The Transactions of The Korean Institute of Electrical Engineers (전기학회논문지)

The Korean Institute of Electrical Engineers (대한전기학회)
권호 표지
DOI QR코드

DOI QR Code

A Study of CR-DuNN based on the LSTM and Du-CNN to Predict Infrared Target Feature and Classify Targets from the Clutters

LSTM 신경망과 Du-CNN을 융합한 적외선 방사특성 예측 및 표적과 클러터 구분을 위한 CR-DuNN 알고리듬 연구

  • Received : 2018.11.30
  • Accepted : 2018.12.22
  • Published : 2019.01.01
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we analyze the infrared feature for the small coast targets according to the surrounding environment for autonomous flight device equipped with an infrared imaging sensor and we propose Cross Duality of Neural Network (CR-DuNN) method which can classify the target and clutter in coastal environment. In coastal environment, there are various property according to diverse change of air temperature, sea temperature, deferent seasons. And small coast target have various infrared feature according to diverse change of environment. In this various environment, it is very important thing that we analyze and classify targets from the clutters to improve target detection accuracy. Thus, we propose infrared feature learning algorithm through LSTM neural network and also propose CR-DuNN algorithm that integrate LSTM prediction network with Du-CNN classification network to classify targets from the clutters.

Keywords

DHJGII_2019_v68n1_153_f0001.png 이미지

그림 1 하절기 해상 소형표적의 적외선 방사특징 Fig. 1 Infrared features of small coast targets in summer season

DHJGII_2019_v68n1_153_f0002.png 이미지

그림 2 동절기 해상 소형표적의 적외선 방사특징 Fig. 2 Infrared features of small coast targets in winter season

DHJGII_2019_v68n1_153_f0003.png 이미지

그림 3 봄가을 해상 소형표적의 적외선 방사특징 Fig. 3 Infrared features of small coast targets in spring/fall season

DHJGII_2019_v68n1_153_f0004.png 이미지

그림 4 1년간 해상 소형표적의 적외선 방사특징 Fig. 4 Infrared features of small coast targets in four season

DHJGII_2019_v68n1_153_f0005.png 이미지

그림 5 계절별 해상 소형표적의 신호세기 Fig. 5 Infrared signal intensity of small coast target by seasons

DHJGII_2019_v68n1_153_f0006.png 이미지

그림 6 계절별 해상 배경의 신호세기 Fig. 6 Infrared signal intensity of sea background by seasons

DHJGII_2019_v68n1_153_f0007.png 이미지

그림 7 적외선 방사특징 예측시스템 LSTM 모델 구조 Fig. 7 LSTM model structure of infrared feature prediction system

DHJGII_2019_v68n1_153_f0008.png 이미지

그림 8 적외선 방사특징 예측시스템 손실함수/정확도 Fig. 8 loss-function / accuracy of infrared feature prediction system

DHJGII_2019_v68n1_153_f0009.png 이미지

그림 9 CR-DuNN 알고리듬 구조 Fig. 9 Algorithm structure of CR-DuNN

표 1 표적과 클러터 구분 결과 비교 Table 1 Comparison result of classification

DHJGII_2019_v68n1_153_t0001.png 이미지

References

  1. Juyoung Lee et al., "An Analysis of Infrared Feature for the Small Coast Targets and applying The Artificial Intelligence Method", KIMST Fall Conference Proceedings, pp. 1201-1202, November. 2018.
  2. Kyung Ha Kim, "A Study on the characteristics of Sunglint in LongWave InfraRed Band", KIMST, Vol. 21, No. 3, pp. 306-314, 2018.
  3. C. Yang, H. Liu, S. Liao and S. Wang, "Small Target Detection in Infrared Video Sequence using Robust Dictionary Learning," Infrared Physics & Technology, Vol. 68, pp. 1-9, 2015. https://doi.org/10.1016/j.infrared.2014.09.039
  4. S. Qi, J. ma, H. Li, S. Zhang and J. Tian, "Infrared Small Target Enhancement via Phase Spectrum of Quaternion Fourier Transform," Infrared Physics & Technology, vol. 62, pp. 50-58, 2014. https://doi.org/10.1016/j.infrared.2013.10.008
  5. Juyoung Lee et al., "A Design of Du-CNN based on the Hybrid Machine Characters to Classify Target and Clutter in the IR Image", KIMST, Vol. 20, No. 6, pp. 758-766, Dec. 2017.
  6. Juyoung Lee et al., "A study of image classification using HMC method applying CNN ensemble in the infrared image", Journal of Electrical Engineering and Technology, Vol. 13, No. 3, pp. 1377-1382, May. 2018. https://doi.org/10.5370/JEET.2018.13.3.1377
  7. Chunho Kim et al., "A study of operational concept of guided missile by network-based Smart Device target information", KIMST Annual Conference Proceedings, pp. 1480-1481, June. 2017.
  8. Sepp Hochreiter, Jurgen Schmidhuber, "LONG SHORTTERM MEMORY", Neural Computation, 1997.
  9. Odegaard, N., Knapskog, A. O., Cochin, C., Louvigne, J. C. "Classification of ships using real and simulated data in a convolutional neural network", Rader Conference, 2016.
  10. Hore A, Ziou D, "Image quality metrics: PSNR vs SSIM", ICPR 20th, Vol. 1, pp. 2366-2369, 2010.
  11. G. Chen et al, "Region-based moving object detection Using SSIM", ICCSNT 4th, Vol. 1, pp. 1361-1364, IEEE, 2015.