{"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/a-survey-of-recent-advances-in-cnn-based","title":"A Survey of Recent Advances in CNN-based Single Image Crowd Counting and Density Estimation","arxiv_id":"1707.01202","date":"2017-07-05","proceeding":null,"authors":["Vishwanath A. Sindagi","Vishal M. Patel"],"abstract":"Estimating count and density maps from crowd images has a wide range of\napplications such as video surveillance, traffic monitoring, public safety and\nurban planning. In addition, techniques developed for crowd counting can be\napplied to related tasks in other fields of study such as cell microscopy,\nvehicle counting and environmental survey. The task of crowd counting and\ndensity map estimation is riddled with many challenges such as occlusions,\nnon-uniform density, intra-scene and inter-scene variations in scale and\nperspective. Nevertheless, over the last few years, crowd count analysis has\nevolved from earlier methods that are often limited to small variations in\ncrowd density and scales to the current state-of-the-art methods that have\ndeveloped the ability to perform successfully on a wide range of scenarios. The\nsuccess of crowd counting methods in the recent years can be largely attributed\nto deep learning and publications of challenging datasets. In this paper, we\nprovide a comprehensive survey of recent Convolutional Neural Network (CNN)\nbased approaches that have demonstrated significant improvements over earlier\nmethods that rely largely on hand-crafted representations. First, we briefly\nreview the pioneering methods that use hand-crafted representations and then we\ndelve in detail into the deep learning-based approaches and recently published\ndatasets. Furthermore, we discuss the merits and drawbacks of existing\nCNN-based approaches and identify promising avenues of research in this rapidly\nevolving field.","url_abs":"http://arxiv.org/abs/1707.01202v1","url_pdf":"http://arxiv.org/pdf/1707.01202v1.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":"a-survey-of-recent-advances-in-cnn-based","repo_url":"https://github.com/gpspelle/Crowd-Counting","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"crowd-counting","task_name":"Crowd Counting"},{"task_slug":"density-estimation","task_name":"Density Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1707.01202","atlas_url":"https://app.syntology.ai/?focus=1707.01202","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}