A statistical study of the correlation between interest points and gaze points

Nauge, Michaël; Larabi, Mohamed–Chaker; Fernández-Maloigne, Christine

doi:10.1117/12.912089

Cited by 11 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This choice can be justified by the ability of these interest points to capture and predict salient features (signal ruptures) on a given image. Moreover, the similarity between interest points (Harris, SIFT and SURF) and gaze points, for a given set of parameters, has been demonstrated by Nauge et al [9]. Therefore, our spatial saliency map is purely based on interest points, without accounting for the influence of central bias and top-down information.…”

Section: Spatial Dimensionmentioning

confidence: 90%

“…Lowe et al showed in his work that the properties of SIFT interest points are similar to those of neurones in the inferior temporal cortex [7]. Moreover, Nauge et al have shown that there is a correlation between interest points and gaze points [9] depending on the parameters tuning. Accordingly, it appears possible to rely on interest points for modeling visual attention.…”

Section: Introductionmentioning

confidence: 98%

See 1 more Smart Citation

Spatio-temporal modeling of visual attention for stereoscopic 3D video

Iatsun¹,

Larabi²,

Fernández-Maloigne³

2014

2014 IEEE International Conference on Image Processing (ICIP)

Self Cite

View full text Add to dashboard Cite

International audienceModeling visual attention is an important stage for the optimization of image processing systems nowadays. Several models have been already developed for 2D static and dynamic content, but only few attempts can be found for stereoscopic 3D content. In this work we propose a saliency model for stereoscopic 3D video. This model is based the fusion of three maps i.e. spatial, temporal and depth. It relies on interest point features known for being close to human visual attention. Moreover, since 3D perception is mostly based on monocular cues, depth information is obtained using a monocular model predicting the depth position of objects. Several fusion strategies have been experimented in order to determine the best match for our model. Finally, our approach has been validated using state-of-the-art metrics in comparison to attention maps obtained by eye-tracking experiments, and showed good performance

show abstract

Section: Spatial Dimensionmentioning

confidence: 90%

Section: Introductionmentioning

confidence: 98%

Spatio-temporal modeling of visual attention for stereoscopic 3D video

Iatsun¹,

Larabi²,

Fernández-Maloigne³

2014

2014 IEEE International Conference on Image Processing (ICIP)

Self Cite

View full text Add to dashboard Cite

show abstract

“…They have been selected thanks to their capacity to predict a signal rupture on an image, that is often correspond to a salient feature. Furthermore, Nauge et al proved in their work [31] the resemblance between fixation points and interest points (Harris, SIFT and SURF) by tuning the settings of the latter. For our purposes, we extract the salient features using only the interest points, no center bias and top-down information has been considered.…”

Section: Spatial Featuresmentioning

confidence: 99%

“…A new direction for saliency evaluation has been opened by the notion of interest points, like Harris detector [16], SIFT (Scale-Invariant Features Transformation) [27] or SURF (Speeded Up Robust Features) [2]. Nauge et al in their work [31] with multiple tests showed the correlation between gaze and interest points thanks to their tuning parameters. The same authors proposed a saliency model for 2D still images based on the properties of interest points [30].…”

Section: Introductionmentioning

confidence: 99%

Visual attention modeling for 3D video using neural networks

Iatsun¹,

Larabi²,

Fernández-Maloigne³

2014

2014 International Conference on 3D Imaging (IC3D)

Self Cite

View full text Add to dashboard Cite

International audienceVisual attention is one of the most important mechanisms in the human visual perception. Recently, its modeling becomes a principal requirement for the optimization of the image processing systems. Numerous algorithms have already been designed for 2D saliency prediction. However, only few works can be found for 3D content. In this study, we propose a saliency model for stereoscopic 3D video. This algorithm extracts information from three dimensions of content, i.e. spatial, temporal and depth. This model benefits from the properties of interest points to be close to human fixations in order to build spatial salient features. Besides, as the perception of depth relies strongly on monocular cues, our model extracts the depth salient features using the pictorial depth sources. Since weights for fusion strategy are often selected in ad-hoc manner, in this work, we suggest to use a machine learning approach. The used artificial Neural Network allows to define adaptive weights based on the eye-tracking data. The results of the proposed algorithm are tested versus ground-truth information using the state-of-the-art techniques

show abstract