Fusion of visual and range features using fuzzy logic

Abstract Multi-sensor systems provide a purposeful description of the environment that a single sensor cannot offer. Fusing several types of data enhances the recognition capability of an autonomous system and yields meaningful information otherwise unavailable or difficult to acquire by a single sensory modality. Because observations provided by sensors are uncertain, incomplete, and/or imprecise, the use of fuzzy sets theory was adopted as a general framework to combine uncertain measurements. A new fusion formula based on fuzziness measure was developed. This fusion formula was mathematically tested against several desirable properties of fusion operators. This method was tested using real data showing a robotic scene. The fused data shows clear benefits from fusion.