|COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring.|
Latent Hough Transform for Object Detection
If you have a question about this talk, please contact Microsoft Research Cambridge Talks Admins.
This event may be recorded and made available internally or externally via http://research.microsoft.com. Microsoft will own the copyright of any recordings made. If you do not wish to have your image/voice recorded please consider this before attending
Since the invention of the Hough transform (HT) in 1960’s, this method has become a very popular method for object detection. Originally proposed for detecting parametric objects like lines, circles, etc., HT has been generalized for detecting arbitrary shapes by parameterizing the objects by a reference point, e.g. the center of mass, and accumulating the votes of local image patches for this point. Although this representation enforces consistency of patches in their relative locations, it produces false positives by combining votes that are consistent in location but inconsistent in other properties like shape, pose, color, etc. which is the main reason behind the poor performance of these approaches. This all raises several questions about the validity of the center as the only parametrization of object categories. In particular, is voting for the center necessary? What other criteria can be used for voting? Can we learn the optimal properties from data?
This talk is part of the Microsoft Research Machine Learning and Perception Seminars series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
Other listsHebrew Open Classes Physics of Living Matter lectures Research Office Linked Events
Other talksBuilding Business in the Sunshine Serre weights and de Rham cohomology of Shimura curves Challenges In Silicon-Based PV Technologies Practically Making the Philosophers' Stone: Recreating Alchemical Experiments A Heisenberg Miscellany Art Speak