Augustin Lux

Learn More
We propose a method to construct computer vision systems using a workbench composed of a multi-faceted toolbox and a general purpose kernel. The toolbox is composed of an open set of library modules. The kernel facilitates incremental dynamic system construction. This method makes it possible to quickly develop and experiment new algorithms, it simplifies(More)
We address the problem of determining if a given image region contains people or not, when environmental conditions such as viewpoint , illumination and distance of people from the camera are changing. We develop three generic approaches to discriminate between visual classes: ridge-based structural models, ridge-normalized gradient histograms, and linear(More)
This paper presents a new approach for face recognition based on the fusion of ten-sors of census transform histograms from Local Gaussian features maps. Local Gaussian feature maps encode the most relevant information from Gaussian derivative features. Census Transform (CT) histograms are calculated and concatenated to form a tensor for each class of(More)
This paper presents a method for object detection based on a cascade of scale and orientation normalized Gaussian derivative classifiers learnt with Adaboost. Normalized Gaussian derivatives provide a small but powerful feature set for rapid learning using Adaboost. Real time detection is made possible by use of a fast integer coefficient algorithm that(More)
We investigate the use of two visual descriptors: Local Binary Patterns-Three Orthogonal Planes(LBP-TOP) and Dense Trajectories for depression assessment on the AVEC 2014 challenge dataset. We encode the visual information generated by the two descriptors using Fisher Vector encoding which has been shown to be one of the best performing methods to encode(More)
— Cet article présente une méthode pour détecter des caractéristiques de type pic et crête dans une image. Ces carac-téristiques seront utilisées pour la modélisation et la reconnaissance d'objets. Un point de type crête ou pic est caractérisé lo-calement par des propriétés géométriques de la conique tangente à la surface-image. Deux critères sont utilisés(More)