Expectation-based selective attention for visual monitoring and control of a robot vehicle Export

@article{BAL97a, abstract = {Reliable vision-based control of an autonomous vehicle requires the ability to focus attention on the important features in an input scene. Previous work with an autonomous lane following system, ALVINN (Pomerleau, 1993), has yielded good results in uncluttered conditions. This paper presents an artificial neural network based learning approach for handling difficult scenes which will confuse the ALVINN system. This work presents a mechanism for achieving task-specific focus of attention by exploiting temporal coherence. A saliency map, which is based upon a computed expectation of the contents of the inputs in the next time step, indicates which regions of the input retina are important for performing the task. The saliency map can be used to accentuate the features which are important for the task, and de-emphasize those which are not.}, author = {Baluja, S. and Pomerleau, D. A.}, citeulike-article-id = {3201328}, citeulike-linkout-0 = {http://dx.doi.org/10.1016/S0921-8890(97)00046-8}, citeulike-linkout-1 = {http://www.ingentaconnect.com/content/els/09218890/1997/00000022/00000003/art00046}, doi = {10.1016/S0921-8890(97)00046-8}, issn = {0921-8890}, journal = {Robotics and Autonomous Systems}, keywords = {application, attention, robotics, vision}, month = {December}, pages = {329--344}, posted-at = {2008-09-07 20:37:27}, priority = {0}, publisher = {Elsevier}, title = {Expectation-based selective attention for visual monitoring and control of a robot vehicle}, url = {http://dx.doi.org/10.1016/S0921-8890(97)00046-8}, year = {1997} }

TY - JOUR ID - BAL97a L3 - citeulike-article-id:3201328 N2 - Reliable vision-based control of an autonomous vehicle requires the ability to focus attention on the important features in an input scene. Previous work with an autonomous lane following system, ALVINN (Pomerleau, 1993), has yielded good results in uncluttered conditions. This paper presents an artificial neural network based learning approach for handling difficult scenes which will confuse the ALVINN system. This work presents a mechanism for achieving task-specific focus of attention by exploiting temporal coherence. A saliency map, which is based upon a computed expectation of the contents of the inputs in the next time step, indicates which regions of the input retina are important for performing the task. The saliency map can be used to accentuate the features which are important for the task, and de-emphasize those which are not. JF - Robotics and Autonomous Systems SN - 0921-8890 EP - 344 TI - Expectation-based selective attention for visual monitoring and control of a robot vehicle PB - Elsevier SP - 329 KW - application KW - attention KW - robotics KW - vision AU - Baluja, S AU - Pomerleau, DA PY - 1997/12// UR - http://dx.doi.org/10.1016/S0921-8890(97)00046-8 ER -