Computer vision systems are becoming more and more anthropomorphic. In addition t o taking an active vision approach, researchers are now investigating robot heads with biologically motivated space-variant sensors. We have designed such an exploring eye system for robot gaze control when observing an arbitrary scene. Our approach uses "retinal" images constructed from overlapping receptive fields that are mapped to form log-polar "cortical" images, We have implemented this system on a parallel SIMD machine using an eficient parallelization algorithm. In order t o demonstrate our approach, we have formulated various types of attentional operators that are used to select interest points t o drive the gaze control mechanism. We show that our system eficiently integrates images from space-variant snapshots in an arbitrary natural environment.
We present in this paper a fasi method to delermine the posiiion and orieniaiion of a mobile robol. An external vision system covering the work area is used o localize the roboL A known paflern composed of coplanar poinis fixed on the robot is exiraced from a single image and used o locate Ihe robot in 3D. Assuming iha the robol's movemenis are locally planar, the exiracled poinis are projecled on ike paUern's plane, estimaied from the previous localization. An iterative ioop to match paflern points and to localize the paUern is then performed. From four idenlified points, a 3D localization is possible.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.