Search

Detection of moving objects concealed behind a concrete wall corner has been demonstrated, using Doppler-based techniques with a stepped-frequency radar centered at 10 GHz, in a reduced-scale model of a street scenario. Micro-Doppler signatures have been traced in the return from a human target, both for walking and for breathing. Separate material measurements of the reflection and transmission of the concrete in the wall have showed that wall reflections are the dominating wave propagation mechanism for producing target detections, while wave components transmitted through the walls could be neglected. Weaker detections have been made of target returns via diffraction in the wall corner. A simple and fast algorithm for the detection and generation of detection tracks in down range has been developed, based on moving target indication technique. ©2011 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE. Ain Sume, Magnus Gustafsson, Magnus Herberthson, Anna Jänis, Stefan Nilsson, Jonas Rahm and Anders Örbom, Radar Detection of Moving Targets Behind Corners, 2011, IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, (49), 6, 2259-2267.http://dx.doi.org/10.1109/TGRS.2010.2096471Postprint available at: Linköping University Electronic Presshttp://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-68912

A simple electromagnetic model of wind-turbine's main structural elements as the linear wired structures is developed to simulate the temporal patterns of observed radar return Doppler spectra (micro-Doppler). Using the model, the micro-Doppler for different combinations of the turbines rotation frequency, radar pulse repetition frequency, and duration of the Doppler measurement interval are analyzed. The model is validated using the PARSAX radar experimental data. The model ability to reproduce the observed Doppler spectra main features can be used for development of signal-processing algorithms to suppress the wind-turbines clutter in modern Doppler radars.

A simple electromagnetic model of wind-turbine's main structural elements as the linear wired structures is developed to simulate the temporal patterns of observed radar return Doppler spectra (micro-Doppler). Using the model, the micro-Doppler for different combinations of the turbines rotation frequency, radar pulse repetition frequency, and duration of the Doppler measurement interval are analyzed. The model is validated using the PARSAX radar experimental data. The model ability to reproduce the observed Doppler spectra main features can be used for development of signal-processing algorithms to suppress the wind-turbines clutter in modern Doppler radars.

Farklı hedef tipleri veya aynı hedefin farklı hareketleri için radar mikro-Doppler sinyalleri birbirinden farklı olmaktadır. Bu durum, radar mikro-Doppler sinyallerinin hedef sınıflandırması için kaynak olarak kullanılması fikrini doğurmuştur. Son 10 yılda mikro-Doppler tabanlı birçok sınıflandırma çalışması yayınlanmıştır. Bu çalışmalar, deneysel radar verileri kullanılarak yapıldığında genellikle yakın mesafelerden ve parazit yansımanın önemsiz olduğu durumlar için gerçekleştirilmektedir. Benzetim çalışmalarında da gürültü ve parazit yansıma etkileri çoğu zaman ihmal edilmektedir. Sınıflandırma başarımının gürültü ve parazit yansıma etkilerinin ihmal edildiği ideal durumlar için ölçülmesi, yapılan çalışmanın sonuçlarını gerçeklikten uzaklaştırmaktadır. Bu çalışmada, benzetim verileri kullanılarak mikro-Doppler imzaları üzerinden bir sınıflandırma çalışması gerçekleştirilmiştir. Hedeflere ait radar benzetim verileri oluşturulurken gürültü ve parazit yansıma etkileri de modellenmiştir. Gürültü ve parazit yansımalı verilerle elde edilen sınıflandırma başarımı, gürültüsüz durumda elde edilen ile karşılaştırılmıştır. Ayrıca, gürültülü durumda görüntü işleme teknikleri kullanılarak başarımı artırmak için bir yöntem önerilmiştir. Sonuçlar iki farklı sınıflandırıcı ile denenmiş ve önerilen yöntemin sınıflandırma başarımında %5 ile %15 arasında bir artış sağladığı görülmüştür., Micro-Doppler radar signals for different target types or different movements of a target are also different from each other. This leads to usage of micro-Doppler radar signals as a source of classifying targets. Many micro-Doppler based target classification studies have been published in the last ten years. The studies which are done using experimental radar data are usually carried out in situations where target is close to the radar and clutter effect is minimal. In simulation studies, noise and clutter effects are also ignored. Measurement of classification performance for idealistic conditions in which noise and clutter effects are not taken into account makes the outcomes of the study doubtful. In this thesis, a classification study of micro-Doppler based target signatures is carried out using simulation data. While generating radar simulation data of targets, noise and clutter effects are also modeled. Classification performance obtained from the data containing noise and clutter is compared to noise free data. In addition, a method is proposed to increase the performance in noisy situations using image processing techniques. The results are obtained with two different classifiers and the proposed method has made an increase from 5% to 15% in the classification performance.

