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
 1. 서 론
 2. 선행 연구 조사
  2.1 CNN기반 Object Detection
  2.2 3D CAD 모델을 사용한 이미지 생성
  2.3 Auto Annotation Tool
 3. Auto Annotation tool
  3.1 Sample 생성
 4. 이미지 합성
  4.1 Rendering Image
  4.2 Cropping Image
  4.3 Overlay Background
  4.4 수중 환경을 반영한 이미지 합성
  4.5 Translating synthetic image to haze image
 5. Object Detection
  5.1 청수로 채워진 수조에서의 실험(Non Haze Dataset)
  5.2 실제 수중 환경을 반영한 수조에서의 실험(Haze Dataset)
 6. 결 론
 References

• 정명환(Robotics Program, KAIST, Daejeon) | 전명환
• 이영준(Korea Research Institute Ship and Ocean engineering (KRISO)) | Yeongjun Lee
• 신영식(Dept. of Civil and Environmental Engineering, KAIST) | Young-Sik Shin
• 장혜수(Dept. of Civil and Environmental Engineering, KAIST) | Hyesu Jang
• 여태경(Korea Research Institute Ship and Ocean engineering (KRISO)) | Taekyeong Yeu
• 김아영(Dept. of Civil and Environmental Engineering, KAIST) | Ayoung Kim Corresponding author