公开(公告)号：US11068705B2

公开(公告)日：2021-07-20

申请号：US16193238

申请日：2018-11-16

Applicant: Cisco Technology, Inc.

Inventor： Ashutosh Arwind Malegaonkar ,  Haihua Xiao ,  Rizhi Chen ,  Li Kang ,  Siqi Ling ,  Mingen Zheng

IPC: G06K9/00 ,  G06K9/62 ,  G06Q30/02 ,  G06F16/583

Abstract: Disclosed are systems, methods, and computer-readable media for a hybrid cloud structure for machine-learning based object recognition. In one aspect, a system includes one or more video-capable access points; and one or more processors configured to receive image data from the one or more video-capable access points; perform, at a first processor of the one or more processors, a first process to detect one or more objects of interest in the image data; generate vector IDs for one or more objects detected in the image data; perform, at a second processor of the one or more processors, a second process to identify the one or more objects in the vector IDs; and generate at least one offline trail for the one or more objects based on statistics associated with the one or more objects identified.