Radar gözetleme sistemlerindeki asıl zorluk insanların hayvanlardan ayrılması olduğu kadar farklı insan hareketlerinin ayrılmasını da kapsamaktadır. Bu nedenle hedef mikro-Doppler imzalarının otomatik hedef sınıflandırması için yüksek başarıma sahip olduğu gösterilse de sonuçlar operasyonel koşulların ideal olduğu durumlar ve belirli öznitelik kümeleri için verilmektedir. Geçmiş yıllarda çok sayıda öznitelik mikro-Doppler imzalarının sınıflandırılması için önerilmiştir. Ancak önerilen özniteliklerinin tümünün kullanılması maksimum sınıflandırma başarımının verilmesini garanti etmemekte ve ideal öznitelik alt kümesinin seçilmesi ise senaryoya bağımlı olarak değişmektedir. Bu çalışmada, kapsamlı olarak mikro-Doppler öznitelik çıkarım yöntemleri ve çıkartılan özniteliklerin radar sistem parametleri ve operasyonel koşullara – merkez frekansı, menzil ve Doppler çözünürlüğü, anten hedef geometrisi, sinyal gürültü oranı ve hedef üzerinde kalma süresi – olan bağımlılıklarını incelemektedir. İnsan mikro-Doppler imzalarına uyarlı bir öznitelik dizaynı gerçekleştirilmiştir. Sınıflandırma performansını en iyileştirecek, azaltılmış sayıda olan özniteliklerin çıkartılması için algoritmalar önerilmiş ve iyi seçilmiş bir öznitelik alt kümesinin daha iyi başarımlar ortaya konduğu gösterilmiştir. Durum çalışması yapılarak önerilen uyarlanabilir öznitelik seçim algoritmasının sınıflandırma performansını arttırılabileceği gösterilmiştir., A key challenge for radar survelliance systems is the discrimination of ground based targets, especially humans from animals, as well as different types of human activities. For this purpose, target micro-Doppler signatures have been shown to yield high automatic target classification rates; however, performance is typically only given for near-optimal operating conditions using a fixed set of features. Over the past decade a vast number of micro-Doppler features have been proposed for classification of radar micro-Doppler signatures. In fact utilization of all possible features does not guarantee maximum classification performance and the selection of an optimal subset of features is scenario dependent. In this work, a comprehensive survey of micro-Doppler features and their dependence upon system parameters and operational conditions – such as transmit frequency, range and Doppler resolution, antenna target geometry, signal to noise ratio, and dwell time – is given. A new feature design for human micro-Doppler signatures is proposed. Algorithms for optimizing classification performance for a reduced number of features are presented and it is shown that a well selected subset of robust features yields better results. Performance gains achievable using adaptive feature selection are assessed for a case study of interest.

International audience; In radar imaging it is well known that relative motion or deformations of parts of illuminated objects induce additional features in the Doppler frequency spectra. These features are called micro-Doppler effect and appear as sidebands around the central Doppler frequency. They can provide valuable information about the structure of the moving parts and may be used for identification purposes.

