We propose the use of deep convolutional neural networks (DCNNs) for human detection and activity classification based on Doppler radar. Previously, proposed schemes for these problems remained in the conventional supervised learning paradigm that relies on the design of handcrafted features. Whereas these schemes attained high accuracy, the requirement for domain knowledge of each problem limits the scalability of the proposed schemes. In this letter, we present an alternative deep learning approach. We apply the DCNN, one of the most successful deep learning algorithms, directly to a raw micro-Doppler spectrogram for both human detection and activity classification problem. The DCNN can jointly learn the necessary features and classification boundaries using the measured data without employing any explicit features on the micro-Doppler signals. We show that the DCNN can achieve accuracy results of 97.6% for human detection and 90.9% for human activity classification.

Human Detection and Activity Classification Based on Micro-Doppler Signatures Using Deep Convolutional Neural Networks

This is a book review of 'The Micro-Doppler Effect in Radar' by V. C. Chen. Artech House, 16 Sussex Street, London, SW1V 4RW, UK. 2011. 290pp + diskette. Illustrated. £90. ISBN 978-1-60807-057-2.

'The Micro-Doppler Effect in Radar' by V.C. Chen

Radar is considered an important technology for health monitoring and fall detection in elderly assisted living due to a number of attributes not shared by other sensing modalities. In this article, we describe the signal processing algorithms and techniques involved in elderly fall detection using radar. A human?s radar signal returns differ in their Doppler characteristics, depending on the nature of the human gross motor activities. These signals are nonstationary in nature, inviting time-frequency analysis in both its linear and bilinear aspects, to play a fundamental role in motion identification, including fall features determination and classification. This article employs real fall data to demonstrate the success of existing detection algorithms as well as to report on some of the challenges facing technology developments for fall detection.

Radar Signal Processing for Elderly Fall Detection: The future for in-home monitoring

In this paper, we investigate the feasibility of recognizing human hand gestures using micro-Doppler signatures measured by Doppler radar with a deep convolutional neural network (DCNN). Hand gesture recognition using radar can be applied to control electronic appliances. Compared with an optical recognition system, radar can work regardless of light conditions and it can be embedded in a case. We classify ten different hand gestures, with only micro-Doppler signatures on spectrograms without range information. The ten gestures, which included swiping from left to right, swiping from right to left, rotating clockwise, rotating counterclockwise, pushing, double pushing, holding, and double holding, were measured using Doppler radar and their spectrograms investigated. A DCNN was employed to classify the spectrograms, with 90% of the data utilized for training and the remaining 10% for validation. After five-fold validation, the classification accuracy of the proposed method was found to be 85.6%. With seven gestures, the accuracy increased to 93.1%.

Hand Gesture Recognition Using Micro-Doppler Signatures With Convolutional Neural Network

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.

Human Detection Using Doppler Radar Based on Physical Characteristics of Targets

The ability to identify human movements can serve as an important tool in many different applications such as surveillance, military combat situations, search and rescue operations and patient monitoring in hospitals. This information can provide soldiers, security personnel and search and rescue workers with critical knowledge that can be used to potentially save lives and/or avoid dangerous situations. Most research involving human activity recognition employs the short-time Fourier transform (STFT) as a method of analysing human micro-Doppler signatures. However, the STFT has time-frequency resolution limitations and Fourier transform-based methods are not well-suited for use with non-stationary and non-linear signals. The authors approach uses the empirical mode decomposition to produce a unique feature vector from the human micro-Doppler signals following which a support vector machine is used to classify human motions. This study presents simulations of simple human motions, which are subsequently validated using experimental data obtained from both an S-band radar and a W-band millimetre wave (mm-wave) radar. Very good classification accuracies are obtained at distances of up to 90 m between the human and the radar.

Classification of human motions using empirical mode decomposition of human micro-Doppler signatures

Micro-Doppler radar signals can be used to separate moving human targets from stationary clutter and also to identify and classify human movements. Traditional micro-Doppler radar, which uses a single-sensor, monostatic system, suffers from the drawback that only the radial component of the micro-Doppler signal will be observed by the radar operator. This reduces the sensitivity of human-activity recognition if the movements are not directly toward or away from the line of sight to the radar antenna. In this paper, we propose overcoming this limitation through the use of a multistatic sensor, which consists of two bistatic micro-Doppler sensors. Through using multiple sensors, the orientation of oscillating targets with respect to the radar line of sight can be inferred, thereby providing additional information to the radar operator. In addition, we conclude that multiple sensors can enhance the classification of micro-Doppler signatures.

