Results 1 -
8 of
8
Joint Attention by Gaze Interpolation and Saliency
"... Abstract—Joint attention, which is the ability of coordination of a common point of reference with the communicating party, emerges as a key factor in various interaction scenarios. This paper presents an image-based method for establishing joint attention between an experimenter and a robot. The pr ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
(Show Context)
Abstract—Joint attention, which is the ability of coordination of a common point of reference with the communicating party, emerges as a key factor in various interaction scenarios. This paper presents an image-based method for establishing joint attention between an experimenter and a robot. The precise analysis of the experimenter’s eye region requires stability and high-resolution image acquisition, which is not always available. We investigate regression-based interpolation of the gaze direction from the head pose of the experimenter, which is easier to track. Gaussian process regression and neural networks are contrasted to interpolate the gaze direction. Then, we combine gaze interpolation with image-based saliency to improve the target point estimates and test three different saliency schemes. We demonstrate the proposed method on a human–robot interaction scenario. Cross-subject evaluations, as well as experiments under adverse conditions (such as dimmed or artificial illumination or motion blur), show that our method generalizes well and achieves rapid gaze estimation for establishing joint attention. Index Terms—Developmental robotics, gaze following, head pose estimation, joint visual attention, saliency, selective attention. I.
Modulating Vision with Motor Plans: A Biologically-inspired Efficient Allocation of Visual Resources
"... Abstract—This paper presents a novel, biologically-inspired, approach for an efficient management of computational resources for visual processing. In particular, we modulate a visual “attentional landscape ” with the motor plans of a robot. The attentional landscape is a more recent, general and a ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
(Show Context)
Abstract—This paper presents a novel, biologically-inspired, approach for an efficient management of computational resources for visual processing. In particular, we modulate a visual “attentional landscape ” with the motor plans of a robot. The attentional landscape is a more recent, general and a more complex concept of an arrangement of spatial attention than a simple ‘‘attentional spotlight ” or a ‘‘zoom-lens ” model of attention. A higher attention priority for visual processing must be given to manipulation-relevant parts of the visual field, in contrast with other, manipulation-irrelevant, parts. Hence, in our model visual attention is not exclusively defined in terms of visual saliency in color, texture or intensity cues, it is rather modulated by motor (manipulation) programs. This computational model is supported by recent experimental findings in visual neuroscience and physiology. We show how this approach can be used to efficiently distribute limited computational resources devoted to visual processing, which is very often the computational bottleneck in a robot system. The model offers a view on the well-know concept of visual saliency that has not been tackled so far, thus this approach can offer interesting alternative prospects not only for robotics, but also for computer vision, physiology and neuroscience. The proposed model is validated in a series of experiments conducted with the iCub robot, both using the simulator and with the real robot. I.
Fusion of Saliency Maps for Visual Attention Selection in Dynamic Scenes
"... Abstract—Human vision system can optionally process the visual information and adjust the contradiction between the limited resources and the huge visual information. Building attention models similar to human visual attention system should be very beneficial to computer vision and machine intellige ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract—Human vision system can optionally process the visual information and adjust the contradiction between the limited resources and the huge visual information. Building attention models similar to human visual attention system should be very beneficial to computer vision and machine intelligence; meanwhile, it has been a challenging task due to the complexity of human brain and limited understanding of the mechanisms underlying the human attention system. Previous studies emphasized on static attention, however the motion features, which are playing key roles in human attention system intuitively, have not been well integrated into the previous models. Motion features such as motion direction are assumed to be processed within the dorsal visual and the dorsal auditory pathways and there is no systematic approach to extract the motion cues well so far. In this paper, we proposed a generic Global Attention Model
Joint Attention by Gaze Interpolation and Saliency
"... Abstract—Joint attention, which is the ability of coordination of a common point of reference with the communicating party, emerges as a key factor in various interaction scenarios. This paper presents an image-based method for establishing joint attention between an experimenter and a robot. The pr ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract—Joint attention, which is the ability of coordination of a common point of reference with the communicating party, emerges as a key factor in various interaction scenarios. This paper presents an image-based method for establishing joint attention between an experimenter and a robot. The precise analysis of experimenter’s eye region requires stability and high resolution image acquisition, which is not always available. We investigate regression-based interpolation of the gaze direction from the head pose of the experimenter, which is easier to track. Gaussian process regression and neural networks are contrasted to interpolate the gaze direction. Then we combine gaze interpolation with image-based saliency to improve the target point estimates and test three different saliency schemes. We demonstrate the proposed method on a human-robot interaction scenario. Cross-subject evaluations, as well as experiments under adverse conditions (such as dimmed or artificial illumination or motion blur) show that our method generalizes well and achieves rapid gaze estimation for establishing joint attention. Index Terms—Joint visual attention, head pose estimation, gaze following, saliency, developmental robotics, selective attention. I.
