Category Archives: Computer Vision

The GRAIL Project

In 1964 the RAND corporation unveiled the GRAIL Project. GRAIL was an early example of a GUI, and (the first?) example of a tablet.

The system used a programming language called GrailLanguage, which was a high-level flowchart-based programming language. All programs were written graphically and with a pen, using character recognition for statements and shape recognition for flow control.

Watch this video and tell me that the best new talent is working on Groupon for Babies or a better way to share photos.

Tagged , , , , , , ,

Android malware designed to build 3-D models of users’ apartments

An interesting article at FastCompany about PlaceRaider, an experimental smartphone trojan designed by Indiana University and the U.S. Navy. It’s Android malware designed to build 3-D models of users’ apartments.

PlaceRaider, which was summarized in a recent arXiv paper, is a piece of “visual malware” which smartphone cameras, accelerometers, and gyroscopes, to reconstruct victims’ rooms and offices. As pictures are uploaded onto the central server, they are knitted together into a 3D model of the indoor location where the pics were taken.

Tagged , , , , ,

Starry Night interactive visualisation

Petros Vrellis has used OpenFrameworks (which I used for my Kinect Pong demo) to create a beautiful fluid flow simulation of the famous Van Gogh painting ‘Starry Night’
Recommended viewing:

Tagged , , , , ,

Microsoft Research shows Augmented Projectors

Some really great work out of MSR.
Combination Depth Camera/Projector/IMU allows for some really novel interactions.

Worth a look.

Tagged , , , , , , , ,

How Google’s Self Driving Car Works

IEEE Spectrum have an article describing some details of the Google autonomous vehicle project, much of the information is public for the first time.
The article is here, but by far the best bit is the video that I’ve embedded below.

Tagged , , , , , , , , , ,

Colorization Using Optimization

A very cool SIGGRAPH ’04 paper on automatic colorization using marked images. A fairly simple algorithm with very impressive results.

The paper as PDF, and the code in MATLAB.

One of the authors of this paper is also an author of the recently quite popular ‘Depixelizing Pixel Art’.

Definitely worth a look.

Tagged , , ,


This is a teaser video showing real-time 3d scene reconstruction being performed using a single Xbox Kinect.
It’s worth a watch. As far as I can see there’s no paper publicly available yet.

For anyone who wants to try something similar at home, Nicolas Burrus’ RGBDemo has a scene reconstruction function that is fun to play with.

Tagged , , , , ,

Cloud Robotics @ Google IO 2011

At Google IO 2011 Ryan Hickman, Damon Kohler, Ken Conley, Brian Gerkey gave an interesting talk about robotics work that was occurring at Google.
If you’re interested in robotics at all I really think it’s worth a look. The gist of the first half of the talk is that cloud based services for object recognition and perception allow computing power to be moved off the robot and into the cloud. This allows information sharing between robots and can leverage tougher computing problems using the massive power available in the cloud.

During the second half of the talk Damon Kohler spoke about his work to get robotics and sensors available to the average hobbyist through the use of Android and other commodity hardware (including the Kinect!).
Some of the projects referenced in the video have been previously linked on this blog.
It’s great to see hobbyist hackers recognised.
He announced rosjava, a port of ROS (Robotic Operating System) to Java to run natively on Android.
Combined with the Android Open Accessories Development Kit, I can see some really interesting applications and excuses to buy new hardware… And it’s all open source!

Recommended viewing:

Tagged , , ,