Université de Neuchâtel

Cue Normalisation Schemes in Saliency-based Visual Attention Models

Ouerhani, Nabil ; Jost, Timothée ; Bur, Alexandre ; Hügli, Heinz

In: Proceeding. Second International Cognitive Vision Workshop (ICVW), 2006, p. 1-7

Université de Neuchâtel

AttentiRobot: A Visual Attention-based Landmark Selection Approach for Mobile Robot Navigation

Ouerhani, Nabil ; Hügli, Heinz ; Gruener, G. ; Codourey, A.

In: Proceedings. 2nd international workshop on attention and performance in computational vision (WAPCV), 2004, p. 1-7

Visual attention refers to the ability of a vision system to rapidly detect visually salient locations in a given scene. On the other hand, the selection of robust visual landmarks of an environment represents a cornerstone of reliable vision-based robot navigation systems. Indeed, can salient scene locations provided by visual attention be useful for robot navigation ? This work investigates the...

Université de Neuchâtel

Détection et reconnaissance automatique de signaux routiers

Ouerhani, Nabil ; Corbat, O. ; Hügli, Heinz

In: Séminaire Research Day NAV, Capteurs de Navigation, 2004, p. 1-4

Le but de ce travail [1] est de concevoir, implémenter et tester une méthode de détection et de reconnaissance de panneaux routiers qui se base sur la vision par ordinateur. L’approche adoptée dans ce travail est constituée de deux modules principaux : un module de détection qui se base sur l’attention visuelle pour repérer des zones de la scène susceptibles de contenir des panneaux...

Université de Neuchâtel

Contribution of depth to visual attention: comparison of a computer model and human

Jost, Timothée ; Ouerhani, Nabil ; von Wartburg, Roman ; Müri, René ; Hügli, Heinz

In: Proceedings. Early cognitive vision workshop, 2004, p. 1-4

The research described in this paper aims at assessing the contribution of depth to visual attention. It reports the measurement of depth induced human visual attention derived from fixation patterns and preliminary results of a quantitative comparison with visual attention as modeled by different versions of a computational model. More specifically, a two-cues color model is compared to a...

Université de Neuchâtel

A Real Time Implementation of the Saliency-Based Model of Visual Attention on a SIMD Architecture

Ouerhani, Nabil ; Hügli, Heinz ; Burgi, Pierre-Yves ; Ruedi, Pierre-François

In: Pattern Recognition (In: Lecture Notes in Computer Science), 2002, vol. 2449, p. 282-289

Visual attention is the ability to rapidly detect the visually salient parts of a given scene. Inspired by biological vision, the saliency-based algorithm efficiently models the visual attention process. Due to its complexity, the saliency-based model of visual attention needs, for a real time implementation, higher computation resources than available in conventional processors. This work...

Université de Neuchâtel

Visual Attention Guided Seed Selection for Color Image Segmentation

Ouerhani, Nabil ; Archip, Neculai ; Hügli, Heinz ; Erard, Pierre-Jean

In: Conference Computer Analysis of Images and Patterns, 2001, vol. 2124, p. 630-637

The ”seeded region growing” (SRG) is a segmentation technique which performs an image segmentation with respect to a set of initial points, known as seeds. Given a set of seeds, SRG then grows the regions around each seed, based on the conventional region growing postulate of similarity of pixels within regions. The choice of the seeds is considered as one of the key steps on which the...

Université de Neuchâtel

A Visual Attention-Based Approach for Automatic Landmark Selection and Recognition

Ouerhani, Nabil ; Hügli, Heinz ; Gruener, G. ; Codourey, A.

In: Attention and Performance in Computational Vision (In: Lecture Notes in Computer Science), 2005, vol. 3368, p. 183-195

Visual attention refers to the ability of a vision system to rapidly detect visually salient locations in a given scene. On the other hand, the selection of robust visual landmarks of an environment represents a cornerstone of reliable vision-based robot navigation systems. Indeed, can salient scene locations provided by visual attention be useful for robot navigation? This work investigates the...

Université de Neuchâtel

A Model of Dynamic Visual Attention for Object Tracking in Natural Image Sequences

Ouerhani, Nabil ; Hügli, Heinz

In: Computational Methods in Neural Modeling. In: Lecture Notes in Computer Science, 2003, vol. 2686, no. 1, p. 702-709

Visual attention is the ability to rapidly detect the interesting parts of a given scene on which higher level computer vision tasks can focus. This paper reports a computational model of dynamic visual attention which combines static and dynamic features to detect salient locations in natural image sequences. Therefore, the model computes a map of interest—saliency map—related to static...

Université de Neuchâtel

Model Performance for Visual Attention in Real 3D Color Scenes

Hügli, Heinz ; Jost, Timothée ; Ouerhani, Nabil

In: Artificial Intelligence and Knowledge Engineering Applications: A Bioinspired Approach. Series: Lecture Notes in Computer Science, 2006, vol. 3562, p. 469-478

Visual attention is the ability of a vision system, be it biological or artificial, to rapidly detect potentially relevant parts of a visual scene. The saliency-based model of visual attention is widely used to simulate this visual mechanism on computers. Though biologically inspired, this model has been only partially assessed in comparison with human behavior. The research described in this...

Université de Neuchâtel

Linear vs. Nonlinear Feature Combination for Saliency Computation: A Comparison with Human Vision

Ouerhani, Nabil ; Bur, Alexandre ; Hügli, Heinz

In: Pattern Recognition, Series: Lecture Notes in Computer Science, 2006, vol. 4174, p. 314-323

In the heart of the computer model of visual attention, an interest or saliency map is derived from an input image in a process that encompasses several data combination steps. While several combination strategies are possible and the choice of a method influences the final saliency substantially, there is a real need for a performance comparison for the purpose of model improvement. This paper...