Drone movement classification based on deep learning using micro-Doppler signature images
1
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
As drones become more popular, interest in drone detection as well as the use of drones is increasing. Small drones typically have a small radar cross section, which is difficult to detect with conventional radar sensors. To solve this problem, technology for detecting drones using micro-Doppler signatures has been introduced. In this study, a micro-Doppler signature was used to classify drone movement and detect drones. The radar signal returned from a drone was quickly calculated using the far-field approximation and reverse-rotating of the incident field with the method of moment. The dataset was created by generating spectrogram images for various incident angles and movements. Through transfer learning, we can classify the drone's four movements with an accuracy of at least 98%.
Abstract
As drones become more popular, interest in drone detection as well as the use of drones is increasing. Small drones typically have a small radar cross section, which is difficult to detect with conventional radar sensors. To solve this problem, technology for detecting drones using micro-Doppler signatures has been introduced. In this study, a micro-Doppler signature was used to classify drone movement and detect drones. The radar signal returned from a drone was quickly calculated using the far-field approximation and reverse-rotating of the incident field with the method of moment. The dataset was created by generating spectrogram images for various incident angles and movements. Through transfer learning, we can classify the drone's four movements with an accuracy of at least 98%.
참고문헌 (11)
- F. Fioranelli, "Classification of loaded", unloaded micro-drones using mul-tistatic radar, 2015, pp.51(22), 1813~1815
- M. Ritchie, "Multistatic micro-Doppler radar feature extraction for clas-sification of unloaded", loaded micro-drones, 2017, pp.11(1), 116~124
- B. K. Kim, "Drone classifica-tion using convolutional neural networks with merged Dop-pler images", IEEE Geoscience and Remote Sensing Letters, 14(1) (2017)
- B. K. Kim, "Experimental analysis of small drone polarimetry based on micro-Doppler signature", IEEE Geoscience and Remote Sensing Letters, 14(10) (2017)
- A. K. Singh, "Automatic measurement of blade length and rotation rate of drone using W-band micro-Doppler radar", IEEE Sensors Journal, 18(5) (2018)
- A. K. Singh, "Accurate measurement of drone’s blade length and rotation rate using pattern analysis with W-band radar", Electronics Letters, 54(8), pp.523~525 (2018)
- W. Zhang, "Detection of multiple micro-drones via cadence velocity diagram analysis", Electronics Letters, 54(7), pp.441~443 (2018)
- M. Rithie, "Micro-drone RCS analysis", Proceedings of the 2015 IEEE Radar Conference, pp.452~456 (2015)
- T. Li and, "Numerical simulation and experimental analysis of small drone rotor blade polarimetry based on RCS and micro-Doppler signature", IEEE Antennas Wire-less Propagation Letters, 18(1), pp.187~191 (2019)
- D. -Y. Lee, "Dynamic RCS esti-mation according to drone movement using MoM and far-field approximation", Journal of Electromagnetic Engineer-ing and Science
- W. Y. Yang, "Novel automatic algorithm for estimating the jet engine blade number of in-sufficient JEM signals", Journal of Electromagnetic Engi-neering and Science