Fusion Method for Uncertain Multi-sensor Information

Aimed at multi-sensor Information fusion on object-level, in which the characteristic values of object types and observations of sensors are in the form of interval numbers, a new fusion method is proposed from the viewpoint of decision making theory. The method defines the deviation degree between two interval numbers. After solving the optimization problem of minimizing the overall square deviation between the object types and the unknown object, the weights of the attributes are obtained. Thus, the result of recognition is given through the deviation degree of overall attributes between object type and unknown object. This method can overcome the subjectivity of selecting attributes weights. It is straightforward and can be performed on computer easily. Finally, a part recognition experiment is given to demonstrate the feasibility and practicability of the proposed method.