Skip to Main content Skip to Navigation

Reconnaissance d'objets utilisant des histogrammes multidimensionnels de champs réceptifs

Bernt Schiele 1 
1 PRIMA - Perception, recognition and integration for observation of activity
GRAVIR - IMAG - Laboratoire d'informatique GRAphique, VIsion et Robotique de Grenoble, Inria Grenoble - Rhône-Alpes
Abstract : During the last few years, there has been a growing interest in object recognition schemes directly based on images, each correspondingg to a particular appearance of the object. Representations of objects, which only use information of images are called (\it appearance based) models. The interest in such representation schemes is due to their robustness, speed and success in recognizing objects. The thesis proposes a framework for the statistical representation of appearances of 3D objects. The representation consists of a probability density function over a set of robust local shape descriptors which can be extracted reliable from images. The object representation is therefore learned automatically from sample images. Multidimensional receptive field histograms are introduced for the approximation of the probability density function. A main result of the thesis is that such a representation scheme based on local object descriptors provides a reliable means for object representation and recognition. Different recognition algorithms are proposed and experimentally evaluated. The first recognition algorithm by histogram matching can be seen as the generalization of the color indexing scheme of Swain and Ballard. The second recognition algorithm calculates probabilities for the presence of objects only based on multidimensional receptive field histograms. The most remarkable property of the algorithm is that he does not rely neither on correspondence nor on figure ground segmentation. Experiments show the capability of the algorithm to recognize 100 objects in cluttered scenes. The third recognition algorithm incorporates several viewpoints in an active recognition framework in order to solve ambiguities inherent in single view recognition schemes. The thesis also proposes visual classes as a general framework for appearance based object classification. Classification has been proven difficult for arbitrary objects due to instabilities of invariant representations. The proposed concepts for extraction, representation and recognition of visual classes provide a general framework for object classification. The thesis aims, from an abstract point of view, to push the limits of the appearance based paradigm without using neither figure ground segmentation nor correspondence. The active object recognition allows the consistent recognition of objects in 3D and therefore overcomes the limits of single view recognition. The appearance based classification framework based on the concept of visual classes will serve for future research.
Document type :
Complete list of metadata
Contributor : Thèses Imag Connect in order to contact the contributor
Submitted on : Friday, February 20, 2004 - 6:31:37 PM
Last modification on : Friday, March 25, 2022 - 11:10:35 AM
Long-term archiving on: : Wednesday, September 12, 2012 - 1:40:20 PM


  • HAL Id : tel-00004962, version 1



Bernt Schiele. Reconnaissance d'objets utilisant des histogrammes multidimensionnels de champs réceptifs. Interface homme-machine [cs.HC]. Institut National Polytechnique de Grenoble - INPG, 1997. Français. ⟨tel-00004962⟩



Record views


Files downloads