Results 1 - 10
of
27
Computational visual attention systems and their cognitive foundations: A survey
- ACM Trans. on Applied Perception
"... 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. H ..."
Abstract
-
Cited by 67 (4 self)
- Add to MetaCart
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 paper 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.
Interactions of visual attention and object recognition: computational modeling, algorithms, and psychophysics
, 2006
"... iii iv I would like to thank my advisor, Dr. Christof Koch, for his guidance and patience throughout the work that led to this thesis. He and the other members of my advisory committee, Dr. Pietro Perona, Dr. Laurent Itti, Dr. Shinsuke Shimojo, and Dr. Richard Andersen, helped me to stay focused whe ..."
Abstract
-
Cited by 21 (0 self)
- Add to MetaCart
iii iv I would like to thank my advisor, Dr. Christof Koch, for his guidance and patience throughout the work that led to this thesis. He and the other members of my advisory committee, Dr. Pietro Perona, Dr. Laurent Itti, Dr. Shinsuke Shimojo, and Dr. Richard Andersen, helped me to stay focused when I was about to embark on yet another project. It was an honor and pleasure to collaborate with Ueli Rutishauser and Dr. Fei-Fei Li at Caltech;
Neurally constrained modeling of perceptual decision making. Psychol Rev
, 2010
"... Stochastic accumulator models account for response time in perceptual decision-making tasks by assuming that perceptual evidence accumulates to a threshold. The present investigation mapped the firing rate of frontal eye field (FEF) visual neurons onto perceptual evidence and the firing rate of FEF ..."
Abstract
-
Cited by 19 (4 self)
- Add to MetaCart
Stochastic accumulator models account for response time in perceptual decision-making tasks by assuming that perceptual evidence accumulates to a threshold. The present investigation mapped the firing rate of frontal eye field (FEF) visual neurons onto perceptual evidence and the firing rate of FEF movement neurons onto evidence accumulation to test alternative models of how evidence is combined in the accumulation process. The models were evaluated on their ability to predict both response time distributions and movement neuron activity observed in monkeys performing a visual search task. Models that assume gating of perceptual evidence to the accumulating units provide the best account of both behavioral and neural data. These results identify discrete stages of processing with anatomically distinct neural populations and rule out several alternative architectures. The results also illustrate the use of neurophysiological data as a model selection tool and establish a novel framework to bridge computational and neural levels of explanation.
Efficient coding correlates with spatial frequency tuning in a model of V1 receptive field organization
, 2009
"... ..."
Attentive Classification
"... Abstract. In this paper, we present a two-step approach for object recognition based on principles of human perception: Attentive Classification. First, regions of interest are detected by a biologically motivated attention system. Second, these regions are analyzed by a fast classifier based on the ..."
Abstract
-
Cited by 2 (1 self)
- Add to MetaCart
(Show Context)
Abstract. In this paper, we present a two-step approach for object recognition based on principles of human perception: Attentive Classification. First, regions of interest are detected by a biologically motivated attention system. Second, these regions are analyzed by a fast classifier based on the Adaboost learning technique. Thus, the classification effort is restricted to a small data subset. The approach has two advantages over normal classification: First, the system becomes considerably faster, which is an important factor for real-time systems. Second, since the attention system is able to make use of top-down target-information, the combination of the systems yields a significant reduction of false detections for objects which are usually difficult to discriminate from the surrounding. We show the performance of the system in several experiments in robotic scenarios. The presented attentive classification system represents an important step towards effective general object recognition which is fast, robust and flexibly adaptable to a current task. 1
Real World Responses to Interactive Gesture Based Public Displays
"... Today, one does not have to travel far to find examples of digital signage, yet the adoption of interactive gesture based public displays remains quite rare. Subsequently, not much is known about them despite a large array of potential advantages. This paper contributes to our understanding of how p ..."
Abstract
-
Cited by 2 (0 self)
- Add to MetaCart
(Show Context)
Today, one does not have to travel far to find examples of digital signage, yet the adoption of interactive gesture based public displays remains quite rare. Subsequently, not much is known about them despite a large array of potential advantages. This paper contributes to our understanding of how people perceive, respond to and interact with such displays outside the controlled environment of a research lab. Unlike other works which have focused on isolated aspects of in-lab interaction, we present a detailed examination that addresses a wide range of responses to such a display- including those who ignore them completely. To facilitate our study we created an experimental coarse gesture based software suite and then deployed the system along with associated applications as part of an existing large scale public display network. Using this as a base, we executed four studies designed to passively observe the reactions of passers-by and followed these up with a fifth controlled experiment that compared the effectiveness of two different kinds of gesture in the context of menu item selection. To conclude, we present our keyfindings and highlight possible avenues of further study for the future of gesture based digital signage.
THE COMBINATION OF HMAX AND HOGS IN AN ATTENTION GUIDED FRAMEWORK FOR OBJECT LOCALIZATION
"... Abstract: Object detection and localization is a challenging task. Among several approaches, more recently hierarchical methods of feature-based object recognition have been developed and demonstrated high-end performance measures. Inspired by the knowledge about the architecture and function of the ..."
Abstract
-
Cited by 2 (2 self)
- Add to MetaCart
(Show Context)
Abstract: Object detection and localization is a challenging task. Among several approaches, more recently hierarchical methods of feature-based object recognition have been developed and demonstrated high-end performance measures. Inspired by the knowledge about the architecture and function of the primate visual system, the computational HMAX model has been proposed. At the same time robust visual object recognition was proposed using feature distributions, e.g. histograms of oriented gradients (HOGs). Since both models build upon an edge representation of the input image, the question arises, whether one kind of approach might be superior to the other. Introducing a new biologically inspired attention steered processing framework, we demonstrate that the combination of both approaches gains the best results. 1
Online Learning for Bootstrapping of Object Recognition and Localization in a Biologically Motivated Architecture
"... Abstract. We present a modular architecture for recognition and localization of objects in a scene that is motivated from coupling the ventral (“what”) and dorsal (“where”) pathways of human visual processing. Our main target is to demonstrate how online learning can be used to bootstrap the represe ..."
Abstract
-
Cited by 1 (1 self)
- Add to MetaCart
(Show Context)
Abstract. We present a modular architecture for recognition and localization of objects in a scene that is motivated from coupling the ventral (“what”) and dorsal (“where”) pathways of human visual processing. Our main target is to demonstrate how online learning can be used to bootstrap the representation from nonspecific cues like stereo depth towards object-specific representations for recognition and detection. We show the realization of the system learning objects in a complex realworld environment and investigate its performance. 1
