A distributed 3D scene recognition system based on a multilevel representation of object models and signals is described. The solution to a recognition problem is obtained through a set of object-observation couples at the different abstraction levels. The various system modules exchange two kinds of information: 1) top-down messages, which are used to communicate to lower modules the predictions made on the basis of a priori knowledge on the application domain, 2) bottom-up messages, which are used to communicate to higher modules the evidence supporting possible local solutions. A local scheme for the combination of message flows is defined, and messages are interpreted by using a probabilistic network of estimators of random variables. The proposed model is suitable for addressing the problem of distributed geometric reasoning aimed at 3D road scene recognition by an autonomous vehicle. Recognition results include road detection and obstacle localization, together with a study of the relative computational load required by different modules of the system. The proposed approach is currently simulated on a workstation, while an effective implementation on board of an autonomous vehicle is under development in the contest of the CEC-EUREKA Prometheus project.
A DISTRIBUTED APPROACH TO 3D ROAD SCENE RECOGNITION
FORESTI, Gian Luca;
1994-01-01
Abstract
A distributed 3D scene recognition system based on a multilevel representation of object models and signals is described. The solution to a recognition problem is obtained through a set of object-observation couples at the different abstraction levels. The various system modules exchange two kinds of information: 1) top-down messages, which are used to communicate to lower modules the predictions made on the basis of a priori knowledge on the application domain, 2) bottom-up messages, which are used to communicate to higher modules the evidence supporting possible local solutions. A local scheme for the combination of message flows is defined, and messages are interpreted by using a probabilistic network of estimators of random variables. The proposed model is suitable for addressing the problem of distributed geometric reasoning aimed at 3D road scene recognition by an autonomous vehicle. Recognition results include road detection and obstacle localization, together with a study of the relative computational load required by different modules of the system. The proposed approach is currently simulated on a workstation, while an effective implementation on board of an autonomous vehicle is under development in the contest of the CEC-EUREKA Prometheus project.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
