Segmentation of underwater images using morphology for deep learning

Ji-Eun Lee; Chul-Won Lee; Seok-Joon Park; Jea-Beom Shin; Hyun-Gi Jung

doi:10.7776/ASK.2023.42.4.370

All Issue

2023 Vol.42, Issue 4 Preview Page

Research Article

Segmentation of underwater images using morphology for deep learning 딥러닝을 위한 모폴로지를 이용한 수중 영상의 세그먼테이션

31 July 2023. pp. 370-376

PDF XML

Abstract

In the underwater image, it is not clear to distinguish the shape of the target due to underwater noise and low resolution. In addition, as an input of deep learning, underwater images require pre-processing and segmentation must be preceded. Even after pre-processing, the target is not clear, and the performance of detection and identification by deep learning may not be high. Therefore, it is necessary to distinguish and clarify the target. In this study, the importance of target shadows is confirmed in underwater images, object detection and target area acquisition by shadows, and data containing only the shape of targets and shadows without underwater background are generated. We present the process of converting the shadow image into a 3-mode image in which the target is white, the shadow is black, and the background is gray. Through this, it is possible to provide an image that is clearly pre-processed and easily discriminated as an input of deep learning. In addition, if the image processing code using Open Source Computer Vision (OpenCV)Library was used for processing, the processing speed was also suitable for real-time processing.

Keywords

Underwater exploration using side scan sonar and synthetic aperture sonar images

Deep learning input images

Morphology segmentation

Underwater target detection

수중영상은 수중 잡음과 낮은 해상도로 표적의 형상과 구분이 명확하지 않다. 그리고 딥러닝의 입력으로 수중영상은 전처리가 필요하며 Segmentation이 선행되어야 한다. 전처리를 하여도 표적은 명확하지 않으며 딥러닝에 의한 탐지, 식별의 성능도 높지 않을 수 있다. 따라서 표적을 구분하며 명확하게 하는 작업이 필요하다. 본 연구에서는 수중영상에서 표적 그림자의 중요성을 확인하고 그림자에 의한 물체 탐지 및 표적 영역 획득, 그리고 수중배경이 없는 표적과 그림자만의 형상이 담긴 데이터를 생성하며 더 나아가 픽셀값이 일정하지 않은 표적과 그림자 영상을 표적은 흰색, 그림자는 흑색, 그리고 배경은 회색의 3-모드의 영상으로 변환하는 과정을 제시한다. 이를 통해 딥러닝의 입력으로 명확히 전처리된 판별이 용이한 영상을 제공할 수 있다. 또한 처리는 Open Source Computer Vision(OpenCV)라이브러리의 영상처리 코드를 사용했으면 처리 속도도 역시 실시간 처리에 적합한 결과를 얻었다.

키워드

사이드 스캔 소나 및 합성개구 소나 영상 활용 수중 탐사

딥러닝 입력 영상

모폴로지 세그먼테이션

수중 표적 탐지

References

D. G, S. S, and M.V. Judy, "Survey on deep learning techniques used for classification of underwater sonar images," Proc. ISMAC-CVB, 53-58 (2020).

P. Soviany and R. T. Ionescu, "Optimizing the trade- off between single-stage and two-stage deep object detectors using image difficulty prediction," Proc. SYNASC, 1-6 (2018). 10.1109/SYNASC.2018.00041

R. Girshick, J. Donahue, T. Darrell, and J. Malik. "Rich feature hierarchies for accurate object detection and semantic segmentation," Proc. IEEE Conf. CVPR, 580-587 (2014). 10.1109/CVPR.2014.81

K. E. A. Sande, J. R. R. Uijlings, T. Gevers, and A. W. M. Smeulders, "Segmentation as selective search for object recognition," Proc. ICCV, 1879-1886 (2011).

H. Shi, H. Wang, C. Zhao, and Z. Shen, "Sonar image preprocessing based on morphological wavelet transform," Proc. ICIA, 1113-1117 (2010). 10.1109/ICINFA.2010.5512170

A. P. Leros and A. S. Andreatos, "Target detection in sonar images using morphological operations and empirical mode decomposition," J. Appl. Math. Bioinform. 6, 1-21 (2016).

H. Mao, H. Yan, L. Lin, W. Dong, Y. Li, Y. Liu, and J. Xue, "Fast segmentation method of sonar images for jacket installation environment," IASC, 36, 1671- 1686 (2023). 10.32604/iasc.2023.028819

R. C. Gonzalez, Digital Image Processing 2nd Ed. (Prentice Hall, New Jersey, 2002), pp. 519-621.

J. E. Lee and T. B. Shim, "Research on segmentation for sidescan sonar image by morphological method" (in Korean), Journal of the Institute of Electronics and Information Engineers, 49, 143-148 (2012). 10.5573/ieek.2012.49.12.003

Information

Publisher :The Acoustical Society of Korea
Publisher(Ko) :한국음향학회
Journal Title :The Journal of the Acoustical Society of Korea
Journal Title(Ko) :한국음향학회지
Volume : 42
No :4
Pages :370-376
Received Date : 2023-05-09
Revised Date : 2023-07-06
Accepted Date : 2023-07-17
DOI :https://doi.org/10.7776/ASK.2023.42.4.370

The Journal of the Acoustical Society of KoreaISSN:1225-4428(Print) 2287-3775(Online)한국음향학회

All Issue