{"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/accelerated-convolutions-for-efficient-multi","title":"Accelerated Convolutions for Efficient Multi-Scale Time to Contact Computation in Julia","arxiv_id":"1612.08825","date":"2016-12-28","proceeding":null,"authors":["Alexander Amini","Berthold Horn","Alan Edelman"],"abstract":"Convolutions have long been regarded as fundamental to applied mathematics,\nphysics and engineering. Their mathematical elegance allows for common tasks\nsuch as numerical differentiation to be computed efficiently on large data\nsets. Efficient computation of convolutions is critical to artificial\nintelligence in real-time applications, like machine vision, where convolutions\nmust be continuously and efficiently computed on tens to hundreds of kilobytes\nper second. In this paper, we explore how convolutions are used in fundamental\nmachine vision applications. We present an accelerated n-dimensional\nconvolution package in the high performance computing language, Julia, and\ndemonstrate its efficacy in solving the time to contact problem for machine\nvision. Results are measured against synthetically generated videos and\nquantitatively assessed according to their mean squared error from the ground\ntruth. We achieve over an order of magnitude decrease in compute time and\nallocated memory for comparable machine vision applications. All code is\npackaged and integrated into the official Julia Package Manager to be used in\nvarious other scenarios.","url_abs":"http://arxiv.org/abs/1612.08825v1","url_pdf":"http://arxiv.org/pdf/1612.08825v1.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":"accelerated-convolutions-for-efficient-multi","repo_url":"https://github.com/aamini/FastConv.jl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","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}