Efficient Classification of Birds and Drones Considering Real Observation Scenarios Using FMCW Radar

Yoon, Se-Won; Kim, Soo-Bum; Jung, Jin‐Myung; Cha, Sangbin; Baek, Youngseok; Koo, Bontae; Choi, In-Oh; Park, Sang-Hong

doi:10.26866/jees.2021.4.r.34

Cited by 11 publications

(8 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used an FMCW radar signal model described previously [18]. A FMCW radar continuously transmits and receives a chirp signal that has a period Tchirp.…”

Section: B Radar Signal Modeling For MDmentioning

confidence: 99%

“…Section IV analyzes and compares the accuracy of each protocol for various observation scenarios and finally, Section V presents our conclusions for the classification of the multiple drones and birds. We used a signal model described previously [18], and assumed that the drone is a quadcopter, which is the most widely used type. The quadcopter has four rotors and each rotor has two blades that have dimensions 2ab × 2bb (ab < bb) that are 180° apart and rotate around the rotor axis at rotation frequency fb (Fig.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Efficient Protocol to Use FMCW Radar and CNN to Distinguish Micro-Doppler Signatures of Multiple Drones and Birds

et al. 2022

View full text Add to dashboard Cite

Classification of multiple drones and birds by comparing micro-Doppler (MD) signatures is a very difficult task because the MD signatures of multiple birds can contaminate the MD signature of drones, and because a single drone can yield a very similar MD signature to that of multiple drones. In this paper, assuming a real observation scenario, we propose three protocols and analyze their accuracy in classification of multiple drones and birds by using the frequency modulated continuous wave radar and a convolutional neural network classifier. In simulations using models of rotating blades and of flapping wings, the method that uses training data that include combinations of drone and bird achieved an accuracy ~ 100 % for the majority vote classification; this result demonstrates that ours is the most appropriate method to distinguish multiple drones from birds.

show abstract

“…We used an FMCW radar signal model described previously [18]. A FMCW radar continuously transmits and receives a chirp signal that has a period Tchirp.…”

Section: B Radar Signal Modeling For MDmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Efficient Protocol to Use FMCW Radar and CNN to Distinguish Micro-Doppler Signatures of Multiple Drones and Birds

et al. 2022

View full text Add to dashboard Cite

show abstract

“…At this point, it is quite safe to say that most of the literature is inclined toward TD methods mainly because of the following reasons: Microwave imaging systems are analogous to radar systems where the transmitted signal is usually in the form of TD pulses [ 13 , 14 ]. Constructed images are in TD so the TD evaluation of scattering mechanisms can be combined with the imaging algorithms [ 15 , 16 ].…”

Section: Introductionmentioning

confidence: 99%

“…Microwave imaging systems are analogous to radar systems where the transmitted signal is usually in the form of TD pulses [ 13 , 14 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Localization of Dielectric Anomalies with Multi-Monostatic S11 Using 2D MUSIC Algorithm with Spatial Smoothing

Borjali

Cho

2022

Sensors

View full text Add to dashboard Cite

This article demonstrates that the complex value of S11 of an antenna, acquired in a multi-monostatic configuration, can be used for localization of a dielectric anomaly hidden inside a dielectric background medium when the antenna is placed close (~5 mm) to the geometry. It uses an Inverse Synthetic Aperture Radar (ISAR) imaging framework where data is acquired at multiple frequencies and look-angles. Initially, near-field scattering data are used for simulation to validate this methodology since the basic derivation of the Multiple Signal Classification (MUSIC) algorithm is based on the plain wave assumption. Later on, from an applications perspective, data acquisition is performed using an antipodal Vivaldi antenna that has eight constant-width slots on each arm. This antenna operates in a frequency range of 1 to 8.5 GHz and its S11 is fed to the 2D MUSIC algorithm with spatial smoothing whereas the antenna artifact and background effect are removed by subtracting the average S11 at each antenna location. Measurements reveal that this methodology gives accurate results with both homogeneous and inhomogeneous backgrounds because the size of data sub-arrays trades between the image noise and resolution, hence reducing the effect of inhomogeneity in the background. In addition to near-field ISAR imaging, this study can be used in the ongoing research on breast tumors and brain stroke detection, among others.

show abstract

Designing a polarization‐insensitive and ultra‐wideband transmissive polarization convertor using a tightly coupled dipole array

Kim

Nam

2022

Micro & Optical Tech Letters

View full text Add to dashboard Cite

In this study, a polarization‐insensitive and ultra‐wideband transmissive polarization convertor (PC) is proposed. The proposed PC operates at 2.29–6.27 GHz (93.32%) for the same polarization reflection at ≤−10 dB, orthogonally rotated polarization transmission at ≥−1 dB, and a 0.22 λlow thickness at the lowest operating frequency. A dual‐polarized tightly coupled dipole array (TCDA) antenna is introduced for application in the wideband PC, where the operating bandwidth is related to the antenna bandwidth. Additionally, the polarization insensitivity is related to the feeding structure, which allows coupling of the receiving signal to the transmitting antenna. Furthermore, the operating principle is described in detail by showing the surface current on the TCDA and the feeding structure. Finally, unit cell simulations and measurements are presented to demonstrate the performance of the proposed PC.

show abstract

Efficient Classification of Birds and Drones Considering Real Observation Scenarios Using FMCW Radar

Cited by 11 publications

References 20 publications

Efficient Protocol to Use FMCW Radar and CNN to Distinguish Micro-Doppler Signatures of Multiple Drones and Birds

Efficient Protocol to Use FMCW Radar and CNN to Distinguish Micro-Doppler Signatures of Multiple Drones and Birds

Localization of Dielectric Anomalies with Multi-Monostatic S11 Using 2D MUSIC Algorithm with Spatial Smoothing

Designing a polarization‐insensitive and ultra‐wideband transmissive polarization convertor using a tightly coupled dipole array

Contact Info

Product

Resources

About