Probabilistic Decisions in Production Net An Example from Vehicle Recognition

Abstract

A structural knowledge-based vehicle recognition method is modified yielding a new probabilistic foundation for the decisions. The method uses a pre-calculated set of hidden line projected views of articulated polyhedral models of the vehicles. Model view structures are set into correspondence with structures composed from edge lines in the image. The correspondence space is searched utilizing a 4D Houghtype accumulator. Probabilistic models of the background and the error in the measurements of the image structures lead to likelihood estimations that are used for the decision. The likelihood is propagated along the structure of the articulated model. The system is tested on a cluttered outdoor scene. To ensure anytime performance the recognition process is implemented in a data-driven production system.

Pose Estimation from Airborne Video Sequences Using a Structural Approach for the Construction of Homographies and Fundamental Matrices

“…Thus spurious calculations are avoided. Originally the production net approach has been invented for dealing with costly object recognition tasks in an accumulative way using affirmative intermediate results [10]. In pose estimation intermediate results may also be mutually competing.…”

Cluster Analysis and Priority Sorting in Huge Point Clouds for Building Reconstruction

“…The similarity condition for n j and n i is used for faster query handling and the simple threshold t 0 for ≈ in the coplanarity query is a rough approximation. [5,8] For t 0 we used 6 cm here, which is double of what has been used in Eq. 1.…”