This paper presents a computationally efficient approach for classifying moving road traffic objects using FMCW radar. The method operates directly on raw radar IQ signals, applying Continuous Wavelet Transform (CWT) and extracting simple statistical features (mean, standard deviation, and maximum) to form compact feature vectors. Classification is performed using lightweight algorithms such as Random Forest, SVM, or kNN, achieving high accuracy on the test set (94–95% for six object classes) while maintaining minimal computational overhead. Unlike image-based CNN methods, the approach eliminates time-consuming spectrogram generation, enabling fast training and prediction suitable for real-time and embedded applications. Comparisons with selected deep learning–based methods reported in the literature indicate that the proposed framework can achieve comparable classification accuracy while requiring substantially lower computational resources. FMCW radar provides robustness against adverse weather and lighting conditions and enables detection independent of optical visibility. This work demonstrates a practical approach for efficient radar-based signal processing and pattern recognition, offering an alternative to vision-based classification for intelligent traffic monitoring and autonomous systems.