Support vector machines for classification of automotive radar interference

This paper studies classification of the automotive radar interference waveforms via support vector machine (SVM). Automotive radar implemented in advanced driver assistance systems (ADASs) is an essential sensor in road traffic safety, e.g., moving target indication, collision avoidance and enhanced navigation system. However, radar-to-radar interference is inevitable as the number of automotive radar increases. Our work shows different types of radar-to-radar interference with analyzing the received signal. Providing linear frequency modulated transmitting (LFM) signal, filtering and dechirping techniques, the classification of six different types of radar-to-radar interference are presented and analyzed. Time-frequency domain signal and range-Doppler profiles of different types of interference are simulated. The machine learning classifier of SVM of multi-class high-dimensional waveform data classification is used to classify different interference waveforms and non-interference waveforms. Random produced dataset is cross validated through the SVM classifier. Different types of interference prediction accuracies are shown and verified by the proposed method. The confusion matrix of interference and non-interference, detecting different types of interference and classifying all incoming receiving signal are presented.