Signal Processing: Image Communication] (]]]])]]]–]]] Contents lists available at SciVerse ScienceDirect Signal Processing: Image Communication
"... journal homepage: www.elsevier.com/locate/image Gaze shift behavior on video as composite information foraging G. Boccignone a,n, M. Ferraro b ..."
Abstract
- Add to MetaCart
journal homepage: www.elsevier.com/locate/image Gaze shift behavior on video as composite information foraging G. Boccignone a,n, M. Ferraro b
Editorial
"... For the first edition of the joint IEEE ICDL-EpiRob conference, we will have keynote presentations by four eminent scientists from the hard, the wet and the human sciences: Andrew Barto (reinforcement learning and cognitive robotics), Erin Schuman (neuroscience), Jean Mandler and Michael Tomasello ( ..."
Abstract
- Add to MetaCart
For the first edition of the joint IEEE ICDL-EpiRob conference, we will have keynote presentations by four eminent scientists from the hard, the wet and the human sciences: Andrew Barto (reinforcement learning and cognitive robotics), Erin Schuman (neuroscience), Jean Mandler and Michael Tomasello (developmental psychology). This interdisciplinarity, focused around a shared set of core questions about development, is an important strength of our field: building bridges that allow for mixing various scientific cultures fosters creativity and insight. I encourage all of you to come and participate at ICDL-EpiRob which will happen in Frankfurt, 24 th-27 th August in Frankfurt, Germany. This interdisciplinarity is also strongly reflected in the dialog of this month, initiated by John Weng and continuing the dialog on symbol grounding held in this newsletter last year. John Weng asked ―Are natural languages symbolic in the brain?‖. This question directly addresses a quite controversial but fundamental issue: is the symbol grounding problem a real problem? Are symbols really fundamental for understanding human cognitive development, or are they just a modern conceptual invention of modern human culture? The answers, written by Stevan Harnad, Jürgen Schmidhüber, Aaron Sloman, Angelo Cangelosi, and Yuuya Sugita and Martin Butz, interestingly mix philosophical and mathematical arguments, showing how recent technical advances can illuminate old questions and vice versa, how philosophical theories can either question or support the assumptions and concepts of modern technical approaches.
Universidad Autónoma de Cd. Juárez
"... Abstract—Autonomous robotic exploration of unstructured and highly dynamic environments is a complex task, particularly, in underwater environments. An underwater robot needs to quickly detect a region of interest and then track it for a certain period of time in order to plan for the next trajector ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract—Autonomous robotic exploration of unstructured and highly dynamic environments is a complex task, particularly, in underwater environments. An underwater robot needs to quickly detect a region of interest and then track it for a certain period of time in order to plan for the next trajectory; all of these while keeping its motion control stable. In this paper, we present a novel approach that robustly detects and tracks regions of interest in underwater video streams at frame rate. First, to detect relevant regions in an image, our approach combines two existing visual attention schemes with some improvements to adjust it to underwater scenes. Second, a scaled version of the resulting image is segmented by using a superpixel segmentation algorithm, and each relevant point is associated to a superpixel descriptor. The descriptor helps to track the same region as long as it results interesting for the visual attention algorithm. The experimental results demonstrate that our approach is robust when tested on different videos of underwater explorations. Keywords-visual attention models; regions of interest; super-pixel segmentation; feature tracking; underwater vision I.
1A Survey of the Ontogeny of Tool Use: from Sensorimotor Experience to Planning
"... Abstract—In this paper we review current knowledge on the development of tool use in infants in order to provide relevant information for cognitive developmental roboticists aiming to design artificial systems which develop tool use abilities. This in-formation covers (1) sketching developmental pat ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract—In this paper we review current knowledge on the development of tool use in infants in order to provide relevant information for cognitive developmental roboticists aiming to design artificial systems which develop tool use abilities. This in-formation covers (1) sketching developmental pathways leading to tool use competences, (2) the characterisation of learning and test situations, (3) the crystallisation of seven mechanisms underlying the developmental process and (4) the formulation of a number of challenges and recommendations for designing artificial systems that exhibit tool use abilities in complex contexts. Index Terms—developmental psychology, infant behaviour, tool use, developmental robotics. I.
