{"url":"/dataset/carpk","name":"CARPK","full_name":"car parking lot dataset","description_markdown":"The Car Parking Lot Dataset (**CARPK**) contains nearly 90,000 cars from 4 different parking lots collected by means of drone (PHANTOM 3 PROFESSIONAL). The images are collected with the drone-view at approximate 40 meters height. The image set is annotated by bounding box per car. All labeled bounding boxes have been well recorded with the top-left points and the bottom-right points. It is supporting object counting, object localizing, and further investigations with the annotation format in bounding boxes.\r\n\r\nSource: [https://lafi.github.io/LPN/](https://lafi.github.io/LPN/)\r\nImage Source: [https://www.researchgate.net/figure/Sample-results-on-the-CARPK-dataset-Top-row-original-images-Bottom-row-predicted_fig4_328685610](https://www.researchgate.net/figure/Sample-results-on-the-CARPK-dataset-Top-row-original-images-Bottom-row-predicted_fig4_328685610)","description_withheld":null,"homepage":"https://lafi.github.io/LPN/","introduced_date":"2017-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/drone-based-object-counting-by-spatially","title":"Drone-based Object Counting by Spatially Regularized Regional Proposal Network","first_author":"Meng-Ru Hsieh","url":null},"license":{"name":"Custom (research-only)","url":"https://lafi.github.io/LPN/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Object Counting","url":"/task/object-counting","datasets_with_task":"/datasets/task/object-counting"}],"languages":[],"variants":["CARPK"],"data_loaders":[{"repo":"https://github.com/activeloopai/Hub","url":"https://docs.activeloop.ai/datasets/carpk-dataset","frameworks":["tf","pytorch"]}],"num_papers_in_archive":71,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/object-counting-on-carpk","task":"Object Counting","dataset_variant":"CARPK","rows":15,"metrics":["MAE","RMSE"],"first_row_in_archive_order":{"model":"HLCNN","paper":"/paper/an-accurate-car-counting-in-aerial-images","metrics":{"MAE":"2.12","RMSE":"3.02"},"code_links":[{"title":"ekilic/Heatmap-Learner-CNN-for-Object-Counting","url":"https://github.com/ekilic/Heatmap-Learner-CNN-for-Object-Counting"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/car-object-counting-and-position-estimation","title":"Car Object Counting and Position Estimation via Extension of the CLIP-EBC Framework","date":"2025-07-11","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/vlcounter-text-aware-visual-representation","title":"VLCounter: Text-aware Visual Representation for Zero-Shot Object Counting","date":"2023-12-27","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/open-world-text-specified-object-counting","title":"Open-world Text-specified Object Counting","date":"2023-06-02","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/countr-transformer-based-generalised-visual","title":"CounTR: Transformer-based Generalised Visual Counting","date":"2022-08-29","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":1,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/represent-compare-and-learn-a-similarity","title":"Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Counting","date":"2022-03-16","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/iterative-correlation-based-feature","title":"Few-shot Object Counting with Similarity-Aware Feature Enhancement","date":"2022-01-22","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/an-accurate-car-counting-in-aerial-images","title":"An Accurate Car Counting in Aerial Images Based on Convolutional Neural Networks","date":"2021-07-13","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/precise-detection-in-densely-packed-scenes","title":"Precise Detection in Densely Packed Scenes","date":"2019-04-01","rows_on_this_dataset":1,"code_links":5,"syntology":null},{"paper":"/paper/focal-loss-for-dense-object-detection","title":"Focal Loss for Dense Object Detection","date":"2017-08-07","rows_on_this_dataset":1,"code_links":234,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":11,"samples_unverified":0,"pointer_only_for_licence":6,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/drone-based-object-counting-by-spatially","title":"Drone-based Object Counting by Spatially Regularized Regional Proposal Network","date":"2017-07-19","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/yolo9000-better-faster-stronger","title":"YOLO9000: Better, Faster, Stronger","date":"2016-12-25","rows_on_this_dataset":1,"code_links":231,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":60,"samples_ran":16,"samples_unverified":44,"pointer_only_for_licence":22,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/a-large-contextual-dataset-for-classification","title":"A Large Contextual Dataset for Classification, Detection and Counting of Cars with Deep Learning","date":"2016-09-14","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/you-only-look-once-unified-real-time-object","title":"You Only Look Once: Unified, Real-Time Object Detection","date":"2015-06-08","rows_on_this_dataset":1,"code_links":144,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":148,"samples_ran":80,"samples_unverified":68,"pointer_only_for_licence":98,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/faster-r-cnn-towards-real-time-object","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","date":"2015-06-04","rows_on_this_dataset":1,"code_links":196,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":124,"samples_ran":59,"samples_unverified":65,"pointer_only_for_licence":42,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":6,"samples_harvested":348,"samples_ran":167,"samples_unverified":181,"pointer_only_for_licence":168,"papers_with_no_sample_that_ran":1,"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."}