{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11514323","patent":{"patent_number":"US-11514323","title":"Methods for performing multi-view object detection by using homography attention module and devices using the same","assignee":null,"inventors":[],"filing_date":"2022-06-10T00:00:00.000Z","publication_date":"2022-11-29T00:00:00.000Z","cpc_codes":["G06N","G06N","G06N","G06N","G06V","G06V","G06V"],"num_claims":22,"abstract":"A method for training a homography attention module (HAM) to perform multi-view object detection includes steps of: generating, from an i-th feature map corresponding to each of multiple training images representing multi-views of a target space, a 1-st to a d-th channel attention map for determining channel attention scores each channel included in the i-th feature map has for each of a 1-st to a d-th height plane of the target space, generating a 1-st to a d-th channel refined feature map by referring to channels with top k channel attention scores for each height, element-wisely multiplying them with corresponding spatial attention map generated therefrom to produce a 1-st to a d-th spatial refined feature map, and then homographically transforming them onto corresponding height plane and aggregating them to generate a BEV occupancy heatmap, which is used with its GT for training."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Methods for performing multi-view object detection by using homography attention module and devices using the same","description":"A method for training a homography attention module (HAM) to perform multi-view object detection includes steps of: generating, from an i-th feature map corresponding to each of multiple training imag","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11514323","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-11514323","citation_suggestion":"Patentable. \"Methods for performing multi-view object detection by using homography attention module and devices using the same\" (US-11514323). https://patentable.app/patents/US-11514323","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11514323","json":"https://patentable.app/api/llm-context/US-11514323","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-31T04:00:40.864Z"}