Sevgi Zubeyde Gurbuz

Knowledge Exploitation for Human Micro-Doppler Classification

Micro-Doppler radar signatures have great potential for classifying pedestrians and animals, as well as their motion pattern, in a variety of surveillance applications. Due to the many degrees of freedom involved, real data need to be complemented with accurate simulated radar data to be able to successfully design and test radar signal processing algorithms. In many cases, the ability to collect real data is limited by monetary and practical considerations, whereas in a simulated environment, any desired scenario may be generated. Motion capture (MOCAP) has been used in several works to simulate the human micro-Doppler signature measured by radar; however, validation of the approach has only been done based on visual comparisons of micro-Doppler signatures. This work validates and, more importantly, extends the exploitation of MOCAP data not just to simulate micro-Doppler signatures but also to use the simulated signatures as a source of a priori knowledge to improve the classification performance of real radar data, particularly in the case when the total amount of data is small.

A short survey of hyperspectral remote sensing applications in agriculture

Hyperspectral sensors are devices that acquire images over hundreds of spectral bands, thereby enabling the extraction of spectral signatures for objects or materials observed. Hyperspectral remote sensing has been used over a wide range of applications, such as agriculture, forestry, geology, ecological monitoring and disaster monitoring. In this paper, the specific application of hyperspectral remote sensing to agriculture is examined. The technological development of agricultural methods is of critical importance as the worlds population is anticipated to continuously rise much beyond the current number of 7 billion. One area upon which hyperspectral sensing can yield considerable impact is that of precision agriculture - the use of observations to optimize the use of resources and management of farming practices. For example, hyperspectral image processing is used in the monitoring of plant diseases, insect pests and invasive plant species; the estimation of crop yield; and the fine classification of crop distributions. This paper also presents a detailed overview of hyperspectral data processing techniques and suggestions for advancing the agricultural applications of hyperspectral technologies in Turkey.

A kinect-based human micro-doppler simulator

Until recently, human surveillance has primarily been accomplished using video cameras. However, radar offers unique advantages over optical sensors, such as being able to operate at far distances, under adverse weather conditions, and at nighttime, when optical devices are unable to acquire meaningful data. Radar is capable of recognizing human activities by classifying the micro-Doppler signature of a subject. Micro-Doppler is caused by any rotating or vibrating parts of a target, and results in frequency modulations centered about the main Doppler shift caused by the translational motion of the target [1]. Thus, the rotation of a helicopter blade, wheels of a vehicle, or treads of a tank all result in micro-Doppler. In the case of humans, the complex motion of the limbs that occur in the course of any activity all result in a micro-Doppler signature visually distinguishable from other targets, even animals [2]-[3], which can then be exploited for human detection [4]-[5], automatic target recognition (ATR) [6]-[7], and activity classification [8].

Micro-Doppler-Based Human Activity Classification Using the Mote-Scale BumbleBee Radar

Human activity recognition is an emerging technology for many security, surveillance, and health service applications utilizing wireless sensor networks (WSNs). However, the exploitation of radar in WSNs has been only recently made possible through the development of small, low-power, and low-cost wireless radar motes, such as the BumbleBee radar developed by the Samraksh Company. This letter explores the capacity of using the BumbleBee radar for indoor human activity classification based on micro-Doppler signatures. The electromagnetic measurements of the signal transmitted by the BumbleBee radar are made to fully characterize the sensor and its limitations. A database of the multiperspective micro-Doppler signatures measured from the BumbleBee radar is compiled to analyze the classification performance and limitations due to the dwell time and the aspect angle. Within the operational constraints delineated, it is shown that the BumbleBee radar can be used to discriminate between walking, running, and crawling, even under variable conditions.

Classification of human micro-Doppler in a radar network

The unique, bi-pedal motion of humans has been shown to generate a characteristic micro-Doppler signature in the time-frequency domain that can be used to discriminate humans from not just other targets, but also between different activities, such as walking and running. However, the classification performance increasingly drops as the aspect angle between the target and radar approaches perpendicular, and the radial velocity component seen by the radar is minimized. In this paper, exploitation of the multi-static micro-Doppler signature formed from multi-angle observations of a radar network is proposed to improve oblique-angle classification performance. The concept of mutual information is applied to find the order of importance of features for a given classification problem, thereby enabling the selection of optimal features prior to classification. Strategies for fusing multistatic data using mutual information and model-based approaches are discussed.

