A saliency-based search mechanism for overt and covert shifts of visual attention-英文文献.pdf
- 1、本文档共18页,可阅读全部内容。
- 2、原创力文档(book118)网站文档一经付费(服务费),不意味着购买了该文档的版权,仅供个人/单位学习、研究之用,不得用于商业用途,未经授权,严禁复制、发行、汇编、翻译或者网络传播等,侵权必究。
- 3、本站所有内容均由合作方或网友上传,本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺!文档内容仅供研究参考,付费前请自行鉴别。如您付费,意味着您自己接受本站规则且自行承担风险,本站不退款、不进行额外附加服务;查看《如何避免下载的几个坑》。如果您已付费下载过本站文档,您可以点击 这里二次下载。
- 4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等,请点击“版权申诉”(推荐),也可以打举报电话:400-050-0827(电话支持时间:9:00-18:30)。
查看更多
A saliency-based search mechanism for overt and covert shifts of visual attention-英文文献
Vision Research 40 (2000) 1489–1506
locatevisres
A saliency-based search mechanism for overt and covert shifts of
visual attention
Laurent Itti, Christof Koch *
Computation and Neural Systems Program, Diision of Biology, California Institute of Technology, Mail -Code 139-74, Pasadena,
CA 91125, USA
Received 27 May 1999; received in revised form 19 July 1999
Abstract
Most models of visual search, whether involving overt eye movements or covert shifts of attention, are based on the concept
of a saliency map, that is, an explicit two-dimensional map that encodes the saliency or conspicuity of objects in the visual
environment. Competition among neurons in this map gives rise to a single winning location that corresponds to the next attended
target. Inhibiting this location automatically allows the system to attend to the next most salient location. We describe a detailed
computer implementation of such a scheme, focusing on the problem of combining information across modalities, here
orientation, intensity and color information, in a purely stimulus-driven manner. The model is applied to common psychophysical
stimuli as well as to a very demanding visual search task. Its successful performance is used to address the extent to which the
primate visual system carries out visual search via one or more such saliency maps and how this can be tested. © 2000 Elsevier
Science Ltd. All rights reserved.
Keywords: Visual atten
您可能关注的文档
- A Learning Algorithm for Continually Running Fully Recurrent Neural Networks-英文文献.pdf
- A Limited Memory Algorithm for Bound Constrained Optimization-英文文献.pdf
- A Long-Memory Property of Stock Market Returns and a New Model-英文文献.pdf
- A message ferrying approach for data delivery in sparse mobile ad hoc networks-英文文献.pdf
- A learning algorithm for Boltzmann machines-英文文献.pdf
- A Meta-Analytic Review of Experiments Examining the Effects of Extrinsic Rewards on Intrinsic Motivation-英文文献.pdf
- A Model of Saliency-based Visual Attention for Rapid Scene Analysis-英文文献.pdf
- A New Extension of the Kalman Filter to Nonlinear Systems-英文文献.pdf
- A New Kind of Science-英文文献.pdf
- A Morphable Model For The Synthesis Of 3D Faces-英文文献.pdf
文档评论(0)