수중에서의 특징점 매칭을 위한 CNN기반 Opti-Acoustic변환
CNN-based Opti-Acoustic Transformation for Underwater Feature Matching
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
In this paper, we introduce the methodology that utilizes deep learning-based front-end to enhance underwater feature matching. Both optical camera and sonar are widely applicable sensors in underwater research, however, each sensor has its own weaknesses, such as light condition and turbidity for the optic camera, and noise for sonar. To overcome the problems, we proposed the opti-acoustic transformation method. Since feature detection in sonar image is challenging, we converted the sonar image to an optic style image. Maintaining the main contents in the sonar image, CNN-based style transfer method changed the style of the image that facilitates feature detection. Finally, we verified our result using cosine similarity comparison and feature matching against the original optic image.
Abstract
In this paper, we introduce the methodology that utilizes deep learning-based front-end to enhance underwater feature matching. Both optical camera and sonar are widely applicable sensors in underwater research, however, each sensor has its own weaknesses, such as light condition and turbidity for the optic camera, and noise for sonar. To overcome the problems, we proposed the opti-acoustic transformation method. Since feature detection in sonar image is challenging, we converted the sonar image to an optic style image. Maintaining the main contents in the sonar image, CNN-based style transfer method changed the style of the image that facilitates feature detection. Finally, we verified our result using cosine similarity comparison and feature matching against the original optic image.
참고문헌 (16)
- Y. Cho, "Online depth estimation and application to underwater image dehazing", OCEANS 2016MTS, 2016, 1~7
- Y. Cho, "Visibility enhancement for underwater visual slam based on underwater light scattering model", 2017IEEE International Conference on Robotics and Automation (ICRA), pp.710~717 (2017)
- J. Li, "Watergan : unsupervised generative network to enable realtime color correction of monocular underwater images", IEEE Robotics and Automation Letters, 3(1), pp.387~394 (2018)
- N. Hurtós, "Fourier-based registrations for two-dimensional forward-looking sonar image mosaicing", 2012 IEEE, 2012, 5298~5305
- J. Li, "Pose-graph slam using forward-looking sonar", IEEE Robotics and Automation Letters, 3(3), pp.2330~2337 (2018)
- S. Negahdaripour, "Optiacoustic stereo imaging : On system calibration and 3-d target reconstruction", IEEE Transactions on Image Processing, 18(6), pp.1203~1214 (2009)
- D. -H. Gwon, "Nontemporal relative pose estimation for opti-acoustic bundle adjustment", OCEANS 2016 MTS, 2016, 1~5
- L. A. Gatys, "Texture synthesis using convolutional neural networks", Computer Vision and Pattern Recognition, pp.262~270 (2015)
- K. Simonyan, "Very deep convolutional networks for large-scale image recognition", arXiv:1409.1556, ~ (2014)
- L. Gatys, "A neural algorithm of artistic style", Journal of Vision (2015)
- P. Isola, "Imageto-image translation with conditional adversarial networks", 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.1125~1134 (2017)
- J. -Y. Zhu, "Unpaired image-to-image translation using cycle-consistent adversarial networks", 2017 IEEE International Conference on Computer Vision (ICCV), pp.2223~2232 (2017)
- L. A. Gatys, "Image style transfer using convolutional neural networks", 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
- 신영식, "항법 적용을 위한 수중 소나 영상 처리 요소 기법 비교 분석", 한국해양공학회지, 30(3), pp.214~220 (2016), 한국해양공학회
- 전명환, "강건한 CNN기반 수중 물체 인식을 위한 이미지 합성과 자동화된 Annotation Tool", 로봇학회 논문지, 14(2), pp.139~149 (2019), 한국로봇학회[DOI]
- 신영식, "수중 영상 소나의 번들 조정과 3차원 복원을 위한 운동 추정의 모호성에 관한 연구", 로봇학회 논문지, 11(2), pp.051~059 (2016), 한국로봇학회[DOI]