Data fusion is a process of combining evidence from different information sources in order to make a better judgment. These questions arise: can we predict the value added by fusing their outputs together, if we know the general characteristics of a set of sensors? Can we specify the needed characteristics of a new sensor/algorithm to add to an existing suite to gain a desired improvement performance? The characteristic of a new sensor can be in any form, e.g., the ratio of a target's signal to the clutter's signal (similar in meaning to the signal-to-noise ratio), the position resolution, etc. In this paper, we consider these questions in the context of fuzzy set theory and in particular, a soft decision level fusion scheme we developed for land mine detection scenarios. Here, we primarily consider the ratio of a target's signal to the clutter's signal (called the d-metric). The tool estimates a final d-metric when the information from several sensors is fused through the linguistic Choquet fuzzy integral. This tool is used in the examination of the performance of d-metrics in a simulation environment. The approach is demonstrated for data obtained from an advanced technology demonstration in vehicle-based mine detection.
Experiments in predictive sensor fusion
2001
12 Seiten, 28 Quellen
Aufsatz (Konferenz)
Englisch
Sensor fusion for Space Station experiments
SPIE | 1994
|SAE Technical Papers | 2002
|Kraftfahrwesen | 2002
|