Method for identifying and classifying an object
View Patent ↗In a method for identifying and classifying an object, an object is detected by at least one physical detector tuned for it, the object is evaluated from the output signal of the detector and by an evaluation unit, and the object is identified and/or classified on the basis of predefinable properties from the output signal. A number of different physical features of the object are derived from the output signal, and the object is assigned to one of N predetermined basic classes on the basis of the derived physical features. The N basic classes are arranged in a predetermined order to form an N-dimensional vector V, which is assigned to the object, such that the elements v 1 , . . . , v N of the vector V indicate that the object belongs to the respective basic class. The object is then assigned to a derived class, which is taken from a reference data base, as a function of the vector V.
1. A method for identifying and classifying a physical object based on detected physical features of the object, comprising:
providing a multitude of derived object classes, each of which relates to a specific physical object, wherein each derived object class is an N-dimensional vector comprising multiple binary values and each binary value is assigned to a physical features and indicates whether or not the assigned physical feature is characteristic for the physical object of the respective derived object class;
after provision of the multitude of derived object classes, initiating the following steps:
detecting one or more physical features of the physical object by at least one physical detector tuned for the object, and
identifying the object using an output signal of the at least one detector by:
(i) determining, using the output signal, whether the detected object possess any of a plurality of predefined physical features,
(ii) assigning a binary value to each of N predetermined basic classes based on the determination of whether the detected object possess any of the plurality of predefined physical features, wherein the binary values indicates whether or not the detected object possesses each of the plurality of predefined physical features,
(iii) arranging the binary values for the N basic classes in a predetermined order to form a detected object class which is an N-dimensional vector V, wherein the detected object class is of a similar structure as a derived object class, and
(iv) classifying the object by comparing (a) the binary values for the N basic classes of the detected object with (b) binary values for the N basic classes for the plurality of derived object classes obtained from a database, wherein each of the derived object classes corresponds to a pre-assigned object, and wherein when the binary values for the N basic classes of the detected object match the binary values for the N basic classes of one of the plurality of derived object classes the detected object is identified as that object being pre-assigned to the matching one of the plurality of derived object classes.
2. The method according to claim 1 , wherein the basic classes are radar source, transmission source, heat source, radar backscatter source, Doppler effect, light source, spectral source, sound source, and contour classes.