강건한 CNN기반 수중 물체 인식을 위한 이미지 합성과 자동화된 Annotation Tool
Synthesizing Image and Automated Annotation Tool for CNN based Under Water Object Detection
0
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
In this paper, we present auto-annotation tool and synthetic dataset using 3D CAD model for deep learning based object detection. To be used as training data for deep learning methods, class, segmentation, bounding-box, contour, and pose annotations of the object are needed. We propose an automated annotation tool and synthetic image generation. Our resulting synthetic dataset reflects occlusion between objects and applicable for both underwater and in-air environments. To verify our synthetic dataset, we use MASK R-CNN as a state-of-the-art method among object detection model using deep learning. For experiment, we make the experimental environment reflecting the actual underwater environment. We show that object detection model trained via our dataset show significantly accurate results and robustness for the underwater environment. Lastly, we verify that our synthetic dataset is suitable for deep learning model for the underwater environments.
Abstract
In this paper, we present auto-annotation tool and synthetic dataset using 3D CAD model for deep learning based object detection. To be used as training data for deep learning methods, class, segmentation, bounding-box, contour, and pose annotations of the object are needed. We propose an automated annotation tool and synthetic image generation. Our resulting synthetic dataset reflects occlusion between objects and applicable for both underwater and in-air environments. To verify our synthetic dataset, we use MASK R-CNN as a state-of-the-art method among object detection model using deep learning. For experiment, we make the experimental environment reflecting the actual underwater environment. We show that object detection model trained via our dataset show significantly accurate results and robustness for the underwater environment. Lastly, we verify that our synthetic dataset is suitable for deep learning model for the underwater environments.
참고문헌 (19)
- R. Girshick, "Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation", 2014 IEEE Conference on Computer Vision and Pattern Recognition (2014)
- J. R. R. Uijlings, , International Journal of Computer Vision, 104(2), pp.154~171 (2013)
- J. Redmon, "You Only Look Once: Unified, Real-Time Object Detection", 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
- K. He, "Mask R-CNN", 2017 IEEE International Conference on Computer Vision (ICCV), pp.2980~2988 (2017)
- R. Girshick, "Fast R-CNN", 2015 IEEE International Conference on Computer Vision (ICCV), pp.1440~1448 (2015)
- X. Peng, "Exploring Invariances in Deep Convolutional Neural Networks using Synthetic Images", ~ (2014)
- H. Su, "Render for CNN:Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views", 2015 IEEE International Conference on Computer Vision (ICCV), pp.2686~2694 (2015)
- "3D Warehouse"[URL]
- M. Johnson-Roberson, "Driving in the Matrix: Can virtual worlds replace human-generated annotations for real world tasks?", 2017 IEEE International Conference on Robotics and Automation (ICRA) (2017)
- H. Hattori, "Synthesizing a Scene-Specific Pedestrian Detector and Pose Estimator for Static Video Surveillance", International Journal of Computer Vision, 126(9), pp.1027~1044 (2018)
- P. P. Busto, "Viewpoint refinement and estimation with adapted synthetic data", Computer Vision and Image Understanding, 169, pp.75~89 (2018)
- Y. Wang, "3D Pose Estimation for Fine-Grained Object Categories", European Conference on Computer Vision, pp.619~632 (2018)
- "Stichting Blender Foundation"[URL]
- J. Xiao, "SUN database: Large-scale scene recognition from abbey to zoo", 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp.3485~3492 (2010)
- M. Prats, "An open source tool for simulation and supervision of underwater intervention missions", 2012 IEEE, 2012, 2577~2582
- Y. Cho, "Channel invariant online visibility enhancement for visual SLAM in a turbid environment", Journal of Field Robotics, 35(7), pp.1080~1100 (2018)
- "SeaDrone"[URL]
- 이영준, "소나 영상을 이용한 확률적 물체 인식 구조 기반 수중로봇의 위치추정", 로봇학회 논문지, 9(4), pp.232~241 (2014), 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]