Université de Neuchâtel

Computer models of dynamic visual attention

Bur, Alexandre ; Hügli, Heinz (Dir.)

Thèse de doctorat : Université de Neuchâtel, 2009 ; Th. 2080.

To perceive the environment efficiently, the human vision system proceeds by selecting salient targets. The targets are explored successively by means of saccadic eye movements, which are responsible for shifting the fovea onto the current fixated target. Defined as selective attention, this mechanism can be seen as a preprocessing step, which reduces the amount of information that will be...

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

Dynamic visual attention: competitive versus motion priority scheme

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

In: Proceedings. International Conference Computer Vision Systems (ICVS), 2007, p. 1-10

Defined as attentive process in presence of visual sequences, dynamic visual attention responds to static and motion features as well. For a computer model, a straightforward way to integrate these features is to combine all features in a competitive scheme: the saliency map contains a contribution of each feature, static and motion. Another way of integration is to combine the features in a...

Université de Neuchâtel

Adaptive visual attention model

Hügli, Heinz ; Bur, Alexandre

In: Proceedings. Conference Image and Vision Computing New Zealand, 2007, p. 1-5

Visual attention, defined as the ability of a biological or artificial vision system to rapidly detect potentially relevant parts of a visual scene, provides a general purpose solution for low level feature detection in a vision architecture. Well considered for its universal detection behaviour, the general model of visual attention is suited for any environment but inferior to dedicated feature...

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

Optimal Cue Combination for Saliency Computation: A Comparison with Human Vision

Bur, Alexandre ; Hügli, Heinz

In: Nature Inspired Problem-Solving Methods in Knowledge Engineering (In: Lecture Notes in Computer Science), 2007, vol. 4528, p. 109-118

The computer model of visual attention derives an interest or saliency map from an input image in a process that encompasses several data combination steps. While several combination strategies are possible, not all perform equally well. This paper compares main cue combination strategies by measuring the performance of the considered models with respect to human eye movements. Six main...

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...

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...