Papers › SeaDronesSee: A Maritime Benchmark for Detecting Humans in Open Water

SeaDronesSee: A Maritime Benchmark for Detecting Humans in Open Water

5 May 2021WACV 2022 1arXiv:2105.01922archive 2025-07-28

Leon Amadeus Varga, Benjamin Kiefer, Martin Messmer, Andreas Zell

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

PaperPDFConference PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Multi-Object TrackingObject DetectionObject Trackingobject-detection

Datasets

Introduced by this paper, per the archive.

SeaDronesSee

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multi-Object Tracking SeaDronesSee Tracktor++ MOTA 0.7190 #1 of 3 Archive leaderboard report
Multi-Object Tracking SeaDronesSee FairMOT D34 MOTA 0.3650 #2 of 3 Archive leaderboard report
Multi-Object Tracking SeaDronesSee FairMOT R34 MOTA 0.3050 #3 of 3 Archive leaderboard report
Object Detection SeaDronesSee Faster R-CNN ResNeXt-101-FPN mAP@0.5 54.66 #3 of 10 Archive leaderboard report
Object Detection SeaDronesSee CenterNet Hourglass104 mAP@0.5 50.32 #4 of 10 Archive leaderboard report
Object Detection SeaDronesSee EfficientDet D0 mAP@0.5 37.11 #6 of 10 Archive leaderboard report
Object Detection SeaDronesSee CenterNet ResNet101 mAP@0.5 36.42 #7 of 10 Archive leaderboard report
Object Detection SeaDronesSee Faster RCNN ResNet50FPN mAP@0.5 30.09 #8 of 10 Archive leaderboard report
Object Detection SeaDronesSee CenterNet ResNet18 mAP@0.5 21.84 #9 of 10 Archive leaderboard report
Object Tracking SeaDronesSee DiMP50 Precision Score 86.84020 #1 of 5 Archive leaderboard report
Object Tracking SeaDronesSee DiMP50 Success Rate 67.33400 #1 of 5 Archive leaderboard report
Object Tracking SeaDronesSee PrDiMP50 Precision Score 84.93010 #2 of 5 Archive leaderboard report
Object Tracking SeaDronesSee PrDiMP50 Success Rate 67.00010 #2 of 5 Archive leaderboard report
Object Tracking SeaDronesSee PrDiMP18 Precision Score 83.51010 #3 of 5 Archive leaderboard report
Object Tracking SeaDronesSee PrDiMP18 Success Rate 65.90210 #3 of 5 Archive leaderboard report
Object Tracking SeaDronesSee DiMP18 Precision Score 82.70010 #4 of 5 Archive leaderboard report
Object Tracking SeaDronesSee DiMP18 Success Rate 64.60100 #4 of 5 Archive leaderboard report
Object Tracking SeaDronesSee Atom Precision Score 82.32100 #5 of 5 Archive leaderboard report
Object Tracking SeaDronesSee Atom Success Rate 63.80000 #5 of 5 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections