Journal of IKEEE (전기전자학회논문지)

Institute of Korean Electrical and Electronics Engineers (한국전기전자학회)
권호 표지
DOI QR코드

DOI QR Code

Real Time Hornet Classification System Based on Deep Learning

딥러닝을 이용한 실시간 말벌 분류 시스템

  • Received : 2020.12.02
  • Accepted : 2020.12.28
  • Published : 2020.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

The hornet species are so similar in shape that they are difficult for non-experts to classify, and because the size of the objects is small and move fast, it is more difficult to detect and classify the species in real time. In this paper, we developed a system that classifies hornets species in real time based on a deep learning algorithm using a boundary box. In order to minimize the background area included in the bounding box when labeling the training image, we propose a method of selecting only the head and body of the hornet. It also experimentally compares existing boundary box-based object recognition algorithms to find the best algorithms that can detect wasps in real time and classify their species. As a result of the experiment, when the mish function was applied as the activation function of the convolution layer and the hornet images were tested using the YOLOv4 model with the Spatial Attention Module (SAM) applied before the object detection block, the average precision was 97.89% and the average recall was 98.69%.

말벌 종은 모양이 매우 유사하기 때문에 비전문가가 분류하기 어렵고, 객체의 크기가 작고 빠르게 움직이기 때문에 실시간으로 탐지하여 종을 분류하는 것은 더욱 어렵다. 본 논문에서는 바운딩 박스를 이용한 딥러닝 알고리즘을 기반으로 말벌 종을 실시간으로 분류하는 시스템을 개발하였다. 훈련 영상의 레이블링 작업 시 바운딩 박스 안에 포함되는 배경 영역을 최소화하기 위하여 말벌의 머리와 몸통 부분만을 선택하는 방법을 제안한다. 또한 실시간으로 말벌을 탐지하고 그 종을 분류할 수 있는 최선의 알고리즘을 찾기 위하여 기존의 바운딩 박스 기반 객체 인식 알고리즘들을 실험을 통하여 비교한다. 실험 결과 컨볼루션 레이어의 활성함수로 mish 함수를 적용하고, 객체 검출 블록 전에 공간집중모듈(Spatial Attention Module, SAM)을 적용한 YOLOv4 모델을 사용하여 말벌 영상을 테스트한 경우 평균 97.89%의 정밀도(Precision)와 98.69%의 재현율(Recall)을 나타내었다.

Keywords

References

  1. Young-Soo Kim, "Development of Natural Luring Liquid Against the Wasps inflicting Honeybees," Journal of Apiculture, Vol.21, No.1, pp.37-42, 2006.
  2. Jin Sil Lee, "Development of trapping system for Vespa velutina and commercialization," Korean Society Of Applied Entomology, 2018.
  3. Cheolhee Lee, Yunju Jeong, "Performance Evaluation of YOLO according to Based Feature Extraction Network in Vespa Detection," Journal of Apiculture, Vol.35, No.3, pp.149-159, 2020. DOI: 10.17519/apiculture.2020.09.35.3.149
  4. Y. Lee, "Histogram of Oriented Gradients and Normalized Correlation Coefficient based Two-wheeler Detection System using Adaboost," Advanced Science and Technology Letters, Vol.129, pp.59-64, 2016. DOI: 10.14257/astl.2016.129.12
  5. T. Ojala, M. Pietikainen and D. Harwood, "A Comparative Study of Texture Measures with Classification Based on Feature Distributions," Pattern Recognition, Vol.29 No.1, pp.51-59, 1996. DOI: 10.1016/0031-3203(95)00067-4
  6. P. Viola and M. J. Jones, "Rapid Object Detection using a Boosted Cascade of Simple Features," CVPR 2001, 2001.
  7. X. Huang, S. Lei and J. Suykens, "Ramp loss linear programming support vector machine," Journal of Machine Learning Research, pp. 2185-2211, 2014. DOI: 10.5555/2627435.2670321
  8. SCHAPIRE, Robert E. "Explaining adaboost," Empirical inference. Springer, Berlin, Heidelberg, pp.37-52, 2013. DOI: 10.1007/978-3-642-41136-6_5
  9. WILSON, Phillip Ian, "FERNANDEZ, John. Facial feature detection using Haar classifiers," Journal of Computing Sciences in Colleges, Vol.21, No.4, pp.127-133, 2006. DOI: 10.5555/1127389.1127416
  10. Girshick, Ross. "Fast r-cnn," Proceedings of the IEEE international conference on computer vision. 2015.
  11. Ren, Shaoqing, et al. "Faster r-cnn: Towards real-time object detection with region proposal networks," Advances in neural information processing systems. 2015.
  12. He, Kaiming, et al. "Mask r-cnn," Proceedings of the IEEE international conference on computer vision. 2017.
  13. Redmon, Joseph, et al. "You only look once: Unified, real-time object detection," Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.
  14. Bochkovskiy, Alexey, Chien-Yao Wang, and Hong-Yuan Mark Liao. "YOLOv4: Optimal Speed and Accuracy of Object Detection." arXiv preprint arXiv:2004.10934, 2020.
  15. Redmon, Joseph, and Ali Farhadi. "Yolov3: An incremental improvement." arXiv preprint arXiv:1804.02767, 2018.
  16. Chethan Kumar B, "YOLOv3 and YOLOv4: Multiple Object Detection for Surveillance Applications," Proceedings of the Third International Conference on Smart Systems and Inventive Technology (ICSSIT 2020), pp.20-22, 2020. DOI: 10.21203/rs.3.rs-86158/v1
  17. Misra, Diganta. "Mish: A self regularized non-monotonic neural activation function." arXiv preprint arXiv:1908.08681, 2019.
  18. Alexey B., "YOLOv4 model zoo," https://github.com/AlexeyAB/darknet/wiki/YOLOv4-model-zoo