Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Detection and Classification for Low-altitude Micro Drone with MFCC and CNN

MFCC와 CNN을 이용한 저고도 초소형 무인기 탐지 및 분류에 대한 연구

  • Shin, Kyeongsik (Department of Electronics and Communication Engineering, Kwangwoon University) ;
  • Yoo, Sinwoo (Department of Electronics and Communication Engineering, Kwangwoon University) ;
  • Oh, Hyukjun (Department of Electronics and Communication Engineering, Kwangwoon University)
  • Received : 2019.11.18
  • Accepted : 2020.02.10
  • Published : 2020.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

This paper is related to detection and classification for micro-sized aircraft that flies at low-altitude. The deep-learning based method using sounds coming from the micro-sized aircraft is proposed to detect and identify them efficiently. We use MFCC as sound features and CNN as a detector and classifier. We've proved that each micro-drones have their own distinguishable MFCC feature and confirmed that we can apply CNN as a detector and classifier even though drone sound has time-related sequence. Typically many papers deal with RNN for time-related features, but we prove that if the number of frame in the MFCC features are enough to contain the time-related information, we can classify those features with CNN. With this approach, we've achieved high detection and classification ratio with low-computation power at the same time using the data set which consists of four different drone sounds. So, this paper presents the simple and effecive method of detection and classification method for micro-sized aircraft.

본 논문은 저고도로 비행하는 초소형 무인기에 대한 탐지 및 분류에 대한 기술로써, 단순히 초소형 무인기를 탐지만 하는 것이 아니라 탐지된 무인기의 종류 및 모델까지 인식하는 심화학습 기반 탐지 및 분류 기법을 제안한다. 무인기의 소리 특성으로 MFCC를 사용하였고 탐지 및 분류를 위해 CNN를 사용하였다. 무인기들은 각각 CNN을 통해 구분할 수 있는 MFCC 특성을 가짐을 입증하였고, 또한 총 4가지의 무인기에 대한 dataset을 대상으로 분류를 한 결과 time-related sequence를 가지는 MFCC라 하더라도 RNN 대신 CNN를 사용하면 탐지 및 분류 능력을 갖추면서도 연산량을 줄일 수 있음을 검증하였다. 따라서 본 논문은 간단하면서도 효과적인 초소형 무인기 탐지 및 분류 방법을 제시한다.

Keywords

References

  1. A. V. Oppenheim, and R. W. Schafer, "From frequency to quefrency: A history of the cepstrum," IEEE signal processing Magazine 21.5 (2004): 95-106. https://doi.org/10.1109/MSP.2004.1328092
  2. S. Umesh, L. Cohen, and D. Nelson, "Fitting the mel scale," 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. no. 99CH36258). vol. 1, IEEE, 1999.
  3. B. Logan, "Mel Frequency Cepstral Coefficients for Music Modeling," ISMIR. vol. 270, 2000.
  4. L. Muda, M. Begam, and I. Elamvazuthi, "Voice recognition algorithms using mel frequency cepstral coefficient (MFCC) and dynamic time warping (DTW) techniques," arXiv preprint arXiv:1003.4083 (2010).
  5. J. S. Chung, A. Senior, O. Vinyals, and A. Zisserman, "Lip reading sentences in the wild," 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2017.
  6. S. Jeon, J. W. Shin, Y. J. Lee, W. H. Kim, W. H. Kim, Y. Kwon, and H. Y. Yang, "Empirical study of drone sound detection in real-life environment with deep neural networks," 2017 25th European Signal Processing Conference (EUSIPCO). IEEE, 2017.
  7. C. Aker, and S. Kalkan, "Using deep networks for drone detection," 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS). IEEE, 2017.
  8. M. Saqib, S. D. Khan, N. Sharma, and M. Blumenstein, "A study on detecting drones using deep convolutional neural networks," 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS). IEEE, 2017.