The Journal of Korea Robotics Society (로봇학회논문지)

Korea Robotics Society (한국로봇학회)
권호 표지
DOI QR코드

DOI QR Code

Study of Marker Detection Performance on Deep Learning via Distortion and Rotation Augmentation of Training Data on Underwater Sonar Image

수중 소나 영상 학습 데이터의 왜곡 및 회전 Augmentation을 통한 딥러닝 기반의 마커 검출 성능에 관한 연구

  • Lee, Eon-Ho (Mechanical Engineering, Kongju National University) ;
  • Lee, Yeongjun (Korea Research Institute of Ships and Ocean Engineering) ;
  • Choi, Jinwoo (Korea Research Institute of Ships and Ocean Engineering) ;
  • Lee, Sejin (Division of Mechanical & Automotive Engineering, Kongju National University)
  • Received : 2018.12.07
  • Accepted : 2019.01.10
  • Published : 2019.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

In the ground environment, mobile robot research uses sensors such as GPS and optical cameras to localize surrounding landmarks and to estimate the position of the robot. However, an underwater environment restricts the use of sensors such as optical cameras and GPS. Also, unlike the ground environment, it is difficult to make a continuous observation of landmarks for location estimation. So, in underwater research, artificial markers are installed to generate a strong and lasting landmark. When artificial markers are acquired with an underwater sonar sensor, different types of noise are caused in the underwater sonar image. This noise is one of the factors that reduces object detection performance. This paper aims to improve object detection performance through distortion and rotation augmentation of training data. Object detection is detected using a Faster R-CNN.

Keywords

References

  1. D. Ribas, P. Ridao, J. D. Tardos, and J. Neira, "Underwater SLAM in Man-Made Structured Environments", Journal of Field Robotics, vol. 25, no. 11-12, pp. 898-921, 2008. https://doi.org/10.1002/rob.20249
  2. S. Lee, "Deep Learning of Submerged Body Images from 2D Sonar Sensor based on Convolutional Neural Network", 2017 IEEE Underwater Technology(UT), Busan, South Korea, pp. 1-3, 2017.
  3. Y.-S. Shin, Y. Lee, H.-T. Choi, and A. Kim, "Bundle Adjustment and 3D Reconstruction Method for Underwater Sonar Image", Journal of Korea Robotics Society, vol. 11, no. 2, pp. 51-59, 2015. https://doi.org/10.7746/jkros.2016.11.2.051
  4. Y. Lee, J. Lee, and H.-T. Choi, "A Framework of Recognition and Tracking for Underwater Objects based on Sonar Images: Part 1. Design and Recognition of Artificial Landmark considering Characteristics of Sonar Images", Journal of the Institute of Electronics and Information Engineers, vol. 51, no. 2, pp. 182-189, 2014. https://doi.org/10.5573/ieie.2014.51.2.182
  5. S. Ren, K. He, R. Girshick, and J. Sun, "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks", IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 6, pp. 1137-1149, Jun., 2017. https://doi.org/10.1109/TPAMI.2016.2577031
  6. Shark Marine Technologies Inc., Navigator: Diver Held Sonar Imaging and Navigation System, [Online], http://www.sharkmarine.com, Accessed: December 5, 2018.
  7. P. Zhu, J. Isaacs, B. Fu, and S. Ferrari, "Deep learning feature extraction for target recognition and classification in underwater sonar images", 2017 IEEE 56th Annual Conference on Decision and Control (CDC), Melbourne, VIC, pp. 2724-2731, 2017.
  8. D. P. Williams, "Underwater target classification in synthetic aperture sonar imagery using deep convolutional neural networks", 2016 23rd International Conference on Pattern Recognition (ICPR), Cancun, Mexico, pp. 2497-2502, 2016.
  9. L. Jian, H. Yang, L. Zhong, and X. Ying, "Underwater Target Recognition Based on Line Spectrum and Support Vector Machine", International Conference on Mechatronics, Control and Electronic Engineering (MCE2014), pp. 79-84, 2014.
  10. X. Cao, X. Zhang, Y. Yu, and L. Niu, "Deep Learning-Based Recognition of Underwater Target", 2016 IEEE International Conference on Digital Signal Processing (DSP), Beijing, China, pp. 89-93, 2016.
  11. A. Krizhevsky, I. Sutskever, and G. E. Hinton, "ImageNet Classification with Deep Convolutional Neural Networks", Neural Information Processing Systems, pp. 84-90, Jun., 2017.
  12. R. Girshick, J. Donahue, T. Darrell, and J. Malik, "Rich feature hierarchies for accurate object detection and semantic segmentation", 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA, pp. 580-587, 2014.
  13. K. He, X. Zhang, S. Ren, and J. Sun, "Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition", European Conference on Computer Vision, pp. 346-361, 2014.
  14. R. Girshick, "Fast R-CNN", 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, pp. 1440-1448, 2015.
  15. Stanford University, Lecture 7: Training Neural Networks, part II(Update rules, ensembles, data augmentation, transfer learning), [Online], http://cs231n.stanford.edu/syllabus.html, Accessed: April 24, 2018.
  16. E. Lee, Y. Lee, J. Choi, and S. Lee, "Study of Marker Detection Performance via Training Data Augmentation for Partial Distortion of Underwater Sonar Image", The Korean Society of Mechanical Engineers Annual Conference, pp. 2176-2181, 2018.

Cited by

  1. 실시간 순환 신경망 기반의 멀티빔 소나 이미지를 이용한 수중 물체의 추적에 관한 연구 vol.15, pp.1, 2020, https://doi.org/10.7746/jkros.2020.15.1.008
  2. Marker-Based Method for Recognition of Camera Position for Mobile Robots vol.21, pp.4, 2019, https://doi.org/10.3390/s21041077