Download now Free registration required
Belief propagation methods are the state-of-the-art with multi-sensor state localization problems. However, when localization applications have to deal with multi-modality sensors whose functionality depends on the environment of operation, the authors understand the need for an inference framework to identify confident and reliable sensors. Such a framework helps eliminate failed/non-functional sensors from the fusion process minimizing uncertainty while propagating belief. They derive a framework inspired from model selection theory and demonstrate results on real world multi-sensor robot state localization and multi-camera target tracking applications.
- Format: PDF
- Size: 373.1 KB