Information-Theoretic Feature Selection for Human Micro-Doppler Signature Classification

Micro-Doppler signatures can be used not only to recognize different targets, such as vehicles, helicopters, animals, and people, but also to classify varying activities, e.g., walking, running, creeping, and crawling. For this purpose, a plethora of features have been proposed in the literature; however, dozens of features are not required to achieve high classification performance. The topic of feature selection has been under addressed in micro-Doppler studies. Moreover, the optimal feature set is not static but varies under different operational conditions, such as signal-to-noise ratio (SNR), dwell time, and aspect angle. The mutual information of features relative to the classification problem at hand offers a measure for assessing the efficacy of features and thus sets a unique framework for feature selection. In this paper, information-theoretic (IT) feature selection techniques are used to identify essential features and minimize the total number of required features, while maximizing classification performance. It is seen that, although some features are consistently preferred, others are never selected. Results show that for SNRs over 10 dB and at least 1 s of data, this approach yields 96% correct classification when the target moves along the radar line-of-sight and over 65% correct classification for tangential motion.

A Nonlinear-Phase Model-Based Human Detector for Radar

Radar offers unique advantages over other sensors for the detection of humans, such as remote operation during virtually all weather and lighting conditions, increased range, and better coverage. Many current radar-based human detection systems employ some type of Fourier analysis, such as Doppler processing. However, in many environments, the signal-to-noise ratio (SNR) of human returns is quite low. Furthermore, Fourier-based techniques assume a linear variation in target phase over the aperture, whereas human targets have a highly nonlinear phase history. The resulting phase mismatch causes significant SNR loss in the detector itself. In this paper, human target modeling is used to derive a more accurate nonlinear approximation to the true target phase history. The likelihood ratio is optimized over unknown model parameters to enhance detection performance. Cramer-Rao bounds on parameter estimates and receiver operating characteristic curves are used to validate analytically the performance of the proposed method and to evaluate simulation results.

Multi-aspect angle classification of human radar signatures

The human micro-Doppler signature is a unique signature caused by the time-varying motion of each point on the human body, which can be used to discriminate humans from other targets exhibiting micro-Doppler, such as vehicles, tanks, helicopters, and even other animals. Classification of targets based on micro-Doppler generally involves joint timefrequency analysis of the radar return coupled with extraction of features that may be used to identify the target. Although many techniques have been investigated, including artificial neural networks and support vector machines, almost all suffer a drastic drop in classification performance as the aspect angle of human motion relative to the radar increases. This paper focuses on the use of radar networks to obtain multi-aspect angle data and thereby ameliorate the dependence of classification performance on aspect angle. Knowledge of human walking kinematics is exploited to generate a fuse spectrogram that incorporates estimates of model parameters obtained from each radar in the network. It is shown that the fused spectrogram better approximates the truly underlying motion of the target observed as compared with spectrograms generated from individual nodes.

Kinematic Model-Based Human Detectors for Multi-Channel Radar

Humans are difficult targets to detect because they have small radar cross sections (RCS) and move at low velocities. Consequently, they are masked by Doppler spread ground clutter generated by the radar bearing platform motion. Furthermore, conventional radar-based human detection systems employ some type of linear-phase matched filtering, whereas most human targets generate a highly nonlinear phase history. This work proposes an enhanced, optimized, nonlinear phase (EnONLP) matched filter that exploits knowledge of human gait to improve the radar detection performance of human targets. A parametric model of the expected human response is derived for multi-channel radar systems and used to generate a dictionary of human returns for a range of possible parameter variations. The best linear combination of projections in this dictionary is computed via orthogonal matching pursuit (OMP) to detect and extract features for multiple targets. Performance of the proposed EnONLP method is compared with that of traditional space-time adaptive processing (STAP) and a previously derived parameter estimation-based ONLP detector. Results show that EnONLP exhibits a detection probability of about 0.8 for a clutter-to-noise (CNR) ratio of 20 dB and input signal-to-noise ratio (SNR) of 0 dB, while ONLP yields a 0.3 and STAP yields a 0.18 probability of detection for the same false alarm rate.

Radar simulation of human micro-Doppler signature from video motion capture data

The availability of data sets on which signal processing techniques may be tested is critical to the development of human detection, identification, and classification algorithms. However, in many cases real radar data of the desired characteristics may be expensive or difficult to obtain. In this case, synthetic or simulated data is desired. Much of the simulated data used in publications is derived from the Boulic kinematic model. But, the Boulic model is only valid for walking and is not applicable to compute the micro-Doppler signatures of other human motions. The Carnegie Mellon University motion capture library includes data from a wide range of human activities and provides the time-varying position of body parts. In this work, this video motion capture data is used to generate the radar micro-Doppler signature for many human activities. Observations about the micro-Doppler signatures computed are also shared.