[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121915-en":3,"doc-seo-121915-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},121915,549758252649,"Ivy","https://ap-avatar.wpscdn.com/avatar/8000253669c5317157?_k=1778319167496531819",6,"Technology","Machine Learning for Shipwreck Segmentation from Side Scan Sonar Imagery: Dataset and Benchmark","Open-source benchmark datasets drive state-of-the-art machine learning for robot perception, but underwater sonar data collection is costly and slow, and labeled targets are scarce relative to the search space. This limits publicly available supervised resources for underwater tasks. The AI4Shipwrecks dataset provides 286 high-resolution, pixel-wise labeled side scan sonar images across 28 distinct shipwrecks. Collected via AUV surveys in Thunder Bay National Marine Sanctuary and labeled with marine archaeologist expertise, it supports benchmarking of supervised segmentation methods and releases open-source tools to accelerate sonar understanding.","arXiv :2401 . 14546v2 [ cs .RO] 27 Aug 2024  \nMachine Learning for Shipwreck Segmentation from Side Scan Sonar Imagery: Dataset and Benchmark  \nJournal Title XX(X):1–12  \n©The Author(s) 2024  \nReprints and permission: [sagepub.co.uk/journalsPermissions.nav](sagepub.co.uk/journalsPermissions.nav)[ ](sagepub.co.uk/journalsPermissions.nav)DOI: 10.1177/ToBeAssigned [www.sagepub.com/](www.sagepub.com/)  \nSAGE  \nAdvaith V. Sethuraman∗ , 1 , Anja Sheppard∗ , 1 , Onur Bagoren 1 , Christopher Pinnow2 , Jamey Anderson2 , Timothy C. Havens2 , and Katherine A. Skinner 1  \nAbstract  \nOpen-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 stateof-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/](https://umfieldrobotics.github.io/ai4shipwrecks/) .  \nKeywords  \nMarine robotics, side scan sonar, deep learning, segmentation, benchmark datasets  \n1 Introduction  \nIt is estimated that over 3 million undiscovered shipwrecks lie on the ocean floor (Gonzalez et al. 2009) . Locating these submerged archaeological sites enables research into important maritime assets of historical significance. However, searching over large areas and vast depths of the sea requires expensive and time-consuming surveys, which inhibits new discovery of shipwreck sites. Marine robotic platforms, including autonomous underwater vehicles (AUVs), have demonstrated potential to carry out efficient, cost-effective large-area surveys of marine environments returning hundreds of gigabytes worth of data. Still, the interpretation of sonar imagery to identify sites of interest requires manual expert review. This can take many months to complete, often requiring multiple surveys to verify potential new discoveries.  \nAutomated processing of sonar data collected over largearea surveys has the potential to accelerate the discovery of new sites of interest. On land, machine learning has led to great advances in computer vision and robot perception tasks, including object detection, semantic segmentation, and scene understanding. State-of-the-art machine learning methods rely on labeled datasets for supervised training of neural networks to learn pixel-wise segmentation predictions. However, for underwater domains, there is limited availability of public, labeled datasets for sonar data  \nFigure 1. Our AI4Shipwrecks dataset aims to accelerate the","cbCaiphUdw1Itlmh","https://ap.wps.com/l/cbCaiphUdw1Itlmh","pdf",7905574,1,12,"English","en",105,"# Introduction\n## Motivation for labeled underwater sonar benchmarks\n## Challenges in collecting sonar datasets\n# AI4Shipwrecks Dataset\n## Dataset composition and labels\n## Data collection using an AUV survey\n## Expert marine archaeologist labeling\n# Benchmarking Experiments\n## Evaluation of supervised segmentation methods\n## Insights, opportunities, and open challenges\n# Dataset Release and Resources","[{\"question\":\"Why are labeled benchmark datasets scarce for underwater sonar applications?\",\"answer\":\"Underwater surveys are expensive and time-consuming, and the number of relevant targets is low compared with the search area, increasing the time and cost needed to collect useful labeled data.\"},{\"question\":\"What does the AI4Shipwrecks dataset include?\",\"answer\":\"It contains 286 high-resolution side scan sonar images covering 28 distinct shipwrecks, with pixel-wise segmentation labels for the shipwreck sites.\"},{\"question\":\"How was the dataset collected and labeled?\",\"answer\":\"The dataset was compiled from AUV surveys conducted in Thunder Bay National Marine Sanctuary, and expert marine archaeologists were consulted to label the robotically gathered data.\"}]","Machine Learning for Shipwreck Segmentation from Side Scan Sonar Imagery: Dataset and Benchmark | PDF",1785807721,30,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-for-shipwreck-segmentation-from-side-scan-sonar-imagery-dataset-and-benchmark","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/technology/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-for-shipwreck-segmentation-from-side-scan-sonar-imagery-dataset-and-benchmark/121915/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why are labeled benchmark datasets scarce for underwater sonar applications?","Question",{"text":75,"@type":76},"Underwater surveys are expensive and time-consuming, and the number of relevant targets is low compared with the search area, increasing the time and cost needed to collect useful labeled data.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What does the AI4Shipwrecks dataset include?",{"text":80,"@type":76},"It contains 286 high-resolution side scan sonar images covering 28 distinct shipwrecks, with pixel-wise segmentation labels for the shipwreck sites.",{"name":82,"@type":73,"acceptedAnswer":83},"How was the dataset collected and labeled?",{"text":84,"@type":76},"The dataset was compiled from AUV surveys conducted in Thunder Bay National Marine Sanctuary, and expert marine archaeologists were consulted to label the robotically gathered data.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,113,118,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":111,"slug":112},50,"technology",{"id":114,"doc_module":4,"doc_module_name":46,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":119,"doc_module":4,"doc_module_name":46,"category_name":120,"show_sort_weight":29,"slug":121},8,"Research & Report","research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]