Abstract: Techniques of machine learning of a radar are disclosed, where the radar has a plurality of antennas that are arranged on an antenna array. In an example, a method of machine learning includes obtaining a real training sample from a first real target in field of view of the radar, where the real training sample includes a plurality of first real data signals, where each of the first real data signals are obtained from a corresponding antenna from amongst the plurality of antennas. The method further includes deriving a synthetic training sample by manipulating the plurality of first real data signals to simulate a rotation of the first real target about a pre-determined axis of the antenna array.

Abstract: Techniques of object classification are described. In operation, a radar signal reflected by an object within range of the radar detection system is received and at least one set of frequency components corresponding to the object are extracted. At least one set of unit energy samples corresponding to the object is then generated based on the at least one set of frequency components followed by computation of a range compensated energy (RCE) corresponding to the object based on the at least one set of frequency components, where the RCE is indicative of range normalized energy corresponding to the object. A feature vector corresponding to the object is then generated based at least on the at least one set of unit energy samples and the RCE, wherein the feature vector is representative of characteristics of the object.