환경 소음 제거를 통한 범용적인 드론 음향 탐지 구현
A General Acoustic Drone Detection Using Noise Reduction Preprocessing
0
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
다양한 장소에서 드론이 활발하게 이용되면서 비행금지구역 내 불법 침입, 정보 유출, 항공기 충돌 등의 위험이 증가하고 있다. 이러한 위험을 줄이기 위해 비행금지구역으로 침입하는 드론을 탐지할 수 있는 시스템 구축이 필요하다. 기존의 드론 음향 탐지 연구는 탐지 모델에 환경 소음에 노출된 드론 음향을 그대로 학습시켰기 때문에 환경 소음에 독립적인 성능을 얻지 못했다. 이에 본 논문에서는 다양한 공간에서 환경 소음에 노출된 드론 음향을 명확하게 탐지하기 위해 주변 환경 소음을 별도로 수집하고, 드론 음향 신호에서 환경 소음을 제거하여 시끄러운 환경 속에서도 견고한 성능을 나타내는 범용적인 드론 탐지 시스템을 제안한다. 제안하는 시스템은 수집한 드론 음향 신호에서 환경 소음을 제거한 후 Mel Spectrogram 특성추출과 CNN 딥러닝을 이용하여 드론 존재 여부를 예측하였다. 실험 결과, 환경 소음으로 인해 감소했던 드론 탐지 성능을 7% 이상 향상시킴을 확인하였다.
Abstract
As individual and group users actively use drones, the risks (Intrusion, Information leakage, and Sircraft crashes and so on) in no-fly zones are also increasing. Therefore, it is necessary to build a system that can detect drones intruding into the no-fly zone. General acoustic drone detection researches do not derive location-independent performance by directly learning drone sound including environmental noise in a deep learning model to overcome environmental noise. In this paper, we propose a drone detection system that collects sounds including environmental noise, and detects drones by removing noise from target sound. After removing environmental noise from the collected sound, the proposed system predicts the drone sound using Mel spectrogram and CNN deep learning. As a result, It is confirmed that the drone detection performance, which was weak due to unstudied environmental noises, can be improved by more than 7%.
참고문헌 (31)
- A. Choi-Fitzpatrick, "Drones for good : technological innovations, social movements, and the state", Journal of International Affairs, 68(1), pp.19~36 (2014)
- Z. Shi, "An acoustic-based surveillance system for amateur drones detection and localization", IEEE transactions on vehicular technology, 69(3), pp.2731~2739 (2020)
- I. Guvenc, "Detection, tracking, and interdiction for amateur drones", IEEE Communications Magazine, 56(4), pp.75~81 (2018)
- D. Gettinger, "Drone sightings and close encounters: an analysis" (2015), Center for the Study of the Drone, Bard College
- S. Park, "Survey on anti-drone systems : components, designs, and challenges", IEEE Access, 9, pp.42635~42659 (2021)
- "Drones Still a Problem Even with Little Traffic"[URL]
- J. P. Yaacoub, "Security analysis of drones systems : Attacks, limitations, and recommendations", Internet of Things, 11, pp.100218~ (2020)
- "Two major Saudi oil installations hit by drone strike, and US blames Iran"[URL]
- M. A. Khan, "On the detection of unauthorized drones-techniques and future perspectives : a review", IEEE Sensors Journal, 22(12), pp.11439~11455 (2022)
- S. Jamil, "Malicious uav detection using integrated audio and visual features for public safety applications", Sensors, 20(14), pp.3923~ (2020)
- U. Seidaliyeva, "Real-time and accurate drone detection in a video with a static background", Sensors, 20(14), pp.3856~ (2020)
- Y. Seo, "Drone detection using convolutional neural networks with acoustic stft features", 2018 15th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp.1~6 (2018)
- X. Shi, "Anti-drone system with multiple surveillance technologies : architecture, implementation, and challenges", IEEE Communications Magazine, 56(4), pp.68~74 (2018)
- A. Rabaoui, "Using one-class SVMs and wavelets for audio surveillance", IEEE Transactions on information forensics and security, 3(4), pp.763~775 (2008)
- S. Salman, "Machine learning inspired efficient audio drone detection using acoustic features", 2021 International Bhurban Conference on Applied Sciences and Technologies (IBCAST), pp.335~339 (2021)
- M. Nijim, "Drone classification and identification system by phenome analysis using data mining techniques", 2016IEEE Symposium on Technologies for Homeland Security (HST), pp.1~5 (2016)
- A. Bernardini, "Drone detection by acoustic signature identification", Electronic Imaging, 29(10), pp.60~64 (2017)
- M. Z. Anwar, "Machine learning inspired sound-based amateur drone detection for public safety applications", IEEE Transactions on Vehicular Technology, 68(3), pp.2526~2534 (2019)
- P. Casabianca, "Acoustic-based uav detection using late fusion of deep neural networks", Drones, 5(3), pp.54~ (2021)
- D. Utebayeva, "Multi-label uav sound classification using stacked bidirectional lstm", 20204th IEEE International Conference on Robotic Computing (IRC), pp.453~458 (2020)
- S. Al-Emadi, "Audio based drone detection and identification using deep learning", 2019 15th International Wireless Communications & Mobile Computing Conference (IWCMC), pp.459~464 (2019)
- B. Yang, "Uav detection system with multiple acoustic nodes using machine learning models", 2019 3rd IEEE International Conference on Robotic Computing (IRC), pp.493~498 (2019)
- H. Kolamunna, "Droneprint : acoustic signatures for open-set drone detection and identification with online data", Proceedings of the acm on interactive, mobile, wearable and ubiquitous technologies, 5(1), pp.1~31 (2021)
- Q. Dong, "Drone sound detection system based on feature result-level fusion using deep learning", Multimedia Tools and Applications, pp.1~23 (2022)
- H. Liu, "Drone detection based on an audio-assisted camera array", 2017 IEEE 3rd International Conference on Multimedia Big Data (BigMM), pp.402~406 (2017)
- F. Christnacher, "Optical and acoustical uav detection", Electro-Optical Remote Sensing X, 9988, pp.83~95 (2016)
- J. Busset, "Detection and tracking of drones using advanced acoustic cameras", Unmanned, 2015, pp.9647, 53~60
- A. Sedunov, "Stevens drone detection acoustic system and experiments in acoustics uav tracking", 2019 IEEE International Symposium on Technologies for Homeland Security (HST), pp.1~7 (2019)
- S. Jeon, "Empirical study of drone sound detection in real-life environment with deep neural networks", 2017 25th European Signal Processing Conference (EUSIPCO), pp.1858~1862 (2017)
- Z. Uddin, "Independent vector analysis inspired amateur drone detection through acoustic signals", IEEE Access, 9, pp.63456~63462 (2021)
- İ. Aydın, "Development of a new light-weight convolutional neural network for acoustic-based amateur drone detection", Applied Acoustics, 193, pp.108773~ (2022)