Human Target Detection Based on 4D Point Cloud Micro-Clusters' Features in Complex Environments

For enhance the home human vital sign continuously monitor, this paper proposes a human target detection approach based on four-dimensional (4D) point cloud micro-clusters' features using multiple-input multiple-output (MIMO) radar. We first perform 4D point cloud imaging on human targets and interference signals, then analyze and extract the 4D point cloud micro-clusters multidimensional features under 10 interference scenarios, and finally use support vector machine (SVM) classifier to complete the classification of different combinations of human targets and interference. The experimental results show that the proposed approach has an average accuracy of 99.2% for human target and interference recognition, and performs significantly better than the traditional cell-averaging constant false alarm rate (CA-CFAR) detector.