Multistatic micro-doppler radar for determining target orientation and activity classification

The ability to identify human movements can be an important tool in many different applications such as surveillance, military combat situations, search and rescue operations, and patient monitoring in hospitals This information can provide soldiers, security personnel, and search and rescue workers with critical knowledge that can be used to potentially save lives and/or avoid a dangerous situation Most research involving human activity recognition is focused on using the Short-Time Fourier Transform (STFT) as a method of analyzing the micro-Doppler signatures Because of the time-frequency resolution limitations of the STFT and because Fourier transform-based methods are not well-suited for use with non-stationary and nonlinear signals, we have chosen a different approach Empirical Mode Decomposition (EMD) has been shown to be a valuable time-frequency method for processing non-stationary and nonlinear data such as micro-Doppler signatures and EMD readily provides a feature vector that can be utilized for classification For classification, the method of a Support Vector Machine (SVMs) was chosen SVMs have been widely used as a method of pattern recognition due to their ability to generalize well and also because of their moderately simple implementation In this paper, we discuss the ability of these methods to accurately identify human movements based on their micro-Doppler signatures obtained from S-band and millimeter-wave radar systems Comparisons will also be made based on experimental results from each of these radar systems Furthermore, we will present simulations of micro-Doppler movements for stationary subjects that will enable us to compare our experimental Doppler data to what we would expect from an "ideal" movement© (2012) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE) Downloading of the abstract is permitted for personal use only

/pdf/classification-and-modeling-of-human-activities-using-4gcto56hy8.pdf

Classification and modeling of human activities using empirical mode decomposition with s-band and millimeter-wave micro-doppler radars

The identification and classification of human motions has become a popular area of research due to its broad range of applications. Knowledge of a person's movements can be a useful tool in surveillance, security, military combat, search and rescue operations, and the medical fields. Classification of common stationary human movements has been performed under various scenarios for two different micro-Doppler radar systems: S-band radar and millimeter-wave (mm-wave) radar. Each radar system has been designed for a specific scenario. The S-band radar is intended for through-the-wall situations at close distances, whereas the mm-wave radar is designed for long distance applications and also for through light foliage. Here, the performance of these radars for different training scenarios is investigated. The S-band radar will be analyzed for classification without a wall barrier, through a brick wall, and also through a cinder block wall. The effect of a wall barrier on micro-Doppler signatures will be briefly discussed. The mm-wave radar will be analyzed for classification at distances of 30, 60, and 91 meters.

Micro-doppler radar classification of human motions under various training scenarios

The automatic identification of human activities has become an area of interest in recent years Identifying
human activities is useful in various applications, such as through-barrier identification of intruders and non-contact
monitoring of patients in hospitals Numerous methods of human activity classification have been
proposed in the past, including the use of Artificial Neural Networks (ANNs) and Support Vector Machines
(SVMs) Most research in this area thus far has utilized the Short-Time Fourier Transform (STFT) as a method
of obtaining the feature vectors necessary for classification In this paper, we propose the use of the Empirical
Mode Decomposition (EMD) algorithm as an alternative approach for obtaining feature vectors from human
micro-Doppler signals and utilize an SVM for classification Since the micro-Doppler signature is unique to
a specific activity, the EMD outputs can be utilized as feature vectors By utilizing the EMD algorithm in
conjunction with an SVM, binary classification of human activities have shown to yield accurate results Because
SVMs were originally developed to solve the binary classification problem, additional steps must be taken in order
to extend the problem to identify multiple classes In this paper, two methods for multi-class classification will
be demonstrated and compared The first method is the one-against-all approach and the second is a decision
tree based approach In both cases, a high degree of accuracy is achieved

Dustin P. Fairchild

Papers

Classification of human motions using empirical mode decomposition of human micro-Doppler signatures

Multistatic micro-doppler radar for determining target orientation and activity classification

Classification and modeling of human activities using empirical mode decomposition with s-band and millimeter-wave micro-doppler radars

Micro-doppler radar classification of human motions under various training scenarios

Human activity classification using Hilbert-Huang transform analysis of radar Doppler data