Faz-se nesta dissertação a análise do movimento humano utilizando sinais de ultrassons refletidos pelos diversos membros do corpo humano, designados por assinaturas de ultrassons. Estas assinaturas são confrontadas com os sinais gerados pelo contato dos membros inferiores do ser humano com o chão, recolhidos de forma passiva. O método seguido teve por base o estudo das assinaturas de Doppler e micro-Doppler. Estas assinaturas são obtidas através do processamento dos ecos de ultrassons recolhidos, com recurso à Short-Time Fourier Transform e apresentadas sobre a forma de espectrograma, onde se podem identificar os desvios de frequência causados pelo movimento das diferentes partes do corpo humano. É proposto um algoritmo inovador que, embora possua algumas limitações, é capaz de isolar e extrair de forma automática algumas das curvas e parâmetros característicos dos membros envolvidos no movimento humano. O algoritmo desenvolvido consegue analisar as assinaturas de micro-Doppler do movimento humano, estimando diversos parâmetros tais como o número de passadas realizadas, a cadência da passada, o comprimento da passada, a velocidade a que o ser humano se desloca e a distância percorrida. Por forma a desenvolver, no futuro, um classificador capaz de distinguir entre humanos e outros animais, são também recolhidas e analisadas assinaturas de ultrassons refletidas por dois animais quadrúpedes, um canino e um equídeo. São ainda estudadas as principais características que permitem classificar o tipo de animal que originou a assinatura de ultrassons. Com este estudo mostra-se ser possível a análise de movimento humano por ultrassons, havendo características nas assinaturas recolhidas que permitem a classificação do movimento como humano ou não humano. Do trabalho desenvolvido resultou ainda uma base de dados de assinaturas de ultrassons de humanos e animais que permitirá suportar trabalho de investigação e desenvolvimento futuro. This dissertation presents the study and analysis of human motion using ultrasonic signals reflected by the various parts of the human body, designated by ultrasonic signatures. The ultrasonic signatures are confronted with signals generated by the contact of the lower limbs of the human with the ground, collected passively. The proposed method was based upon the study of Doppler and micro-Doppler signatures. These signatures are obtained by processing the acquired ultrasonic echoes using the Short-Time Fourier Transform and presented in the form of a spectrogram, which can identify the frequency deviations caused by the movement of the various parts of the human body. An innovative algorithm is proposed and despite its limitations, it is capable of isolating and automatically extracting some of the curves and characteristic parameters of the parts involved in human motion. The proposed algorithm can analyze the signatures of micro-Doppler of human motion, estimating various parameters such as the number of strides performed the cadence of stride, stride length, the speed which humans are moving and distance walked. In order to develop a classifier able to distinguish between humans and other animals, ultrasound signatures reflected by two quadrupeds’ animals, a dog and a horse were collected and analyzed. One feature that wasn’t implemented yet is the classification engine that allows the recognition of the type of animal that originated the ultrasound signature. With this study it is shown that it is possible the analysis of human motion through ultrasound systems, having as main characteristic the acquisition of signatures that allows the classification of movement as human or non-human. From the work undertaken, resulted an extensive database of ultrasound signatures of humans and animals that will enable endure research and future developments.

n traditional ISAR imaging, rigid-body motion is usually assumed without considering non-stationary targets. Relative motion or deformation of parts of illuminated objects induce additional features in the Doppler frequency spectra. These features are called micro-Doppler effect and appear as sidebands around the central Doppler frequency. They can provide valuable information about the structure of the moving parts and may be used for recognition purposes. Previous papers have mostly focused on temporal micro-Doppler analysis. Besides except theoretical case studies, there are very few models and real data of non-stationary targets. Through the study of the wheel and the human motion, we propose in this thesis to emphasize and model the motion involving a micro-Doppler effect. We use both the micro-Doppler and a high range resolution analysis to finely characterize such non-stationary targets in radar imaging. Moreover we emphasize the influence of the relative geometry between the radar and the target. This thesis lies on a significant experimental part with the use of data provided by the ultra-wide band radar HYCAM developed by ONERA. In addition, the development of a simulator tool permits to link experimental data and models in order to extract physical features., Les méthodes traditionnelles de formation d'images ISAR supposent que la cible est rigide et ne tiennent pas compte de ses déformations géométriques. Ces mouvements, qui s'ajoutent au déplacement global de la cible, créent une modulation en fréquence sur le signal réfléchi. Ce phénomène, aussi appelé effet micro-Doppler, se traduit d'un point de vue spectral par un étalement des fréquences autour de la fréquence Doppler centrale. Comme les caractéristiques de ces modulations sont directement reliées aux propriétés géométriques et dynamiques de la cible, l'analyse de l'effet micro-Doppler peut apporter des informations complémentaires aux méthodes existantes de reconnaissance de cibles mobiles. Les travaux précédents ont principalement été consacrés à l'analyse temporelle de l'effet micro-Doppler sans tenir compte de la dimension spatiale. En outre, mis à part les cas d'étude théoriques, il existe très peu de modélisations et de données réelles de cibles déformables. A travers les exemples de la roue et du piéton, cette thèse consiste à caractériser finement les effets des déformations géométriques en imagerie radar, en combinant l'analyse en distance et en Doppler. En outre, un accent est mis sur l'influence de la géométrie relative entre le radar et la cible.\\ Ces travaux s'appuient sur un large volet expérimental où sont exploitées les données issues du radar HYCAM, un système d'acquisition large bande développé par l'ONERA. En complément des mesures, le développement d'un outil de simulation permet de faire le lien entre les données réelles et le modèle de l'objet afin d'extraire des grandeurs physiques du phénomène étudié.

