{"url":"/dataset/uavdt","name":"UAVDT","full_name":"Unmanned Aerial Vehicle Benchmark Object Detection and Tracking","description_markdown":"UAVDT is a large scale challenging UAV Detection and Tracking benchmark (i.e., about 80, 000 representative frames from 10 hours raw videos) for 3 important fundamental tasks, i.e., object DETection\r\n(DET), Single Object Tracking (SOT) and Multiple Object Tracking (MOT).\r\n\r\nThe dataset is captured by UAVs in various complex scenarios. The objects of\r\ninterest in this benchmark are vehicles. The frames are manually annotated with bounding boxes and some useful attributes, e.g., vehicle category and occlusion. \r\n\r\nThe UAVDT benchmark consists of 100 video sequences, which are selected\r\nfrom over 10 hours of videos taken with an UAV platform at a number of locations in urban areas, representing various common scenes including squares, arterial streets, toll stations, highways, crossings and T-junctions. The videos\r\nare recorded at 30 frames per seconds (fps), with the JPEG image resolution of 1080 × 540 pixels.","description_withheld":null,"homepage":"https://sites.google.com/view/grli-uavdt/%E9%A6%96%E9%A1%B5","introduced_date":"2018-03-26","introduced_date_note":null,"introduced_by":{"paper":"/paper/the-unmanned-aerial-vehicle-benchmark-object","title":"The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking","first_author":"Dawei Du","url":null},"license":{"name":"Custom (research-only)","url":"https://sites.google.com/view/grli-uavdt/%E9%A6%96%E9%A1%B5"},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Object Detection","url":"/task/object-detection","datasets_with_task":"/datasets/task/object-detection"},{"name":"Object Tracking","url":"/task/object-tracking","datasets_with_task":"/datasets/task/object-tracking"},{"name":"Multi-Object Tracking","url":"/task/multi-object-tracking","datasets_with_task":"/datasets/task/multi-object-tracking"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["UAVDT"],"data_loaders":[{"repo":"https://github.com/Graviti-AI/datasets","url":"https://gas.graviti.com/dataset/graviti/UAVDT","frameworks":["tf","pytorch"]}],"num_papers_in_archive":96,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/object-detection-on-uavdt","task":"Object Detection","dataset_variant":"UAVDT","rows":8,"metrics":["mAP"],"first_row_in_archive_order":{"model":"PRB-FPN","paper":"/paper/parallel-residual-bi-fusion-feature-pyramid","metrics":{"mAP":"76.55"},"code_links":[{"title":"pingyang1117/PRBNet_PyTorch","url":"https://github.com/pingyang1117/PRBNet_PyTorch"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multi-object-tracking-on-uavdt","task":"Multi-Object Tracking","dataset_variant":"UAVDT","rows":2,"metrics":["IDF1","MOTA"],"first_row_in_archive_order":{"model":"SAM2MOT","paper":"/paper/sam2mot-a-novel-paradigm-of-multi-object","metrics":{"IDF1":"74.4","MOTA":"55.63"},"code_links":[{"title":"TripleJoy/SAM2MOT","url":"https://github.com/TripleJoy/SAM2MOT"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/sam2mot-a-novel-paradigm-of-multi-object","title":"SAM2MOT: A Novel Paradigm of Multi-Object Tracking by Segmentation","date":"2025-04-06","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/dronemot-drone-based-multi-object-tracking","title":"DroneMOT: Drone-based Multi-Object Tracking Considering Detection Difficulties and Simultaneous Moving of Drones and Objects","date":"2024-07-12","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/ffavod-feature-fusion-architecture-for-video","title":"FFAVOD: Feature Fusion Architecture for Video Object Detection","date":"2021-09-15","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/parallel-residual-bi-fusion-feature-pyramid","title":"Parallel Residual Bi-Fusion Feature Pyramid Network for Accurate Single-Shot Object Detection","date":"2020-12-03","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/rn-vid-a-feature-fusion-architecture-for","title":"RN-VID: A Feature Fusion Architecture for Video Object Detection","date":"2020-03-24","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/spotnet-self-attention-multi-task-network-for","title":"SpotNet: Self-Attention Multi-Task Network for Object Detection","date":"2020-02-13","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/the-unmanned-aerial-vehicle-benchmark-object","title":"The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking","date":"2018-03-26","rows_on_this_dataset":4,"code_links":0,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}