{"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/fast-robust-continuous-monocular-egomotion","title":"Fast, Robust, Continuous Monocular Egomotion Computation","arxiv_id":"1602.04886","date":"2016-02-16","proceeding":null,"authors":["Andrew Jaegle","Stephen Phillips","Kostas Daniilidis"],"abstract":"We propose robust methods for estimating camera egomotion in noisy,\nreal-world monocular image sequences in the general case of unknown observer\nrotation and translation with two views and a small baseline. This is a\ndifficult problem because of the nonconvex cost function of the perspective\ncamera motion equation and because of non-Gaussian noise arising from noisy\noptical flow estimates and scene non-rigidity. To address this problem, we\nintroduce the expected residual likelihood method (ERL), which estimates\nconfidence weights for noisy optical flow data using likelihood distributions\nof the residuals of the flow field under a range of counterfactual model\nparameters. We show that ERL is effective at identifying outliers and\nrecovering appropriate confidence weights in many settings. We compare ERL to a\nnovel formulation of the perspective camera motion equation using a lifted\nkernel, a recently proposed optimization framework for joint parameter and\nconfidence weight estimation with good empirical properties. We incorporate\nthese strategies into a motion estimation pipeline that avoids falling into\nlocal minima. We find that ERL outperforms the lifted kernel method and\nbaseline monocular egomotion estimation strategies on the challenging KITTI\ndataset, while adding almost no runtime cost over baseline egomotion methods.","url_abs":"http://arxiv.org/abs/1602.04886v1","url_pdf":"http://arxiv.org/pdf/1602.04886v1.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":"fast-robust-continuous-monocular-egomotion","repo_url":"https://github.com/stephenphillips42/erl_egomotion","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"motion-estimation","task_name":"Motion Estimation"},{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":null,"task_name":"counterfactual"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}