Farklı hedef tipleri veya aynı hedefin farklı hareketleri için radar mikro-Doppler sinyalleri birbirinden farklı olmaktadır. Bu durum, radar mikro-Doppler sinyallerinin hedef sınıflandırması için kaynak olarak kullanılması fikrini doğurmuştur. Son 10 yılda mikro-Doppler tabanlı birçok sınıflandırma çalışması yayınlanmıştır. Bu çalışmalar, deneysel radar verileri kullanılarak yapıldığında genellikle yakın mesafelerden ve parazit yansımanın önemsiz olduğu durumlar için gerçekleştirilmektedir. Benzetim çalışmalarında da gürültü ve parazit yansıma etkileri çoğu zaman ihmal edilmektedir. Sınıflandırma başarımının gürültü ve parazit yansıma etkilerinin ihmal edildiği ideal durumlar için ölçülmesi, yapılan çalışmanın sonuçlarını gerçeklikten uzaklaştırmaktadır. Bu çalışmada, benzetim verileri kullanılarak mikro-Doppler imzaları üzerinden bir sınıflandırma çalışması gerçekleştirilmiştir. Hedeflere ait radar benzetim verileri oluşturulurken gürültü ve parazit yansıma etkileri de modellenmiştir. Gürültü ve parazit yansımalı verilerle elde edilen sınıflandırma başarımı, gürültüsüz durumda elde edilen ile karşılaştırılmıştır. Ayrıca, gürültülü durumda görüntü işleme teknikleri kullanılarak başarımı artırmak için bir yöntem önerilmiştir. Sonuçlar iki farklı sınıflandırıcı ile denenmiş ve önerilen yöntemin sınıflandırma başarımında %5 ile %15 arasında bir artış sağladığı görülmüştür., Micro-Doppler radar signals for different target types or different movements of a target are also different from each other. This leads to usage of micro-Doppler radar signals as a source of classifying targets. Many micro-Doppler based target classification studies have been published in the last ten years. The studies which are done using experimental radar data are usually carried out in situations where target is close to the radar and clutter effect is minimal. In simulation studies, noise and clutter effects are also ignored. Measurement of classification performance for idealistic conditions in which noise and clutter effects are not taken into account makes the outcomes of the study doubtful. In this thesis, a classification study of micro-Doppler based target signatures is carried out using simulation data. While generating radar simulation data of targets, noise and clutter effects are also modeled. Classification performance obtained from the data containing noise and clutter is compared to noise free data. In addition, a method is proposed to increase the performance in noisy situations using image processing techniques. The results are obtained with two different classifiers and the proposed method has made an increase from 5% to 15% in the classification performance.

Human detection offers many advantages in applications of search and rescue, smart environments, and security. Infrared, acoustic, vibration/seismic and visual sensors have been often used in human detection and recognition systems. Radar offers unique advantages for sensing humans, such as remote operation during virtually all weather conditions, increased range, and better coverage. However, radar systems are typically very expensive and physically large. The BumbleBee radar, in contrast to most radars, is a low power pulse Doppler radar that is about the size of a business card. Moreover, it is a radar that can be integrated into indoor wireless sensor networks. In this work, the application of BumbleBee radar to human activity recognition by computing the human micro-Doppler signature is examined. Humans are complex targets that are capable of many motions. Every part of the human causes different reflection and every motion of the human has its unique micro-doppler signatures. The differences in micro-Doppler data of activities such as walking, running, and crawling that is gathered from low-cost, low-power radar is discussed. © 2014 IEEE.

The classification of different human activities with radar has been a widely researched topic in recent years. Oftentimes, when no experimental data is available, simulated data can be exploited to test classification algorithms. Kinematic models such as the Thalmann Model and motion capture (MOCAP) data are frequently used to simulate radar signatures of human movements. While the Thalmann Model provides a model only for human walking, MOCAP data has the capability to supply data for almost any type of human activity. However, most commercial MOCAP data acquisition systems are quite expensive, making it difficult to obtain MOCAP data. In this paper, economical, easily obtainable and practical Kinect sensor is used to develop a skeleton tracking algorithm. In this way, simulated radar micro-Doppler signatures for different people and activities are computed.

