Method Based on Interval Number for Multi-sensor Information Fusion on Object-level

Abstract

Aimed at the object recognition problem in which the characteristic values of object types and observations of sensors are in the form of interval numbers, a new method based on interval number for multi-sensor data fusion on object-level is proposed by grey relational analysis. The method defines the distance between the two interval numbers, obtains the distance matrix and grey relational matrix between all object types and unknown object. After solving the optimization problem of maximizing the deviation for all attributes, the weights of the attributes are derived. Thus, the result of recognition for the unknown object is given by the grey relational grade. This method can avoid the subjectivity of selecting attributes weights and improve the objectivity and accuracy of object recognition. The simulated example verifies the feasibility and practicability of the proposed method.