A Rarity-Based Visual Attention Map - Application to Texture Description

Mancaş, Matei; Mancas-Thillou, Céline; Gosselin, Bernard; Macq, Benoît

doi:10.1109/icip.2006.312489

Cited by 29 publications

(29 citation statements)

References 8 publications

(8 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Over the past decade, many different algorithms have been proposed to compute visual saliency maps from digital imagery. 17,[28][29][30][31][32][33][34][35][36][37][38][39][40][41][42][43][44][45][46][47] These algorithms typically transform a given input image into a scalar-valued map in which local signal intensity corresponds to local image saliency. 33,45 In an extensive comparative evaluation study 48 we recently established that the maximum value over the target support computed by Achanta's Frequency Tuned Saliency model 45 is currently the best saliency-based predictor of human visual search and detection performance in complex realistic scenarios.…”

Section: Frequency-tuned Saliencymentioning

confidence: 99%

Urban camouflage assessment through visual search and computational saliency

Toet

Hogervorst

2012

Opt. Eng

View full text Add to dashboard Cite

Abstract. We present a new method to derive a multiscale urban camouflage pattern from a given set of background image samples. We applied this method to design a camouflage pattern for a given (semi-arid) urban environment. We performed a human visual search experiment and a computational evaluation study to assess the effectiveness of this multiscale camouflage pattern relative to the performance of 10 other (multiscale, disruptive and monotonous) patterns that were also designed for deployment in the same operating theater. The results show that the pattern combines the overall lowest detection probability with an average mean search time. We also show that a frequency-tuned saliency metric predicts human observer performance to an appreciable extent. This computational metric can therefore be incorporated in the design process to optimize the effectiveness of camouflage patterns derived from a set of background samples.

show abstract

Section: Frequency-tuned Saliencymentioning

confidence: 99%

Urban camouflage assessment through visual search and computational saliency

Toet

Hogervorst

2012

Opt. Eng

View full text Add to dashboard Cite

show abstract

“…As we already stated in [9] and [14] a feature does not attract attention by itself: bright and dark, locally contrasted areas or not, red or blue can equally attract human attention depending on their context. In the same way, motion can be as interesting as the lack of motion depending on the context.…”

Section: A Rarity-based Approachmentioning

confidence: 82%

Gesture Saliency: A Context-Aware Analysis

Mancaş

Glowinski

Volpe

et al. 2010

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. This paper presents a motion attention model that aims at analyzing gesture saliency using context-related information at three different levels. At the first level, motion features are compared in the spatial context of the current video frame; at the intermediate level, salient behavior is analyzed on a short temporal context; at the third level, computation of saliency is extended to longer time windows. An attention/saliency index is computed at the three levels based on an information theory approach. This model can be considered as a preliminary step towards context-aware expressive gesture analysis.

show abstract

“…All those words are actually synonyms and they all amount to searching for some unusual features in a given context which is here a spatial one. The proposed method is an evolution of [7,8,9] and also uses the local contrast and global rarity measure. In the next section, the RARE algorithm is described and a comparison with the state of the art methods is proposed.…”

Section: Introductionmentioning

confidence: 99%

Rare: A new bottom-up saliency model

Riche

Mancaş

Gosselin

et al. 2012

2012 19th IEEE International Conference on Image Processing

Self Cite

View full text Add to dashboard Cite

In this paper, a new bottom-up visual saliency model is proposed. Based on the idea that locally contrasted and globally rare features are salient, this model will be called "RARE" in the following sections. It uses a sequential bottom-up features extraction where first low-level features as luminance and chrominance are computed and from those results medium-level features as image orientations are extracted. A qualitative and a quantitative comparison are achieved on a 120 images dataset. The RARE algorithm powerfully predicts human fixations compared with most of the freely available saliency models.

show abstract

A Rarity-Based Visual Attention Map - Application to Texture Description

Cited by 29 publications

References 8 publications

Urban camouflage assessment through visual search and computational saliency

Urban camouflage assessment through visual search and computational saliency

Gesture Saliency: A Context-Aware Analysis

Rare: A new bottom-up saliency model

Contact Info

Product

Resources

About