Refine my results

Document type

Institution

Specific Collection

Language

Université de Neuchâtel

Motion integration in visual attention models for predicting simple dynamic scenes

Bur, Alexandre ; Wurtz, Pascal ; Muri, Rene M. ; Hügli, Heinz

In: Human Vision and Electronic Imaging XII (Proceedings of SPIE), 2007, vol. 6492, no. 47, p. 649219- 649229

Visual attention models mimic the ability of a visual system, to detect potentially relevant parts of a scene. This process of attentional selection is a prerequisite for higher level tasks such as object recognition. Given the high relevance of temporal aspects in human visual attention, dynamic information as well as static information must be considered in computer models of visual attention....

Université de Neuchâtel

3D vision methods and selected experiences in micro and macro applications

Hügli, Heinz ; Mure-Dubois, James

In: Two- and Three-Dimensional Methods for Inspection and Metrology IV (Proceedings of SPIE), 2006, vol. 6382, no. 10, p. 638209- 638216

The paper provides considerations relative to the application of 3D vision methods and presents some lessons learnt in this respect by presenting four 3D vision tasks and discussing the selection of vision sensing devices meant to solving the task. After a short reminder of 3D vision methods of interest for optical range imaging for microvision and macrovision applications, the paper enumerates...

Université de Neuchâtel

Multiresolution reliability scheme for range image filtering

Zamofing, Thierry ; Hügli, Heinz

In: Two- and Three-Dimensional Vision Systems for Inspection, Control, and Metrology II (Proceedings of SPIE), 2006, vol. 5606, no. 9, p. 134-144

A large number of 3D cameras suffer from so-called holes in thedata, i.e. the measurement lattice is affected by invalidmeasurements and the range image has undefined values.Conventional image filters used for removing the holes perform notwell in presence of holes with large varying hole sizes. The novelhole-filling method presented in this paper operates onreliability attributed range images...

Université de Neuchâtel

Applied multifocus 3D microscopy

Zamofing, Thierry ; Hügli, Heinz

In: Two- and Three-Dimensional Vision Systems for Inspection, Control, and Metrology (Proceedings of SPIE), 2003, vol. 5265, no. 19, p. 134-144

The depth from focus measurement principle relies on the detection of the optimal focusing distance for measuring the depth map of an object and finding its 3D shape. The principle is most effective at microscopic ranges where it is usually found implemented around a z-controlled microscope and sometimes named multifocus 3D microscopy. Assuch, the method competes with many other 3D measurement...

Université de Neuchâtel

Computing visual attention from scene depth

Ouerhani, Nabil ; Hügli, Heinz

In: Proceeding 15th International Conference on Pattern Recognition (ICPR), 2000, vol. 1, p. 375-378

Visual attention is the ability to rapidly detect the interesting parts of a given scene. Inspired by biological vision, the principle of visual attention is used with a similar goal in computer vision. Several previous works deal with the computation of visual attention from images provided by standard video cameras, but little attention has been devoted so far to scene depth as source for...

Université de Neuchâtel

From topological knowledge to geometrical map

Tièche, François ; Hügli, Heinz

In: Control Engineering Practice, 1999, vol. 7, no. 6, p. 797-802

The behavioral approach to robot navigation, characterized by a representation of the environment that is topological and robot-environmental interactions that are reactive, is preferable to purely geometrical navigation because it is far more robust against unpredictable changes of the environment. Nevertheless, there is still a need to obtain geometrical maps. This paper considers a geometrical...

Université de Neuchâtel

Usefulness of the LPC-residue in text-independent speaker verification

Thévenaz, Philippe ; Hügli, Heinz

In: Speech Communication, 1995, vol. 17, no. 1-2, p. 145-157

This paper is a contribution to automatic speaker recognition. It considers speech analysis by linear prediction and investigates the recognition contribution of its two main resulting components, namely the synthesis filter on one hand and the residue on the other hand. This investigation is motivated by the orthogonality property and the physiological significance of these two components, which...

Université de Neuchâtel

Real-time visual attention on a massively parallel SIMD architecture

Ouerhani, Nabil ; Hügli, Heinz

In: Real-Time Imaging, 2003, vol. 9(3), p. 189-196

Visual attention is the ability to rapidly detect the visually salient parts of a given scene on which higher level vision tasks, such as object recognition, can focus. Found in biological vision, this mechanism represents a fundamental tool for computer vision. This paper reports the first real-time implementation of the complete visual attention mechanism on a compact and low-power...

Université de Neuchâtel

Empirical Validation of the Saliency-based Model of Visual Attention

Ouerhani, Nabil ; Hügli, Heinz ; Müri, René ; Von Wartburg, Roman

In: Electronic Letters on Computer Vision and Image Analysis, 2003, vol. 3(1), p. 13-23

Visual attention is the ability of the human vision system to detect salient parts of the scene, on which higher vision tasks, such as recognition, can focus. In human vision, it is believed that visual attention is intimately linked to the eye movements and that the fixation points correspond to the location of the salient scene parts. In computer vision, the paradigm of visual attention has...

Université de Neuchâtel

Visual attention-based robot self-localization

Ouerhani, Nabil ; Bur, Alexandre ; Hügli, Heinz

In: In Proceeding of European Conference on Mobile Robotics, 2005, p. 8-13

This paper reports a landmark-based localization method relying on visual attention. In a learning phase, the multi-cue, multi-scale saliency-based model of visual attention is used to automatically acquire robust visual landmarks that are integrated into a topological map of the navigation environment. During navigation, the same visual attention model detects the most salient visual features...