{"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/foreground-segmentation-using-a-triplet","title":"Foreground Segmentation Using a Triplet Convolutional Neural Network for Multiscale Feature Encoding","arxiv_id":"1801.02225","date":"2018-01-07","proceeding":null,"authors":["Long Ang Lim","Hacer Yalim Keles"],"abstract":"A common approach for moving objects segmentation in a scene is to perform a\nbackground subtraction. Several methods have been proposed in this domain.\nHowever, they lack the ability of handling various difficult scenarios such as\nillumination changes, background or camera motion, camouflage effect, shadow\netc. To address these issues, we propose a robust and flexible encoder-decoder\ntype neural network based approach. We adapt a pre-trained convolutional\nnetwork, i.e. VGG-16 Net, under a triplet framework in the encoder part to\nembed an image in multiple scales into the feature space and use a transposed\nconvolutional network in the decoder part to learn a mapping from feature space\nto image space. We train this network end-to-end by using only a few training\nsamples. Our network takes an RGB image in three different scales and produces\na foreground segmentation probability mask for the corresponding image. In\norder to evaluate our model, we entered the Change Detection 2014 Challenge\n(changedetection.net) and our method outperformed all the existing\nstate-of-the-art methods by an average F-Measure of 0.9770. Our source code\nwill be made publicly available at https://github.com/lim-anggun/FgSegNet.","url_abs":"http://arxiv.org/abs/1801.02225v1","url_pdf":"http://arxiv.org/pdf/1801.02225v1.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":"foreground-segmentation-using-a-triplet","repo_url":"https://github.com/lim-anggun/FgSegNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"change-detection","task_name":"Change Detection"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"foreground-segmentation","task_name":"Foreground Segmentation"},{"task_slug":null,"task_name":"Triplet"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}