发明名称 |
Method for Extracting Low-Rank Descriptors from Images and Videos for Querying, Classification, and Object Detection |
摘要 |
A method extracts a low-rank descriptor of a video acquired of a scene by first extracting a set of descriptors for each image in the video. The sets of descriptors for the video are aggregated to form a descriptor matrix. Iteratively, a low-rank descriptor matrix is determined from the descriptor matrix, as well as a selection matrix that associates each column in the descriptor matrix to a corresponding column in the low-rank descriptor matrix. The low-rank descriptor matrix is output upon convergence. |
申请公布号 |
US2015254513(A1) |
申请公布日期 |
2015.09.10 |
申请号 |
US201414202327 |
申请日期 |
2014.03.10 |
申请人 |
Mitsubishi Electric Research Laboratories, Inc. |
发明人 |
Mansour Hassan;Rane Shantanu;Boufounos Petros T.;Vetro Anthony |
分类号 |
G06K9/00;G06K9/64;G06K9/46;G06F17/30 |
主分类号 |
G06K9/00 |
代理机构 |
|
代理人 |
|
主权项 |
1. A method for extracting a low-rank descriptor of a video acquired of a scene, wherein the video includes a sequence of images, further comprising:
extracting a set of descriptors for each image in the video; aggregating the sets of descriptors for the video to form a descriptor matrix; determining, iteratively until convergence, a low-rank descriptor matrix. from the descriptor matrix and a selection matrix that associates each column in the descriptor matrix to a corresponding column in the low-rank descriptor matrix; and outputting the low-rank descriptor matrix upon convergence, wherein the steps are performed in a processor. |
地址 |
Cambridge MA US |