Year: 2010
Type: dissertation
Abstract: Scene understanding is an essential element involved in the exploration of an unknown territory using mobile robots.In this regard, scene understanding refers to the identification and localization of elements in the scene.When the scene is dynamic by nature or has objects that move around, they need to be characterized and discriminated from the static elements, which is essential for the SLAM (Simultaneous Localization And Mapping) process when external global localization information is not available.We present some techniques and algorithms to accomplish these goals with regard to a scenario where we have a co-operative of robots equipped with a monocular camera having three degrees of freedom (x,y,), observing a dynamic scene.The objectives are to use the static elements of the scene for self-localization of robots and try to estimate the velocity, trajectory and structure of moving objects.The latter is much more difficult to solve than the former.We discuss some metrics that have been identified that could be used for the co-ordination of robots and develop optimized steering mechanisms, which would help reduce the errors associated with the estimated parameters.v
Author: Franklin, Stephen Jeyapaul,
Institution: University of South Australia
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: University of South Australia
OpenAlex ID: W7217595512
