{"url":"/dataset/dronergbt","name":"DroneRGBT","full_name":"DroneRGBT","description_markdown":"人群计数旨在识别物体的数量，在智能交通、城市管理和安全监控中发挥着重要作用。由于比例变化、照明变化、遮挡和较差的成像条件，尤其是在夜间和雾霾条件下，人群计数的任务非常具有挑战性。 在本文中，我们提出了一个基于无人机的 RGB-Thermal 人群计数数据集 （DroneRGBT），该数据集由 3600 对图像组成，涵盖不同的属性，包括高度、照明和密度。为了利用可见光和热红外模态中的互补信息，我们提出了一种具有多尺度特征学习模块、模态对齐模块和自适应融合模块的多模态人群计数网络 （MMCCN）。在 DroneRGBT 上的实验证明了所提出的方法的有效性。","description_withheld":null,"homepage":"https://github.com/VisDrone/DroneRGBT","introduced_date":"2020-11-04","introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Crowd Counting","url":"/task/crowd-counting","datasets_with_task":"/datasets/task/crowd-counting"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["DroneRGBT"],"data_loaders":[{"repo":"https://github.com/VisDrone/DroneRGBT","url":"https://github.com/VisDrone/DroneRGBT","frameworks":["pytorch"]}],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/crowd-counting-on-dronergbt","task":"Crowd Counting","dataset_variant":"DroneRGBT","rows":1,"metrics":["10.83"],"first_row_in_archive_order":{"model":"P2PNet","paper":"/paper/transformer-based-dual-optical-attention","metrics":{"10.83":"1"},"code_links":[{"title":"zz-zik/tapnet","url":"https://github.com/zz-zik/tapnet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/transformer-based-dual-optical-attention","title":"Transformer-Based Dual-Optical Attention Fusion Crowd Head Point Counting and Localization Network","date":"2025-05-11","rows_on_this_dataset":1,"code_links":1,"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."}