{"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/deeppbm-deep-probabilistic-background-model","title":"DeepPBM: Deep Probabilistic Background Model Estimation from Video Sequences","arxiv_id":"1902.00820","date":"2019-02-03","proceeding":null,"authors":["Amirreza Farnoosh","Behnaz Rezaei","Sarah Ostadabbas"],"abstract":"This paper presents a novel unsupervised probabilistic model estimation of\nvisual background in video sequences using a variational autoencoder framework.\nDue to the redundant nature of the backgrounds in surveillance videos, visual\ninformation of the background can be compressed into a low-dimensional subspace\nin the encoder part of the variational autoencoder, while the highly variant\ninformation of its moving foreground gets filtered throughout its\nencoding-decoding process. Our deep probabilistic background model (DeepPBM)\nestimation approach is enabled by the power of deep neural networks in learning\ncompressed representations of video frames and reconstructing them back to the\noriginal domain. We evaluated the performance of our DeepPBM in background\nsubtraction on 9 surveillance videos from the background model challenge\n(BMC2012) dataset, and compared that with a standard subspace learning\ntechnique, robust principle component analysis (RPCA), which similarly\nestimates a deterministic low dimensional representation of the background in\nvideos and is widely used for this application. Our method outperforms RPCA on\nBMC2012 dataset with 23% in average in F-measure score, emphasizing that\nbackground subtraction using the trained model can be done in more than 10\ntimes faster.","url_abs":"http://arxiv.org/abs/1902.00820v1","url_pdf":"http://arxiv.org/pdf/1902.00820v1.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":"deeppbm-deep-probabilistic-background-model","repo_url":"https://github.com/ostadabbas/DeepPBM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}