Massachusetts Institute of Technology (MIT) researchers say they have developed an algorithm that can aggregate different perspectives and recognize four times as many objects as one that uses a single perspective while reducing the number of misidentifications, and that works 10 times faster than conventional algorithms.
"If you just took the output of looking at it from one viewpoint, there's a lot of stuff that might be missing, or it might be the angle of illumination or something blocking the object that causes a systematic error in the detector," says graduate student Lawson Wong, a researcher in MIT's Computer Science and Artificial Intelligence Laboratory.
The researchers tested the algorithm using scenarios in which they had 20 to 30 different images of household objects clustered together on a table. In several of the scenarios, the clusters included multiple instances of the same object, closely packed together, which makes the task of matching different perspectives more difficult. The algorithm does not discard any of the hypotheses it generates across successive images, and instead samples from them at random.
Because there is significant overlap between different hypotheses, a large-enough number of samples will typically yield consensus on the correspondences between the objects in any two successive images.
From MIT News
View Full Article
Abstracts Copyright © 2015 Information Inc., Bethesda, Maryland, USA