- 专利标题: VERIFYING OBJECT CLASSIFICATION USING COMPONENT-BASED DESCRIPTORS AND TEMPORAL SIMILARITY MEASURES
-
申请号: US18578591申请日: 2022-07-08
-
公开(公告)号: US20240203131A1公开(公告)日: 2024-06-20
- 发明人: Amir RAHIMI , Hyukseong Kwon , Amit AGARWAL , Rajan BHATTACHARYYA
- 申请人: HRL Laboratories, LLC
- 申请人地址: US CA Malibu
- 专利权人: HRL Laboratories, LLC
- 当前专利权人: HRL Laboratories, LLC
- 当前专利权人地址: US CA Malibu
- 国际申请: PCT/US2022/073573 2022.07.08
- 进入国家日期: 2024-01-11
- 主分类号: G06V20/58
- IPC分类号: G06V20/58 ; G06V10/764 ; G06V10/776
摘要:
A method and apparatus for verifying object classification includes comparing detected object-components with trained component-based descriptors and similarity measures to generate object classification verification data. The object classification verification data represents object classification confidence or misclassification errors to weight uncertainty for perception-based decision making. A sequence of similarity measures associated with a current frame and prior frames within a reference observation time constraint are compared to a reference temporal similarity measure boundary to generate the object classification verification data.
信息查询