This paper presents the results of accompanying classification of tracking for different classes of targets such as a car (moving non-rigid target), moving people (slow moving non-rigid target). The Data are collected using frequency modulation continuous wave (FMCW)radar, while different neural algorithms are considered for classification of targets recorded. A Doppler and Micro Doppler have been used as target features, while short time Fourier transform (STFT) has been used as a feature extraction algorithm. A novel combination between Kalman filter and tree-structured, as well as self-organizing map (SOM) neural network has been proposed as an estimator and classifier, respectively. The results show that the proposed approach is overperformed to the conventional classifier SVM by 1.6% and the gained classification is 92.6%, while the reduction error due to using Kalman filter is 95%.

No abstract

No abstract

No abstract

No abstract