Machine learning for shipwreck segmentation from side scan sonar imagery: Dataset and benchmark

被引:1
作者
Sethuraman, Advaith V. [1 ]
Sheppard, Anja [1 ]
Bagoren, Onur [1 ]
Pinnow, Christopher [2 ]
Anderson, Jamey [2 ]
Havens, Timothy C. [2 ]
Skinner, Katherine A. [1 ]
机构
[1] Univ Michigan, Dept Robot, 2505 Hayward St, Ann Arbor, MI 48109 USA
[2] Michigan Technol Univ, Great Lakes Res Ctr, Houghton, MI USA
关键词
Marine robotics; side scan sonar; deep learning; segmentation; benchmark datasets;
D O I
10.1177/02783649241266853
中图分类号
TP24 [机器人技术];
学科分类号
080202 ; 1405 ;
摘要
Open-source benchmark datasets have been a critical component for advancing machine learning for robot perception in terrestrial applications. Benchmark datasets enable the widespread development of state-of-the-art machine learning methods, which require large datasets for training, validation, and thorough comparison to competing approaches. Underwater environments impose several operational challenges that hinder efforts to collect large benchmark datasets for marine robot perception. Furthermore, a low abundance of targets of interest relative to the size of the search space leads to increased time and cost required to collect useful datasets for a specific task. As a result, there is limited availability of labeled benchmark datasets for underwater applications. We present the AI4Shipwrecks dataset, which consists of 28 distinct shipwrecks totaling 286 high-resolution labeled side scan sonar images to advance the state-of-the-art in autonomous sonar image understanding. We leverage the unique abundance of targets in Thunder Bay National Marine Sanctuary in Lake Huron, MI, to collect and compile a sonar imagery benchmark dataset through surveys with an autonomous underwater vehicle (AUV). We consulted with expert marine archaeologists for the labeling of robotically gathered data. We then leverage this dataset to perform benchmark experiments for comparison of state-of-the-art supervised segmentation methods, and we present insights on opportunities and open challenges for the field. The dataset and benchmarking tools will be released as an open-source benchmark dataset to spur innovation in machine learning for Great Lakes and ocean exploration. The dataset and accompanying software are available at https://umfieldrobotics.github.io/ai4shipwrecks/.
引用
收藏
页码:341 / 354
页数:14
相关论文
共 50 条
  • [31] Machine Learning for Neurodegenerative Disorder - Diagnosis Survey of Practices and Launch of Benchmark Dataset
    Tagaris, Athanasios
    Kollias, Dimitrios
    Stafylopatis, Andreas
    Tagaris, Georgios
    Kollias, Stefanos
    INTERNATIONAL JOURNAL ON ARTIFICIAL INTELLIGENCE TOOLS, 2018, 27 (03)
  • [32] Advanced gray-scale morphological filters for the detection of sea mines in side-scan sonar imagery
    Lange, H
    Vincent, L
    DETECTION AND REMEDIATION TECHNOLOGIES FOR MINES AND MINELIKE TARGETS V, PTS 1 AND 2, 2000, 4038 : 362 - 372
  • [33] SEABED FEATURES FROM A SIDE SCAN SONAR SURVEY AT NORTH OF ANTIMILOS ISLAND
    Mitrousis, Anastasios
    10TH INTERNATIONAL MULTIDISCIPLINARY SCIENTIFIC GEOCONFERENCE: SGEM 2010, VOL I, 2010, : 809 - 814
  • [34] Real-time underwater target detection for AUV using side scan sonar images based on deep learning
    Li, Liang
    Li, Yiping
    Yue, Chenghai
    Xu, Gaopeng
    Wang, Hailin
    Feng, Xisheng
    APPLIED OCEAN RESEARCH, 2023, 138
  • [35] Research on Side-scan Sonar Image Target Classification Method Based on Transfer Learning
    Ye, Xiufen
    Li, Chuanlong
    Zhang, Siyuan
    Yang, Peng
    Li, Xiang
    OCEANS 2018 MTS/IEEE CHARLESTON, 2018,
  • [36] Super Resolution by Deep Learning Improves Boulder Detection in Side Scan Sonar Backscatter Mosaics
    Feldens, Peter
    REMOTE SENSING, 2020, 12 (14)
  • [37] A Variational Level Set Side-scan Sonar Image Segmentation Approach Using a Gamma Observation Model
    Huo, Guanying
    Li, Qingwu
    Sheng, Huixing
    Zhou, Yan
    2012 4TH INTERNATIONAL CONFERENCE ON ENVIRONMENTAL SCIENCE AND INFORMATION APPLICATION TECHNOLOGY (ESIAT 2012), 2013, 14 : 518 - 523
  • [38] Adaptive filter/feature orthogonalization processing string for optimal LLRT mine classification in side-scan sonar imagery
    Aridgides, T
    Libera, P
    Fernandez, M
    Dobeck, G
    DETECTION AND REMEDIATION TECHNOLOGIES FOR MINES AND MINELIKE TARGETS, 1996, 2765 : 110 - 121
  • [39] A Sentinel-2 Multiyear, Multicountry Benchmark Dataset for Crop Classification and Segmentation With Deep Learning
    Sykas, Dimitrios
    Sdraka, Maria
    Zografakis, Dimitrios
    Papoutsis, Ioannis
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2022, 15 : 3323 - 3339
  • [40] Multiresolution 3-D reconstruction from side-scan sonar images
    Coiras, Enrique
    Petillot, Yvan
    Lane, David M.
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2007, 16 (02) : 382 - 390