A region covariances-based visual attention model for RGB-D images

Abstract

Existing computational models of visual attention generally employ simple image features such as color, intensity or orientation to generate a saliency map which highlights the image parts that attract human attention. Interestingly, most of these models do not process any depth information and operate only on standard two-dimensional RGB images. On the other hand, depth processing through stereo vision is a key characteristics of the human visual system. In line with this observation, in this study, we propose to extend two state-of-the-art static saliency models that depend on region covariances to process additional depth information available in RGB-D images. We evaluate our proposed models on NUS-3D benchmark dataset by taking into account different evaluation metrics. Our results reveal that using the additional depth information improves the saliency prediction in a statistically significant manner, giving more accurate saliency maps.

Authors and Affiliations

Erkut Erdem*| Hacettepe University. Department of Computer Engineering, Ankara, Turkey – TR-06800

Keywords

Related Articles

Particle Swarm Optimization Based Approach for Location Area Planning in Cellular Networks

Location area planning problem plays an important role in cellular networks because of the trade-off caused by paging and registration signalling (i.e., location update). Compromising between the location update and the...

A highly Reliable and Fully Automated Classification System for Sleep Apnea Detection

Sleep apnea (SA) in the form of Obstructive sleep apnea (OSA) is becoming the most common respiratory disorder during sleep, which is characterized by cessations of airflow to the lungs. These cessations in breathing mus...

GA Based Selective Harmonic Elimination for Five-Level Inverter Using Cascaded H-bridge Modules

Multilevel inverters (MLI) have been commonly used in industry especially to get quality output voltage in terms of total harmonic distortion (THD). In addition, development in semiconductor technology and advanced modul...

Structure-Texture Decomposition of RGB-D Images

In this paper, we study the problem of separating texture from structure in RGB-D images. Our structure preserving image smoothing operator is based on the region covariance smoothing (RCS) method in [16] that we present...

The Classification of Eye State by Using kNN and MLP Classification Models According to the EEG Signals

What is widely used for classification of eye state to detect human’s cognition state is electroencephalography (EEG). In this study, the usage of EEG signals for online eye state detection method was proposed. In this s...

Download PDF file
  • EP ID EP811
  • DOI 10.18201/ijisae.2016426384
  • Views 449
  • Downloads 25

How To Cite

Erkut Erdem* (2016). A region covariances-based visual attention model for RGB-D images. International Journal of Intelligent Systems and Applications in Engineering, 4(4), 128-134. https://europub.co.uk/articles/-A-811