Underwater Object Detection and Pose Estimation using Deep Learning. Issue 21 (2019)

• Record Type: Journal Article
• Authors: Jeon, MyungHwan; Lee, Yeongjun; Shin, Young-Sik; Jang, Hyesu; Kim, Ayoung
• Is Part Of: IFAC-PapersOnLine. Volume 52:Issue 21(2019)
• Page Start: 78
• Page End: 81
• Publication Date: 2019
• Subjects: Automatic control -- Periodicals; 629.805
• DOI: 10.1016/j.ifacol.2019.12.286
• Languages: English
• ISSNs: 2405-8963

Abstract

Abstract: This paper presents an approach for making a dataset using a 3D CAD model for deep learning based underwater object detection and pose estimation. We also introduce a simple pose estimation network for underwater objects. In the experiment, we show that object detection and pose estimation networks trained via our synthetic dataset present a preliminary potential for deep learning based approaches in underwater. Lastly, we show that our synthetic image dataset provides meaningful performance for deep learning models in underwater environments.