Earth Imaging Journal: Remote Sensing, Satellite Images, Satellite Imagery
Breaking News
Image Shows Shanghai, Beijing, Massive Sedimentation
The Copernicus Sentinel-3A looks at an extremely populous portion...
Join GITA in Tampa – March 2019!
GITA is proud to announce along with our local...
CoreLogic and Esri Expand Premium Content Offerings
CoreLogic® (NYSE: CLGX), a leading global property information, analytics...
OGC Calls for Participation in Vector Tiles Pilot
The Open Geospatial Consortium (OGC) has released a Call...
Azteca Systems Releases Cityworks 15.3
Cityworks–Azteca Systems announced the release of Cityworks 15.3, the...

MIT researchers are fine tuning algorithms to consider arm positions and hand positions separately, which drastically cuts down on the computational complexity of their task.

The problem of interpreting hand signals has two distinct parts. The first is simply inferring the body pose of the signaler from a digital image: Are the hands up or down, the elbows in or out? The second is determining which specific gesture is depicted in a series of images. The MIT researchers are chiefly concerned with the second problem; they present their solution in the March issue of the journal ACM Transactions on Interactive Intelligent Systems. But to test their approach, they also had to address the first problem, which they did in work presented at last year’s IEEE International Conference on Automatic Face and Gesture Recognition.

Read the full story.

Comments are closed.