Son zamanlarda, derin yapay sinir ağları (DNN), sentetik açıklılı radar (SAR) veya mikro-Doppler tabanlı otomatik hedef tanıma gibi RF sinyal sınıflandırma uygulamalarında araştırma konusu olmuştur. Bununla birlikte, radar verisi elde etmenin masraflı ve zor olması, elde edilebilecek veri sayısını kısıtlamaktadır. DNN'ler yüksek varyanslı modeller olmaları sebebiyle aşırı öğrenmeye yatkıdırlar. Dolayısıyla iyi bir genelleme öğrenebilmek için fazla miktarda etiketlenmiş veriye ihtiyaç duymaktadırlar. Bu tez çalışmasında, ilk olarak 4 GHz sürekli dalga radarı 12 farklı ancak birbirine benzer insan hareketi için bir veri seti oluşturulmuştur. Sonrasında literatürde az sayıda veriyle DNN eğitmek için önerilen iki temel teknik kıyaslanmıştır: Gözetimsiz ön-eğitim ve aktarımlı öğrenme. Gözetimsiz ön-eğitim bir konvolüsyonel otokodlayıcı (CAE) yapısı üzerinden, aktarımlı öğrenme ise ImageNet üzerine eğitilmiş popüler CNN mimarileri (VGGNet, GoogleNet and ResNet) üzerinden gerçekleştirilmiştir. Buna ek olarak, aktarımlı öğrenmenin benzer transfer alanı üzerinden uygulanabilmesi için, farklılaştırılmış radar mikro-Doppler simülasyonları oluşturan yenilikçi bir metot önerilmiştir. Tüm sonuçlar, el işçiliği ile oluşturulmuş özniteliklerin çıkartılarak bir SVM sınıflandırıcısının eğitildiği geleneksel yöntem ile kıyaslanmıştır. Tezin sonunda, önerilen artçıl aktarımlı öğrenme ağı DivNet'in, diğer DNN mimarileri arasında en yüksek sınıflandırma doğruluğunu sağladığı ve gürültüye karşı gürbüz olduğu gösterilmiştir., Recently, deep neural networks (DNNs) have been the subject of intense research for the classification of radio frequency (RF) signals, such as synthetic aperture radar (SAR) imagery or micro-Doppler based automatic target recognition. However, a fundamental challenge is the typically small amount of data available due to the high costs and resources required for measurements. Deep neural networks (DNNs), however, require large-scale labeled datasets to prevent overfitting while having good generalization. In this thesis, the efficacy of two neural network initialization techniques - unsupervised pre-training and transfer learning - for dealing with training DNNs on small data sets are compared. Unsupervised pre-training is implemented through the design of a convolutional autoencoder (CAE), while transfer learning from two popular CNN architectures (VGGNet, GoogleNet and ResNet). Also, a novel method for generating diversified radar micro-Doppler signatures using Kinect-based motion capture simulations is proposed as a training database for DNNs exploiting transfer learning. Results have also been compared with the conventional approach where handcrafted features are employed to train an SVM classifier. In particular, it is shown that the proposed residual transfer learning network, DivNet, offers the highest classification accuracy among other DNN architectures and, is robust to image noise.

Radar-based activity recognition is a problem that has been of great interest due to applications such as border control and security, pedestrian identification for automotive safety, and remote health monitoring. This paper seeks to show the efficacy of micro-Doppler analysis to distinguish even those gaits whose micro-Doppler signatures are not visually distinguishable. Moreover, a three-layer, deep convolutional autoencoder (CAE) is proposed, which utilizes unsupervised pretraining to initialize the weights in the subsequent convolutional layers. This architecture is shown to be more effective than other deep learning architectures, such as convolutional neural networks and autoencoders, as well as conventional classifiers employing predefined features, such as support vector machines (SVM), random forest, and extreme gradient boosting. Results show the performance of the proposed deep CAE yields a correct classification rate of 94.2% for micro-Doppler signatures of 12 different human activities measured indoors using a 4 GHz continuous wave radar-17.3% improvement over SVM.

This paper introduces the use of a Chebychev moments' based feature for micro-Doppler based Classification, Recognition and Fingerprinting of Drones. This specific feature has been selected for its low computational cost and orthogonality property. The capability of the proposed feature extraction framework is assessed at three different levels of major classification steps, namely classification, recognition and fingerprinting, demonstrating the effectiveness of the proposed approach to discriminate drones from birds, fixed wings from multi-rotors and drones carrying different payloads on real measured radar data.

