In this letter, we propose a method for detecting a human subject using Doppler radar by investigating the physical characteristics of targets. Human detection has a number of applications in security, surveillance, and search-and-rescue operations. To classify a target from the Doppler signal, several features related to the physical characteristics of a target are extracted from a spectrogram. The features include the frequency of the limb motion, stride, bandwidth of the Doppler signal, and distribution of the signal strength in a spectrogram. The main contribution of this letter is the use of stride information of a target for the classification. Owing to the different lengths of legs and kinematic signatures of the target species, a human subject occupies a unique space in the domain of the stride and the frequency of limb motion. To verify the proposed method, we investigated humans, dogs, bicycles, and vehicles using the developed continuous-wave Doppler radar. The human subject is identified by a classifier of a support vector machine (SVM) trained to the extracted features. The trained SVM can detect a human subject with an accuracy of 96% with fourfold cross validation.

The authors investigate the feasibility of classifying different human activities using ultra-wide band (UWB) radar. Eight human subjects performing eight different activities are measured using a UWB radar. The eight activities include walking, running, rotating, punching, jumping, transitioning between standing and sitting, crawling and standing still. The dimension of the UWB returns is reduced using principal component analysis (PCA). The time-varying UWB signatures are characterised within a time window through observing the variation of the PCA coefficients. A support vector machine (SVM) is used to classify the activities based on the signatures. A multi-class classification is implemented using a one-versus-one method. Optimal parameters for the SVM are found through a 4-fold cross-validation. The resulting classification accuracy is found to be more than 85%. The potential of classifying human activities with different ground planes and with cluttered environments is also investigated. To extract more information regarding the target motion, human walking style classification with the developed method is also discussed.

In this paper, we propose the human detection technique using Neural Networks to effectively classify the Doppler signals caused by human walking along with the background noise sources. The frequency or phase feature vectors converted from the given input signal are directly used as the input of Neural Networks. In addition, Gaussian noise is added in the input nodes of Neural Network in order to prevent the overfitting problem. We developed the low-cost & short-range K-band Doppler radar for the experiment. The proposed technique was examined with human walking data accompanied with the background noises caused by the fan, rain, snow, and other outdoor environmental factors. The trained Neural Network detection technique can detect human walking with 95.2% of the true positive rate and it has 4.6% of the false positive rate.

This paper describes a study of compensation for the physical temperature variation in microwave radiometers. The compensation method is derived by using a multivariable least squares estimation with a radiometer model with temperature-dependent parameters for three system blocks. The feasibility of the method is demonstrated with several experiments with a Ka-band total power radiometer and a temperature control system developed to test the method in various thermal conditions. The results show that the compensation method can be applied to calibrate microwave radiometers without switching systems and is expected to compensate internal temperature gradients and temporal variation of physical temperature.

We propose a stacking method for ensemble learning to distinguish micro-Doppler signals generated by human walking from background noises using radar sensors. We collected micro-Doppler signals caused by four types of background noise (line of sight (LoS), fan, snow and rain) and additionally considered micro-Doppler signals caused by human walking combined with these four types of background noise. We firstly verified the effectiveness of a fully connected deep neural network (DNN) to classify 8 types of signals. The average accuracy was 88.79% for the test set. Then, we propose a stacking method to combine two base classifiers of different structures. The average accuracy of the stacking method on the test set was 91.43%. Lastly, we designed a modified stacking method to reuse feature information stored at the previous stage and the average test accuracy increased to 95.62%. This result shows that the proposed stacking methods can be an effective approach to improve classifier’s accuracy in recognizing human walking using micro-Doppler signals with background noise.