{"url":"/dataset/c2a-dataset-human-detection-in-disaster","name":"C2A: Human Detection in Disaster Scenarios","full_name":"Combination to Application","description_markdown":"# C2A: Combination to Application Dataset\r\n\r\n## Overview\r\n\r\nThis repository contains the code and information for the paper \"UAV-Enhanced Combination to Application: Comprehensive Analysis and Benchmarking of a Human Detection Dataset for Disaster Scenarios\" by Ragib Amin Nihal, Benjamin Yen, Katsutoshi Itoyama, and Kazuhiro Nakadai.\r\n\r\nThe C2A (Combination to Application) dataset is a novel synthetic dataset designed to advance human detection in disaster scenarios using UAV imagery. It combines disaster scene backgrounds from the AIDER dataset with human poses from the LSP/MPII-MPHB dataset to create a comprehensive resource for training machine learning models.\r\n\r\nThe full paper is available at: [https://arxiv.org/pdf/2408.04922](https://arxiv.org/pdf/2408.04922)\r\n\r\n## Dataset\r\n\r\nThe C2A dataset consists of 10,215 images containing over 360,000 annotated human instances in various disaster scenarios. It includes diverse human poses (bent, kneeling, lying, sitting, upright) and disaster contexts (traffic incidents, fire, flood, collapsed buildings). \r\n\r\n### Usage Notes\r\n\r\n- The dataset is split into training, validation, and test sets.\r\n- Two annotation formats are provided for flexibility: YOLO and COCO.\r\n- Pose information is available in a separate folder for all images.\r\n- Users can choose between standard object detection (YOLO/COCO) or pose-aware detection (All labels with Pose info).\r\n\r\n## Key Features\r\n\r\n- Synthetic dataset combining real disaster scenes with human poses\r\n- Over 360,000 annotated human instances\r\n- 5 human pose categories\r\n- 4 disaster scenario types\r\n- Image resolutions ranging from 123x152 to 5184x3456 pixels\r\n- Designed to improve human detection in complex disaster environments","description_withheld":null,"homepage":"https://www.kaggle.com/datasets/rgbnihal/c2a-dataset","introduced_date":"2024-08-09","introduced_date_note":null,"introduced_by":{"paper":"/paper/uav-enhanced-combination-to-application","title":"UAV-Enhanced Combination to Application: Comprehensive Analysis and Benchmarking of a Human Detection Dataset for Disaster Scenarios","first_author":"Ragib Amin Nihal","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Environment","url":"/datasets/modality/environment"}],"tasks":[{"name":"2D Object Detection","url":"/task/2d-object-detection","datasets_with_task":"/datasets/task/2d-object-detection"},{"name":"Object Detection","url":"/task/object-detection","datasets_with_task":"/datasets/task/object-detection"},{"name":"2D Human Pose Estimation","url":"/task/2d-human-pose-estimation","datasets_with_task":"/datasets/task/2d-human-pose-estimation"},{"name":"Object Detection In Aerial Images","url":"/task/object-detection-in-aerial-images","datasets_with_task":"/datasets/task/object-detection-in-aerial-images"},{"name":"Disaster Response","url":"/task/disaster-response","datasets_with_task":"/datasets/task/disaster-response"},{"name":"Human Detection","url":"/task/human-detection","datasets_with_task":"/datasets/task/human-detection"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["C2A: Human Detection in Disaster Scenarios"],"data_loaders":[],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/object-detection-on-c2a-human-detection-in","task":"Object Detection","dataset_variant":"C2A: Human Detection in Disaster Scenarios","rows":1,"metrics":["Average mAP"],"first_row_in_archive_order":{"model":"B2BDet","paper":"/paper/from-blurry-to-brilliant-detection-yolov5","metrics":{"Average mAP":"0.784"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/from-blurry-to-brilliant-detection-yolov5","title":"From Blurry to Brilliant Detection: YOLOv5-Based Aerial Object Detection with Super Resolution","date":"2024-01-26","rows_on_this_dataset":1,"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."}