Micro-Doppler, induced by micro-motion of targets, is an important characteristic for target recognition once extracted via parameter estimation. However, micro-Doppler is usually too significant to result in aliasing in the terahertz band. According to this problem, a Doppler aliasing free micro-motion parameter estimation method based on the modulo Generalized Hough transform is proposed in this paper. Its basic idea is to search and match the parameters of aliasing micro-Doppler curves in the time-frequency distribution image. The high estimation precision and excellent noise immunity of this method are verified through simulations based on CST data and experiments based on a 0.33 THz radar system.

Deep neural networks (DNNs) require large-scale labeled data sets to prevent overfitting while having good generalization. In radar applications, however, acquiring a measured data set of the order of thousands is challenging due to constraints on manpower, cost, and other resources. In this letter, the efficacy of two neural network initialization techniques-unsupervised pretraining and transfer learning-for dealing with training DNNs on small data sets is compared. Unsupervised pretraining is implemented through the design of a convolutional autoencoder (CAE), while transfer learning from two popular convolutional neural network architectures (VGGNet and GoogleNet) is used to augment measured RF data for training. A 12-class problem for discrimination of micro-Doppler signatures for indoor human activities is utilized to analyze activation maps, bottleneck features, class model, and classification accuracy with respect to training sample size. Results show that on meager data sets, transfer learning outperforms unsupervised pretraining and random initialization by 10% and 25%, respectively, but that when the sample size exceeds 650, unsupervised pretraining surpasses transfer learning and random initialization by 5% and 10%, respectively. Visualization of activation layers and learned models reveals how the CAE succeeds in representing the micro-Doppler signature.

Farklı hedef tipleri veya aynı hedefin farklı hareketleri için radar mikro-Doppler sinyalleri birbirinden farklı olmaktadır. Bu durum, radar mikro-Doppler sinyallerinin hedef sınıflandırması için kaynak olarak kullanılması fikrini doğurmuştur. Son 10 yılda mikro-Doppler tabanlı birçok sınıflandırma çalışması yayınlanmıştır. Bu çalışmalar, deneysel radar verileri kullanılarak yapıldığında genellikle yakın mesafelerden ve parazit yansımanın önemsiz olduğu durumlar için gerçekleştirilmektedir. Benzetim çalışmalarında da gürültü ve parazit yansıma etkileri çoğu zaman ihmal edilmektedir. Sınıflandırma başarımının gürültü ve parazit yansıma etkilerinin ihmal edildiği ideal durumlar için ölçülmesi, yapılan çalışmanın sonuçlarını gerçeklikten uzaklaştırmaktadır. Bu çalışmada, benzetim verileri kullanılarak mikro-Doppler imzaları üzerinden bir sınıflandırma çalışması gerçekleştirilmiştir. Hedeflere ait radar benzetim verileri oluşturulurken gürültü ve parazit yansıma etkileri de modellenmiştir. Gürültü ve parazit yansımalı verilerle elde edilen sınıflandırma başarımı, gürültüsüz durumda elde edilen ile karşılaştırılmıştır. Ayrıca, gürültülü durumda görüntü işleme teknikleri kullanılarak başarımı artırmak için bir yöntem önerilmiştir. Sonuçlar iki farklı sınıflandırıcı ile denenmiş ve önerilen yöntemin sınıflandırma başarımında %5 ile %15 arasında bir artış sağladığı görülmüştür., Micro-Doppler radar signals for different target types or different movements of a target are also different from each other. This leads to usage of micro-Doppler radar signals as a source of classifying targets. Many micro-Doppler based target classification studies have been published in the last ten years. The studies which are done using experimental radar data are usually carried out in situations where target is close to the radar and clutter effect is minimal. In simulation studies, noise and clutter effects are also ignored. Measurement of classification performance for idealistic conditions in which noise and clutter effects are not taken into account makes the outcomes of the study doubtful. In this thesis, a classification study of micro-Doppler based target signatures is carried out using simulation data. While generating radar simulation data of targets, noise and clutter effects are also modeled. Classification performance obtained from the data containing noise and clutter is compared to noise free data. In addition, a method is proposed to increase the performance in noisy situations using image processing techniques. The results are obtained with two different classifiers and the proposed method has made an increase from 5% to 15% in the classification performance.

