{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/seadronessee-a-maritime-benchmark-for","title":"SeaDronesSee: A Maritime Benchmark for Detecting Humans in Open Water","arxiv_id":"2105.01922","date":"2021-05-05","proceeding":"WACV 2022 1","authors":["Leon Amadeus Varga","Benjamin Kiefer","Martin Messmer","Andreas Zell"],"abstract":"Unmanned Aerial Vehicles (UAVs) are of crucial importance in search and rescue missions in maritime environments due to their flexible and fast operation capabilities. Modern computer vision algorithms are of great interest in aiding such missions. However, they are dependent on large amounts of real-case training data from UAVs, which is only available for traffic scenarios on land. Moreover, current object detection and tracking data sets only provide limited environmental information or none at all, neglecting a valuable source of information. Therefore, this paper introduces a large-scaled visual object detection and tracking benchmark (SeaDronesSee) aiming to bridge the gap from land-based vision systems to sea-based ones. We collect and annotate over 54,000 frames with 400,000 instances captured from various altitudes and viewing angles ranging from 5 to 260 meters and 0 to 90 degrees while providing the respective meta information for altitude, viewing angle and other meta data. We evaluate multiple state-of-the-art computer vision algorithms on this newly established benchmark serving as baselines. We provide an evaluation server where researchers can upload their prediction and compare their results on a central leaderboard","url_abs":"https://arxiv.org/abs/2105.01922v2","url_pdf":"https://arxiv.org/pdf/2105.01922v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"multi-object-tracking","task_name":"Multi-Object Tracking"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[{"slug":"seadronessee","name":"SeaDronesSee","full_name":"SeaDronesSee: A Maritime Benchmark for Detecting Humans in Open Water"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/multi-object-tracking-on-seadronessee","task":"Multi-Object Tracking","dataset":"SeaDronesSee","model":"Tracktor++","rank_in_archive_order":1,"of":3,"metrics":{"MOTA":"0.7190"},"uses_additional_data":false},{"leaderboard":"/sota/multi-object-tracking-on-seadronessee","task":"Multi-Object Tracking","dataset":"SeaDronesSee","model":"FairMOT D34","rank_in_archive_order":2,"of":3,"metrics":{"MOTA":"0.3650"},"uses_additional_data":false},{"leaderboard":"/sota/multi-object-tracking-on-seadronessee","task":"Multi-Object Tracking","dataset":"SeaDronesSee","model":"FairMOT R34","rank_in_archive_order":3,"of":3,"metrics":{"MOTA":"0.3050"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-seadronessee","task":"Object Detection","dataset":"SeaDronesSee","model":"Faster R-CNN ResNeXt-101-FPN","rank_in_archive_order":3,"of":10,"metrics":{"mAP@0.5":"54.66"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-seadronessee","task":"Object Detection","dataset":"SeaDronesSee","model":"CenterNet Hourglass104","rank_in_archive_order":4,"of":10,"metrics":{"mAP@0.5":"50.32"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-seadronessee","task":"Object Detection","dataset":"SeaDronesSee","model":"EfficientDet D0","rank_in_archive_order":6,"of":10,"metrics":{"mAP@0.5":"37.11"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-seadronessee","task":"Object Detection","dataset":"SeaDronesSee","model":"CenterNet ResNet101","rank_in_archive_order":7,"of":10,"metrics":{"mAP@0.5":"36.42"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-seadronessee","task":"Object Detection","dataset":"SeaDronesSee","model":"Faster RCNN ResNet50FPN","rank_in_archive_order":8,"of":10,"metrics":{"mAP@0.5":"30.09"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-seadronessee","task":"Object Detection","dataset":"SeaDronesSee","model":"CenterNet ResNet18","rank_in_archive_order":9,"of":10,"metrics":{"mAP@0.5":"21.84"},"uses_additional_data":false},{"leaderboard":"/sota/object-tracking-on-seadronessee","task":"Object Tracking","dataset":"SeaDronesSee","model":"DiMP50","rank_in_archive_order":1,"of":5,"metrics":{"Precision Score":"86.84020","Success Rate":"67.33400"},"uses_additional_data":false},{"leaderboard":"/sota/object-tracking-on-seadronessee","task":"Object Tracking","dataset":"SeaDronesSee","model":"PrDiMP50","rank_in_archive_order":2,"of":5,"metrics":{"Precision Score":"84.93010","Success Rate":"67.00010"},"uses_additional_data":false},{"leaderboard":"/sota/object-tracking-on-seadronessee","task":"Object Tracking","dataset":"SeaDronesSee","model":"PrDiMP18","rank_in_archive_order":3,"of":5,"metrics":{"Precision Score":"83.51010","Success Rate":"65.90210"},"uses_additional_data":false},{"leaderboard":"/sota/object-tracking-on-seadronessee","task":"Object Tracking","dataset":"SeaDronesSee","model":"DiMP18","rank_in_archive_order":4,"of":5,"metrics":{"Precision Score":"82.70010","Success Rate":"64.60100"},"uses_additional_data":false},{"leaderboard":"/sota/object-tracking-on-seadronessee","task":"Object Tracking","dataset":"SeaDronesSee","model":"Atom","rank_in_archive_order":5,"of":5,"metrics":{"Precision Score":"82.32100","Success Rate":"63.80000"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2105.01922","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}