{"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/detection-tracking-and-counting-meets-drones","title":"Detection, Tracking, and Counting Meets Drones in Crowds: A Benchmark","arxiv_id":"2105.02440","date":"2021-05-06","proceeding":"CVPR 2021 1","authors":["Longyin Wen","Dawei Du","Pengfei Zhu","QinGhua Hu","Qilong Wang","Liefeng Bo","Siwei Lyu"],"abstract":"To promote the developments of object detection, tracking and counting algorithms in drone-captured videos, we construct a benchmark with a new drone-captured largescale dataset, named as DroneCrowd, formed by 112 video clips with 33,600 HD frames in various scenarios. Notably, we annotate 20,800 people trajectories with 4.8 million heads and several video-level attributes. Meanwhile, we design the Space-Time Neighbor-Aware Network (STNNet) as a strong baseline to solve object detection, tracking and counting jointly in dense crowds. STNNet is formed by the feature extraction module, followed by the density map estimation heads, and localization and association subnets. To exploit the context information of neighboring objects, we design the neighboring context loss to guide the association subnet training, which enforces consistent relative position of nearby objects in temporal domain. Extensive experiments on our DroneCrowd dataset demonstrate that STNNet performs favorably against the state-of-the-arts.","url_abs":"https://arxiv.org/abs/2105.02440v1","url_pdf":"https://arxiv.org/pdf/2105.02440v1.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":[{"paper_slug":"detection-tracking-and-counting-meets-drones","repo_url":"https://github.com/VisDrone/DroneCrowd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"crowd-counting","task_name":"Crowd Counting"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":null,"task_name":"Position"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[{"slug":"dronecrowd","name":"DroneCrowd","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/crowd-counting-on-up-count","task":"Crowd Counting","dataset":"UP-COUNT","model":"STNNet","rank_in_archive_order":1,"of":3,"metrics":{"L-AP@10":"28.48"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2105.02440","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}