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

SLAM – Map Building and Navigation via ROS#

The presented work describes a ROS based control system of a Turtlebot robot for mapping and navigation in indoor environments. It presents the navigation of Turtlebot in self-created environment. The mapping process is...

An Analysis of Archive Update for Vector Evaluated Particle Swarm Optimization

Multi-objective optimization problem is commonly found in many real world problems. In computational intelligence, Particle Swarm Optimization (PSO) algorithm is a popular method in solving optimization problems. An exte...

A Modified Flower Pollination Algorithm forFractional Programming Problems

Flower pollination algorithm is a new nature-inspired algorithm, based on the characteristics of flowering plants. In this paper, a new method is developed chaos-based Flower Pollination Algorithm (CFPA) to solve Fractio...

Rainfall estimation for the south shore of the Mediterranean Sea using MSG infrared images

The objective of this paper is the estimation of rainfall over the Algerian territory using MSG (Meteosat Second Generation) infrared data. To achieve this aim, we applied a calibrated GPI (GOES Precipitation Index) appr...

Download PDF file
  • EP ID EP811
  • DOI 10.18201/ijisae.2016426384
  • Views 474
  • 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