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. In the literature, many different features have been proposed for classification applications. However, it is not known which features have a greater impact on classification performance, or indeed how many features should be used to achieve good classification. In this work, the mutual information of features extracted from human micro-Doppler signatures is computed. Taking the problem of classifying human arm-swing as an example, the features extracted are ordered in terms of importance.

Human detection offers many advantages in applications of search and rescue, smart environments, and security. Infrared, acoustic, vibration/seismic and visual sensors have been often used in human detection and recognition systems. Radar offers unique advantages for sensing humans, such as remote operation during virtually all weather conditions, increased range, and better coverage. However, radar systems are typically very expensive and physically large. The Bumble Bee radar, in contrast to most radars, is a low power pulse Doppler radar that is about the size of a business card. Moreover, it is a radar that can be integrated into indoor wireless sensor networks. In this work, the application of Bumble Bee radar to human activity recognition by computing the human micro-Doppler signature is examined. Humans are complex targets that are capable of many motions. Every part of the human causes different reflection and every motion of the human has its unique micro-doppler signatures. The differences in micro-Doppler data of activities such as walking, running, and crawling that is gathered from low-cost, low-power radar is discussed.

Radar gözetleme sistemlerindeki asıl zorluk insanların hayvanlardan ayrılması olduğu kadar farklı insan hareketlerinin ayrılmasını da kapsamaktadır. Bu nedenle hedef mikro-Doppler imzalarının otomatik hedef sınıflandırması için yüksek başarıma sahip olduğu gösterilse de sonuçlar operasyonel koşulların ideal olduğu durumlar ve belirli öznitelik kümeleri için verilmektedir. Geçmiş yıllarda çok sayıda öznitelik mikro-Doppler imzalarının sınıflandırılması için önerilmiştir. Ancak önerilen özniteliklerinin tümünün kullanılması maksimum sınıflandırma başarımının verilmesini garanti etmemekte ve ideal öznitelik alt kümesinin seçilmesi ise senaryoya bağımlı olarak değişmektedir. Bu çalışmada, kapsamlı olarak mikro-Doppler öznitelik çıkarım yöntemleri ve çıkartılan özniteliklerin radar sistem parametleri ve operasyonel koşullara – merkez frekansı, menzil ve Doppler çözünürlüğü, anten hedef geometrisi, sinyal gürültü oranı ve hedef üzerinde kalma süresi – olan bağımlılıklarını incelemektedir. İnsan mikro-Doppler imzalarına uyarlı bir öznitelik dizaynı gerçekleştirilmiştir. Sınıflandırma performansını en iyileştirecek, azaltılmış sayıda olan özniteliklerin çıkartılması için algoritmalar önerilmiş ve iyi seçilmiş bir öznitelik alt kümesinin daha iyi başarımlar ortaya konduğu gösterilmiştir. Durum çalışması yapılarak önerilen uyarlanabilir öznitelik seçim algoritmasının sınıflandırma performansını arttırılabileceği gösterilmiştir., A key challenge for radar survelliance systems is the discrimination of ground based targets, especially humans from animals, as well as different types of human activities. For this purpose, target micro-Doppler signatures have been shown to yield high automatic target classification rates; however, performance is typically only given for near-optimal operating conditions using a fixed set of features. Over the past decade a vast number of micro-Doppler features have been proposed for classification of radar micro-Doppler signatures. In fact utilization of all possible features does not guarantee maximum classification performance and the selection of an optimal subset of features is scenario dependent. In this work, a comprehensive survey of micro-Doppler features and their dependence upon system parameters and operational conditions – such as transmit frequency, range and Doppler resolution, antenna target geometry, signal to noise ratio, and dwell time – is given. A new feature design for human micro-Doppler signatures is proposed. Algorithms for optimizing classification performance for a reduced number of features are presented and it is shown that a well selected subset of robust features yields better results. Performance gains achievable using adaptive feature selection are assessed for a case study of interest.

Developing automatic target classification algorithms using radar is a widely researched topic in recent years. Among the targets classified in these algorithms, the most studied is humans. Classification of humans with high accuracy is very significant for many military and civil applications. Moreover, in these studies, besides the classification of human target, activities are also analyzed. Knowledge of the activity a person is engaged in can substantially change the alarm level in some applications. In this paper, an algorithm that automatically classifies walking, running, crawling, and creeping using radar is presented.