Search Results (6)

This study evaluates different machine learning algorithms in detecting and identifying drones using radar data from a 60 GHz millimeter-wave sensor. These signals were collected from a bionic bird and two drones, namely DJI Mavic and DJI Phantom 3 Pro, which were represented in complex form to preserve amplitude and phase information. The first benchmarks used four algorithms, namely long short-term memory (LSTM), gated recurrent unit (GRU), one-dimensional convolutional neural network (Conv1D), and Transformer, and they were benchmarked for robustness under noisy conditions, including artificial noise types like white noise, Pareto noise, impulsive noise, and multipath interference. As expected, Transformer outperformed other algorithms in terms of accuracy, even on noisy data; however, in certain noise contexts, particularly Pareto noise, it showed weaknesses. For this purpose, we propose Multimodal Transformer, which incorporates more statistical features—skewness and kurtosis—in addition to amplitude and phase data. This resulted in a improvement in detection accuracy, even under difficult noise conditions. Our results demonstrate the importance of noise in processing radar signals and the benefits afforded by a multimodal presentation of data in detecting unmanned aerial vehicle and birds. This study sets up a benchmark for state-of-the-art machine learning methodologies for radar-based detection systems, providing valuable insight into methods of increasing the robustness of algorithms to environmental noise. Full article

Remote sensing techniques in the microwave frequency range have been successfully used in the context of bird, bat and insect measurements. This article breaks new ground in the analysis of freely flying insects by using a continuous-wave (CW) radar system in W-band, i.e., higher mm-wave frequencies, by measuring and analyzing the micro-Doppler signature of their wing beat motion. In addition to numerical and experimental methods, the investigation also includes the development of a new signal processing method using a cepstrogram approach in order to automatically determine the wing beat frequency. In this study, mosquitoes (culex pipiens) and bees (apis mellifera) are considered as model insects throughout the measurement campaign. It was found that 50 independent micro-Doppler measurements of mosquitoes and bees can be clearly distinguished from each other. Moreover, the proposed radar signal model accurately matches the experimental measurements for both species. Full article

Once, bird respiration was thought to be responsible for the 10 dB-level fluctuations in the radar signals of birds. Although, recently, many researchers provide evidence against this, there are almost no quantification measurements of the contribution of respiration to bird signals in microwave anechoic chambers. Here, we first measured the radar signals modulated by the respiration of birds in a microwave anechoic chamber. Theoretically, the simulated signal fluctuation caused by the respiration of a 1 kg standard avian target (SAT) duck is approximately 1.2 dB based on the water sphere model. Then, experimentally, in a microwave anechoic chamber, we measured the signal fluctuations produced by the respiration movement of ducks using a dynamic system composed of a network analyzer and a high-speed camera. We tracked continuous radar data of a living duck and a dead duck within the S-band, X-band, and Ku-band, and then presented them using low-resolution range profiles (LRRP) and high-resolution range profiles (HRRP). The results indicate that respiration movement causes periodic signal fluctuation with a respiration rate of approximately 0.7 Hz, but the amplitudes within S-band, X-band, and Ku-band are approximately 1 dB level, much less than the 10 dB level. Respiration is not responsible for the 10 dB-level periodic signal fluctuation in radar echoes from birds. Full article

Aiming at the difficult problem of the classification between flying bird and rotary-wing drone by radar, a micro-motion feature classification method is proposed in this paper. Using K-band frequency modulated continuous wave (FMCW) radar, data acquisition of five types of rotor drones (SJRC S70 W, DJI Mavic Air 2, DJI Inspire 2, hexacopter, and single-propeller fixed-wing drone) and flying birds is carried out under indoor and outdoor scenes. Then, the feature extraction and parameterization of the corresponding micro-Doppler (m-D) signal are performed using time-frequency (T-F) analysis. In order to increase the number of effective datasets and enhance m-D features, the data augmentation method is designed by setting the amplitude scope displayed in T-F graph and adopting feature fusion of the range-time (modulation periods) graph and T-F graph. A multi-scale convolutional neural network (CNN) is employed and modified, which can extract both the global and local information of the target’s m-D features and reduce the parameter calculation burden. Validation with the measured dataset of different targets using FMCW radar shows that the average correct classification accuracy of drones and flying birds for short and long range experiments of the proposed algorithm is 9.4% and 4.6% higher than the Alexnet- and VGG16-based CNN methods, respectively. Full article

Recent and archived data from weather radar networks are extensively used for the quantification of continent-wide bird migration patterns. While the process of discriminating birds from weather signals is well established, insect contamination is still a problem. We present a simple method combining two Doppler radar products within a Gaussian mixture model to estimate the proportions of birds and insects within a single measurement volume, as well as the density and speed of birds and insects. This method can be applied to any existing archives of vertical bird profiles, such as the European Network for the Radar surveillance of Animal Movement repository, with no need to recalculate the huge amount of original polar volume data, which often are not available. Full article

The increase in drone misuse by civilian apart from military applications is alarming and need to be addressed. This drone is characterized as a low altitude, slow speed, and small radar cross-section (RCS) (LSS) target and is considered difficult to be detected and classified among other biological targets, such as insects and birds existing in the same surveillance volume. Although several attempts reported the successful drone detection on radio frequency-based (RF), thermal, acoustic, video imaging, and other non-technical methods, however, there are also many limitations. Thus, this paper investigated a micro-Doppler analysis from drone rotating blades for detection in a special Forward Scattering Radar (FSR) geometry. The paper leveraged the identified benefits of FSR mode over conventional radars, such as improved radar cross-section (RCS) value irrespective of radar absorbing material (RAM), direct signal perturbation, and high resolutions. To prove the concept, a received signal model for micro-Doppler analysis, a simulation work, and experimental validation are elaborated and explained in the paper. Two rotating blades aspect angle scenarios were considered, which are (i) when drone makes a turn, the blade cross-sectional area faces the receiver and (ii) when drone maneuvers normally, the cross-sectional blade faces up. The FSR system successfully detected a commercial drone and extracted the micro features of a rotating blade. It further verified the feasibility of using a parabolic dish antenna as a receiver in FSR geometry; this marked an appreciable achievement towards the FSR system performance, which in future could be implemented as either active or passive FSR system. Full article