On detection of multiple object instances using Hough transform

ЗаголовокOn detection of multiple object instances using Hough transform
Тип публикацииConference Paper
Год публикации2010
АвторыBarinova O, Lempitsky V, Kohli P
Refereed DesignationRefereed
КонференцияComputer Vision and Pattern Recognition
Язык публикацииEnglish
Ключевые словаHough transform, object detection
Аннотация

To detect multiple objects of interest, the methods based on Hough transform use non-maxima supression or mode seeking in order to locate and to distinguish peaks in Hough images. Such postprocessing requires tuning of extra parameters and is often fragile, especially when objects of interest tend to be closely located. In the paper, we develop a new probabilistic framework that is in many ways related to Hough transform, sharing its simplicity and wide applicability. At the same time, the framework bypasses the problem of multiple peaks identification in Hough images, and permits detection of multiple objects without invoking nonmaximum suppression heuristics. As a result, the experiments demonstrate a significant improvement in detection accuracy both for the classical task of straight line detection and for a more modern category-level (pedestrian) detection problem.

URLhttp://graphics.cs.msu.ru/en/science/research/machinelearning/hough
Ключ цитирования540