human supervision, LiveLights automatically scans through the video stream, removing repetitive and uninteresting contents. The result is a compilation of the most salient and informative portions of the video. Below are three examples of consumer video and the corresponding summarization automatically generated by LiveLights.
How do you use OpenCV to capture and image process frames so that you can build computer vision applications under Linux on the Beaglebone – I do this using the boneCV.cpp program as described below. This code uses the OpenCV library which is available on the Angstrom distribution of the Beaglebone. Finally, I write a small program boneCVtiming.cpp to test the performance of the Beaglebone black for capturing and processing image data.
Want to take 3D pictures? Need cool things to make with your 3D printer? This 3D camera build uses a Structured lighting technique to create a 3D representation that can be rendered with any 3D software. Structured lighting is basically a set of images that are sequentially projected onto a scene and captured with an ordinary CMOS camera. The deformation of the structured light is ran though an algorithm to determine the depth at each pixel. The resulting X,Y and Z coordinates (3D point cloud) are used to reproduce a 3D model of the scene.
CV Dazzle is an independent project, but it won't be for long.
If you're a coder, computer vision expert, fashion designer, hacker, makeup artist, hair stylist, 3D modeler, privacy enthusiast, activist, fashion designer, or have something to contribute to the project, you should really introduce yourself:
CV Dazzle is an independent project, but it won't be for long.
If you're a coder, computer vision expert, fashion designer, hacker, makeup artist, hair stylist, 3D modeler, privacy enthusiast, activist, fashion designer, or have something to contribute to the project, you should really introduce yourself:
Kinect@Home is a place where you can help robotics and computer vision researchers around the world and get 3D models of your room, office or whatever you want in return, right in your browser!
Kinect@Home aims to use your powers to make robots more awesome than ever. Robotics and computer vision researchers need vast amount of images from everyday environments such as homes and offices to improve their algorithms.
In labs people have been experimenting with computer vision for a long time, like being able to track a body. We can go back almost 20 years and find examples of that at the MIT video lab, designing interfaces that track someone's arm or hand. It's really only with the release of the Sony iToy where that became something that was more public. And now with the Kinect, it's become massively public. So that's an example of the technology changing.