%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2016/08.16.14.19
%2 sid.inpe.br/sibgrapi/2016/08.16.14.19.35
%T A Keypoint detector based on Visual and Depth features
%D 2016
%A Vasconcelos, Levi Osterno,
%A Campos, Mario Fernandes Montenegro,
%A Nascimento, Erickson Rangel do,
%@affiliation Universidade Federal de Minas Gerais
%@affiliation Universidade Federal de Minas Gerais
%@affiliation Universidade Federal de Minas Gerais
%E Aliaga, Daniel G.,
%E Davis, Larry S.,
%E Farias, Ricardo C.,
%E Fernandes, Leandro A. F.,
%E Gibson, Stuart J.,
%E Giraldi, Gilson A.,
%E Gois, João Paulo,
%E Maciel, Anderson,
%E Menotti, David,
%E Miranda, Paulo A. V.,
%E Musse, Soraia,
%E Namikawa, Laercio,
%E Pamplona, Mauricio,
%E Papa, João Paulo,
%E Santos, Jefersson dos,
%E Schwartz, William Robson,
%E Thomaz, Carlos E.,
%B Conference on Graphics, Patterns and Images, 29 (SIBGRAPI)
%C São José dos Campos, SP, Brazil
%8 4-7 Oct. 2016
%I Sociedade Brasileira de Computação
%J Porto Alegre
%S Proceedings
%K keypoint detector, RGB-D image, decision tree, information fusion.
%X One of the first steps in numerous computer vision tasks is the extraction of keypoints. Despite the large number of works proposing image keypoint detectors, only a few methodologies are able to efficiently use both visual and geometrical information. In this work we introduce KVD (Keypoints from Visual and Depth Data), a novel keypoint detector which is scale invariant and combines intensity and geometrical data using a decision tree. We present results from several experiments showing that our methodology produces the best performing detector when compared to state-of-the-art methods, with the highest repeatability scores for rotations, translations and scale changes, as well as robustness to corrupted visual or geometric data. Additionally, as processing time is concerned, KVD yields the best time performance among methods that also use depth and visual data.
%@language en
%3 camera-ready-levi.pdf