RCS based target recognition with real FMCW radar implementation

IET Radar, Sonar & Navigation, 2018

This study proposes an original ultra-wideband short-range radar (UWB-SRR) recognition system based on higherorder statistics (HOS) and support vector machines (SVMs). The main purpose of this work is to improve the road safety by implementing these techniques for detection and recognition of the uncovered road users such as pedestrians and cyclists. The combination of HOS and cell-averaging constant false alarm rate (CA-CFAR) radar detector has been proposed and investigated. The results show that a combination of HOS and CA-CFAR promises a good performance for UWB radar detector. The authors have also evaluated the performance of SVM-based target recognition system using normalised radar signature as input features. A total of 1000 signatures have been extracted for each class including pedestrian, cyclist, and car, where 50% of them have been used for the training data and the rest for the validation data. The results show that the SVM gives a good performance for the proposed system, where the recognition rates are up to 96.23, 95.25 and 97.23% for the cyclist, pedestrian and car. In the real testing performance using their scenarios, the system has successfully identified 92.77% of the right cyclist, 90.82% of the right pedestrian and 90.73% of the right car.

2007

Vehicle classification is of great importance to the development of Intelligent Transportation Systems. In this paper, a novel ground vehicle classification approach using unmodulated CW radar is proposed. The radar is set up to look forward down to the road; vehicles are modelled as body targets composed of multiple scattering centers. Analysis shows that the spatial distribution of scattering centers can be derived from the Doppler signature of radar echo. Hough Transform is performed to estimate the distribution which is then used for classification. In experiments, vehicles are classified into three types at an average accuracy of 94.8%.

Progress in Pattern …, 2006

This paper introduces an Automatic Target Recognition (ATR) method based on X Band Radar image processing. A software which implements this method was developed following four principal stages: digital image formation, image preprocessing, feature selection through a combination of C4.5 Decision Tree and PCA and classification using SVM. The automatic process was validated using two images sets, one of them containing real images with natural noise levels and the other with different degrees of impulsive noise contamination. The method achieves a very nice computation behavior and effectiveness, high accuracy and robustness in noise environments with a low storage memory and high decision speed.

IEEE Access

The Forward scattering radars (FSRs) are special types of Bistatic radars in which detected targets should exist in the narrow baseline to obtain their tracking at an angle of 180 degree. This gives the radar several features such as target classification which makes FSR more privileged in comparison to traditional radar systems. Existing research works concerning the ground target detection and classification have utilized neural network for the identification processes and compared it to other statistical models in terms of signal complexity. However, these works considered limited number of scenarios and thereby, the results are insufficient to create an automatic classification system. This study investigates and analyses the classification of ground targets in FSR using Machine-learning (ML) techniques, and proposes a hybrid model for ground target classification. The analysis in this paper represent a foundation for a potential use of pre-processing and signal processing techniques, statistical analysis, and ML in radar applications. The obtained results show that the k-nearest neighbor classifier (KNN) achieves the best performance in all examined scenarios. Additionally, combining multiple pre-processing techniques enhances the accuracy of classification by approximately 30.2% and increases the overall accuracy to more than 99%.

2021

This paper presents a method for classifying traffic participants based on high-resolution automotive radar sensors for autonomous driving applications. The major classes of traffic participants addressed in this work are pedestrians, bicyclists and passenger cars. The preprocessed radar detections are first segmented into distinct clusters using density-based spatial clustering of applications with noise (DBSCAN) algorithm. Each cluster of detections would typically have different properties based on the respective characteristics of the object that they originated from. Therefore, sixteen distinct features based on radar detections, that are suitable for separating pedestrians, bicyclists and passenger car categories are selected and extracted for each of the cluster. A support vector machine (SVM) classifier is constructed, trained and parametrised for distinguishing the road users based on the extracted features. Experiments are conducted to analyse the classification performanc...

2021

This work investigates the problem of unmanned aerial vehicles (UAVs) identification using their radar crosssection (RCS) signature. The RCS of six commercial UAVs are measured at 15 GHz and 25 GHz in an anechoic chamber, for both vertical-vertical and horizontal-horizontal polarization. The RCS signatures are used to train 15 different classification algorithms, each belonging to one of three different categories: statistical learning (SL), machine learning (ML), and deep learning (DL). The study shows that while the classification accuracy of all the algorithms increases with the signal-tonoise ratio (SNR), the ML algorithm achieved better accuracy than the SL and DL algorithms. For example, the classification tree ML achieves an accuracy of 98.66% at 3 dB SNR using the 15 GHz VV-polarized RCS test data from the UAVs. We investigate the classification accuracy using Monte Carlo analysis with the aid of boxplots, confusion matrices, and classification plots. On average, the accurac...

Compel, 2024

Purpose-This study focuses on the classification of targets with varying shapes using radar cross section (RCS), which is influenced by the target's shape. This study aims to develop a robust classification method by considering an incident angle with minor random fluctuations and using a physical optics simulation to generate data sets. Design/methodology/approach-The approach involves several supervised machine learning and classification methods, including traditional algorithms and a deep neural network classifier. It uses histogrambased definitions of the RCS for feature extraction, with an emphasis on resilience against noise in the RCS data. Data enrichment techniques are incorporated, including the use of noise-impacted histogram data sets. Findings-The classification algorithms are extensively evaluated, highlighting their efficacy in feature extraction from RCS histograms. Among the studied algorithms, the K-nearest neighbour is found to be the most accurate of the traditional methods, but it is surpassed in accuracy by a deep learning network classifier. The results demonstrate the robustness of the feature extraction from the RCS histograms, motivated by mmwave radar applications. Originality/value-This study presents a novel approach to target classification that extends beyond traditional methods by integrating deep neural networks and focusing on histogram-based methodologies. It also incorporates data enrichment techniques to enhance the analysis, providing a comprehensive perspective for target detection using RCS.

—This paper examines target detection using a Linear Support Vector Machine (L-SVM). Traditional radars typically use a Constant False Alarm Rate (CFAR) processor to adaptively adjust the detection threshold based on the fast-time return signal. The SVM formulation uses the same block-diagram structure as the CFAR approach; however, data from the leading and lagging windows is directly used to classify each cell under test. The L-SVM method is compared to a Cell-Averaging CFAR (CA-CFAR) on simulated radar return signals with and without Swerling I targets. The results show that the L-SVM is able to detect very small SNR signals, while the CA-CFAR is unable to detect these signals below –10 dB SNR. In addition, the probability of detection and probability of false alarm for the L-SVM degrade much more gracefully than for the CA-CFAR detector for low-SNR targets.

2022 IEEE/AIAA 41st Digital Avionics Systems Conference (DASC), 2022

This work studies binary classification problem for small airborne targets (drones vs other) by means of their trajectory analysis. For this purpose a set of the kinematic features extracted from drone trajectories using radar detections with a classification scheme that utilises Random Forests is proposed. The development is based on experimental data acquired from the Holographic radar from Aveillant Ltd. An approach for real-time classification is proposed, where an adaptive sliding window procedure is employed to make predictions over time from trajectories. Several models utilising different kinematic features (angle, slope, velocity, and their combination) are studied. The best model achieves an accuracy of more than 95%. In addition, fundamental issues with imbalanced datasets in the context of this topic are raised and illustrated using the collected data.

Pattern Recognition, 2000

This paper considers a mixture model approach to automatic target recognition using high-resolution radar measurements. The mixture model approach is motivated from several perspectives including requirements that the target classifier is robust to uncertainty in amplitude scaling, rotation and translation of the target. Estimation of the model parameters is achieved using the expectation-maximisation (EM) algorithm. Gamma mixtures are introduced and