{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-9697614","patent":{"patent_number":"US-9697614","title":"Method for segmenting and tracking content in videos using low-dimensional subspaces and sparse vectors","assignee":null,"inventors":[],"filing_date":"2014-12-08T00:00:00.000Z","publication_date":"2017-07-04T00:00:00.000Z","cpc_codes":["G06T","G06F","G06V","G06V","G06V","G06V","G06V"],"num_claims":19,"abstract":"A method segments and tracks content in a video stream including sets of one or more images by first determining measured data from each set of one or more images. An adaptive step-size parameter and a low-dimensional subspace characterizing motion of the content the measured data are initialized. A sparse vector representing a sparse component that characterizes the motion of the content different from the motion of the content characterized by the low-dimensional subspace is determined. A change in the low-dimensional subspace for the measured data is determined using a proximal point iteration and the parameter, which is updated according to the change. A low-rank subspace matrix representing the low-dimensional subspace is updated according to the change and the parameter. Then, the low-rank matrix representing the low-dimensional subspace and the sparse vector are outputted."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Method for segmenting and tracking content in videos using low-dimensional subspaces and sparse vectors","description":"A method segments and tracks content in a video stream including sets of one or more images by first determining measured data from each set of one or more images. An adaptive step-size parameter and ","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-9697614","license":"CC-BY-4.0-like","license_terms":"AI-generated analysis on this page (summary, layman_explanation, technical_analysis, business_analysis, faqs) may be reused with attribution and a visible link back to the canonical URL above. Patent abstracts, claims, and bibliographic data are USPTO public domain.","required_link":"https://patentable.app/patents/US-9697614","citation_suggestion":"Patentable. \"Method for segmenting and tracking content in videos using low-dimensional subspaces and sparse vectors\" (US-9697614). https://patentable.app/patents/US-9697614","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-9697614","json":"https://patentable.app/api/llm-context/US-9697614","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-06-06T10:53:09.425Z"}