Computational visual attention systems and their cognitive foundations

Abstract

Based on concepts of the human visual system, computational visual attention systems aim to detect regions of interest in images. Psychologists, neurobiologists, and computer scientists have investigated visual attention thoroughly during the last decades and profited considerably from each other. However, the interdisciplinarity of the topic holds not only benefits but also difficulties: Concepts of other fields are usually hard to access due to differences in vocabulary and lack of knowledge of the relevant literature. This article aims to bridge this gap and bring together concepts and ideas from the different research areas. It provides an extensive survey of the grounding psychological and biological research on visual attention as well as the current state of the art of computational systems. Furthermore, it presents a broad range of applications of computational attention systems in fields like computer vision, cognitive systems, and mobile robotics. We conclude with a discussion on the limitations and open questions in the field.

Multispectral image analysis for object recognition and classification

“…Such systems are characterized as "bio-inspired" if their design, implementation and results can be correlated or matched to biological research findings. A brief overview of the human visual system is provided in [9] and states that light captured by the human eye advances through various stages in the brain starting with a coarse detection of color, contrast [10] and orientation. This process is also known as early vision.…”

Semi-task-dependent and uncertainty-driven world model maintenance

“…A similar combined bottom-up/top-down approach can be found in other work on attention selection literature such as (Rasolzadeh et al 2007;Xu et al 2009). The survey of Frintrop et al (2010) provides an extensive overview of visual attention systems. Our aim differs from the attention selection literature in that we focus on steering an autonomous robot with the purpose of maintaining a world model, rather than based on the current sensor data and what appears 'interesting' within this data.…”

Fast 3D Salient Region Detection in Medical Images Using GPUs

“…Perceiving this information in its entirety is a hard task. The human brain has evolved neurological processes that selectively focus atten- * Currently with vizury.com † Currently with the Department of Computer Science, University of British Columbia tion [10] at one salient frequency, scale or image location at a time. In order to enable processing of large amounts of data, it is natural to automate these neurological processes.…”