Underwater Object Detection and Pose Estimation using Deep Learning

Myunghwan Jeon; Yeongjun Lee; Young Sik Shin; Hyesu Jang; Ayoung Kim

doi:10.1016/j.ifacol.2019.12.286

Underwater Object Detection and Pose Estimation using Deep Learning

Myunghwan Jeon
, Yeongjun Lee
, Young Sik Shin
, Hyesu Jang
, Ayoung Kim

School of Mechanical Engineering

Korea Advanced Institute of Science and Technology
Korea Institute of Ocean Science & Technology

Research output: Contribution to journal › Conference article › peer-review

21 Scopus citations

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.

Original language	English
Pages (from-to)	78-81
Number of pages	4
Journal	IFAC-PapersOnLine
Volume	52
Issue number	21
DOIs	https://doi.org/10.1016/j.ifacol.2019.12.286
State	Published - 2019
Event	12th IFAC Conference on Control Applications in Marine Systems, Robotics, and Vehicles CAMS 2019 - Daejeon, Korea, Republic of Duration: 18 Sep 2019 → 20 Sep 2019

Access to Document

10.1016/j.ifacol.2019.12.286

Cite this

@article{25cb46e5653649a6a75448ed7c009c84,

title = "Underwater Object Detection and Pose Estimation using Deep Learning",

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.",

author = "Myunghwan Jeon and Yeongjun Lee and Shin, \{Young Sik\} and Hyesu Jang and Ayoung Kim",

note = "Publisher Copyright: {\textcopyright} 2019. The Authors. Published by Elsevier Ltd. All rights reserved.; 12th IFAC Conference on Control Applications in Marine Systems, Robotics, and Vehicles CAMS 2019 ; Conference date: 18-09-2019 Through 20-09-2019",

year = "2019",

doi = "10.1016/j.ifacol.2019.12.286",

language = "English",

volume = "52",

pages = "78--81",

journal = "IFAC-PapersOnLine",

issn = "2405-8971",

publisher = "Elsevier B.V.",

number = "21",

}

TY - JOUR

T1 - Underwater Object Detection and Pose Estimation using Deep Learning

AU - Jeon, Myunghwan

AU - Lee, Yeongjun

AU - Shin, Young Sik

AU - Jang, Hyesu

AU - Kim, Ayoung

PY - 2019

Y1 - 2019

N2 - 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.

AB - 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.

UR - https://www.scopus.com/pages/publications/85079597652

U2 - 10.1016/j.ifacol.2019.12.286

DO - 10.1016/j.ifacol.2019.12.286

M3 - Conference article

AN - SCOPUS:85079597652

SN - 2405-8971

VL - 52

SP - 78

EP - 81

JO - IFAC-PapersOnLine

JF - IFAC-PapersOnLine

IS - 21

T2 - 12th IFAC Conference on Control Applications in Marine Systems, Robotics, and Vehicles CAMS 2019

Y2 - 18 September 2019 through 20 September 2019

ER -

Underwater Object Detection and Pose Estimation using Deep Learning

Abstract

Access to Document

Other files and links

Fingerprint

Cite this