350 rub
Journal Neurocomputers №2 for 2010 г.
Article in number:
The model of visual system multilevel presetting for three-dimensional object recognition
Authors:
M.V. Petrushan
Abstract:
The interaction between active observer and environment is concerned with interpretation ambiguity of visual signals. The ambiguity can be treated as action motivation. Perspective picture variations on sensitive visual matrix can be concerned with dynamic environment or visual system movements. To define variation components, corresponded to dynamic environmental processes, observer need to have internal environment model and to forecast perspective picture variations while movement. If forecast do not correspond to observed perspective picture, the environment is dynamic. Another type of ambiguity appears in recognition tasks. Some objects have the same perspective projections and have to be observed from different points of view to be recognized. Therefore recognition process is treated as procedures sequence: forecast, verification, decision. Three-dimensional objects representation is possible with active monocular sensor or with binocular visual system. In any case the correspondent point problem has to be solved to make three-dimensional objects representation. Correspondent points have to be found on the perspective pictures sequence. Three-dimensional point coordinates (in internal coordinate system) can be defined if two perspective correspondent points are found and observer movement vector is known. Observer movements set restriction rules to forecast movements of correspondent points on perspective projections. Correspondent points have to be searched on parallel lines if visual system configuration is binocular and have to be searched on radial rays if monocular visual system moves in view direction. Forecast is modeled as visual system presetting. If presetting procedures are involved in cognitive cycle the dynamic environment perception can be performed.
Pages: 47-53
References
  1. Hans Jacob S. Feder1, John J. Leonard, Christopher M. Smith.Adaptive Mobile Robot Navigation and Mapping // International Journal of Robotics Research, Special Issue on Field and Service Robotics. 1999. July.
  2. Dario Floreano, Toshifumi Kato, Davide Marocco, Eric Sauser. Coevolution of active vision and feature selection // Biol. Cybern. 90. Springer-Verlag. 2004. P. 218-228.
  3. Wershofen K. P., Graefe V. An Intelligent Autonomous Vehicle Guided by Behavior-Based Navigation // IFToMM-jc International Symposium on Theory of Machines and Mechanisms. Nagoya. 1992. P. 244 - 249.
  4. Самарин А.И., Шевченко М.А.Алгоритм автоматического построения описаний объектов сцены в базисе рассматривающих движений фовеального сенсора // Сборник научных трудов. В 2-х частях. Ч.1. М.: МИФИ. 2002. С. 85 - 94.
  5. Петрушан М.В. Алгоритмы стереокинетического восприятия в оценке параметров объемных зрительных сцен // В сборнике «Молодежь 21 века - будущее российской науки». Ростов-на-Дону: Изд. РГУ. 2004. С. 54 - 55.
  6. Лампинен Ю., Шевченко М.А., Петрушан М.В., Самарин А.И. Модель формирования карты местности в процессе активного взаимодействия робота со средой // В мат. 7-й Всероссийской научно-технической конференции Нейроинформатика. М.: МИФИ. 2005. С. 155 - 164.