{"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/drone-based-object-counting-by-spatially","title":"Drone-based Object Counting by Spatially Regularized Regional Proposal Network","arxiv_id":"1707.05972","date":"2017-07-19","proceeding":"ICCV 2017 10","authors":["Meng-Ru Hsieh","Yen-Liang Lin","Winston H. Hsu"],"abstract":"Existing counting methods often adopt regression-based approaches and cannot\nprecisely localize the target objects, which hinders the further analysis\n(e.g., high-level understanding and fine-grained classification). In addition,\nmost of prior work mainly focus on counting objects in static environments with\nfixed cameras. Motivated by the advent of unmanned flying vehicles (i.e.,\ndrones), we are interested in detecting and counting objects in such dynamic\nenvironments. We propose Layout Proposal Networks (LPNs) and spatial kernels to\nsimultaneously count and localize target objects (e.g., cars) in videos\nrecorded by the drone. Different from the conventional region proposal methods,\nwe leverage the spatial layout information (e.g., cars often park regularly)\nand introduce these spatially regularized constraints into our network to\nimprove the localization accuracy. To evaluate our counting method, we present\na new large-scale car parking lot dataset (CARPK) that contains nearly 90,000\ncars captured from different parking lots. To the best of our knowledge, it is\nthe first and the largest drone view dataset that supports object counting, and\nprovides the bounding box annotations.","url_abs":"http://arxiv.org/abs/1707.05972v3","url_pdf":"http://arxiv.org/pdf/1707.05972v3.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":[],"tasks":[{"task_slug":"object-counting","task_name":"Object Counting"},{"task_slug":"region-proposal","task_name":"Region Proposal"}],"methods":[],"datasets_introduced":[{"slug":"carpk","name":"CARPK","full_name":"car parking lot dataset"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/object-counting-on-carpk","task":"Object Counting","dataset":"CARPK","model":"RetinaNet (2018)","rank_in_archive_order":9,"of":15,"metrics":{"MAE":"16.62","RMSE":"22.30"},"uses_additional_data":false},{"leaderboard":"/sota/object-counting-on-carpk","task":"Object Counting","dataset":"CARPK","model":"LPN Counting (2017)","rank_in_archive_order":11,"of":15,"metrics":{"MAE":"22.76","RMSE":"34.46"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.05972","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}