Research on Human Micro-Doppler Image Quality Evaluation Based on Principal Component Analysis
Under the background of aging society,the key to monitor elderly activities with radar technology is to ensure the accuracy of radar micro-Doppler information transmission.So it is very important to improve the accuracy and robustness of human motion micro-Doppler image quality evaluation.Firstly,phase noise images of different levels and corresponding subjective score data are added to expand the HMMDIQA database and increase the diversity of the database in this paper.Furthermore,an algorithm based on subspace feature enhancement of Principal Component Analysis(PCA)is proposed for human motion micro-Doppler image quality evaluation.The experimental results in HMMDIQA database show that the various evaluation indicators of designed algorithm have been improved than the basic network.