{"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/towards-perspective-free-object-counting-with","title":"Towards perspective-free object counting with deep learning","arxiv_id":null,"date":"2016-01-01","proceeding":"journal 2016 1","authors":["Daniel O˜noro-Rubio","Roberto J. L´opez-Sastre"],"abstract":"In this paper we address the problem of counting objects\r\ninstances in images. Our models are able to precisely estimate the number of vehicles in a traffic congestion, or to count the humans in a very\r\ncrowded scene. Our first contribution is the proposal of a novel convolutional neural network solution, named Counting CNN (CCNN). Essentially, the CCNN is formulated as a regression model where the network\r\nlearns how to map the appearance of the image patches to their corresponding object density maps. Our second contribution consists in\r\na scale-aware counting model, the Hydra CNN, able to estimate object\r\ndensities in different very crowded scenarios where no geometric information of the scene can be provided. Hydra CNN learns a multiscale\r\nnon-linear regression model which uses a pyramid of image patches extracted at multiple scales to perform the final density prediction. We\r\nreport an extensive experimental evaluation, using up to three different\r\nobject counting benchmarks, where we show how our solutions achieve\r\na state-of-the-art performance.","url_abs":"http://agamenon.tsc.uah.es/Investigacion/gram/publications/eccv2016-onoro.pdf","url_pdf":"http://agamenon.tsc.uah.es/Investigacion/gram/publications/eccv2016-onoro.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":"towards-perspective-free-object-counting-with","repo_url":"https://github.com/gramuah/ccnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"towards-perspective-free-object-counting-with","repo_url":"https://github.com/wangqiqi/ncnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-counting","task_name":"Object Counting"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}