Neural chip helps Kinect make finger recognition a snap
While the Microsoft (Redmond, WA, USA) Kinect camera does an excellent job of tracking a user's limbs and hands, because the sensor image data from it can be noisy when looking at fine detail, it is difficult to distinguish and track a user's fingers.
But by using the Kinect camera and its Software Development Kit (SDK) in conjunction with CogniMem's (Folsom, CA, USA) own CM1K cognitive computer chip, engineers Bill Nagel and Chris McCormick have developed a solution to overcome that problem.
The system they created uses the Kinect camera to provide the skeleton and depth field information, while the CM1K device - which sports 1024 neurons working in parallel - enhances the image data by comparing the overall shape of the hand with a database of trained examples so that different finger gestures can be recognized.
The demonstration served a dual purpose -- firstly, to prove how CogniMem's technology can be used for gesture recognition even if the input is noisy or not 100 per cent accurate, and secondly, to show how easy it is to integrate with off-the-shelf technology like the Kinect.
The system was shown at the Computer Vision and Pattern Recognition (CVPR) conference in Providence, Rhode Island in June this year.
The engineers have produced a demonstration of the technology in action on YouTube here.
Interested in reading how others are using the Kinect? Here's a compendium of five news stories on the Kinect that Vision Systems Design has published over the past six months.
1. Kinect software helps rehabilitate stroke victims
Engineers at the Hong Kong Polytechnic University (Hong Kong, China) have developed a free software game for the Microsoft Kinect that aims to help rehabilitate individuals who have suffered a stroke.
2. Shoulder-mounted projector uses Kinect to track movement
Engineers at the University of Munich (Munich, Germany) have developed a shoulder-mounted system that tracks the movement of users' hands and fingers as they interact with images projected by the system onto a surface.
3. 3-D videoconferencing embeds Kinect sensors
At Canada's Queen's University, researchers have created a human-sized 3-D videoconferencing system that allows people in different locations to participate in a video conference as if they were standing in front of each other.
4. How accurate is the Kinect?
An assistant professor at the Faculty of Geo-Information Science and Earth Observation of the University of Twente (Enschede, The Netherlands) has written a technical paper that analyses the accuracy and resolution of the depth data from the Microsoft Kinect sensor.
5. Kinect software brings animation to the masses
Researchers at Microsoft (Redmond, WA, USA) have released details of their new KinÊtre software that employs gesture recognition, enabling users to animate inanimate objects by moving their bodies.
-- Dave Wilson, Senior Editor, Vision Systems Design