{"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/image-crowd-counting-using-convolutional","title":"Image Crowd Counting Using Convolutional Neural Network and Markov Random Field","arxiv_id":"1706.03686","date":"2017-06-12","proceeding":null,"authors":["Kang Han","Wanggen Wan","Haiyan Yao","Li Hou"],"abstract":"In this paper, we propose a method called Convolutional Neural Network-Markov\nRandom Field (CNN-MRF) to estimate the crowd count in a still image. We first\ndivide the dense crowd visible image into overlapping patches and then use a\ndeep convolutional neural network to extract features from each patch image,\nfollowed by a fully connected neural network to regress the local patch crowd\ncount. Since the local patches have overlapping portions, the crowd count of\nthe adjacent patches has a high correlation. We use this correlation and the\nMarkov random field to smooth the counting results of the local patches.\nExperiments show that our approach significantly outperforms the\nstate-of-the-art methods on UCF and Shanghaitech crowd counting datasets.","url_abs":"http://arxiv.org/abs/1706.03686v3","url_pdf":"http://arxiv.org/pdf/1706.03686v3.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":"image-crowd-counting-using-convolutional","repo_url":"https://github.com/hankong/crowd-counting","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"crowd-counting","task_name":"Crowd Counting"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}