-
公开(公告)号：US20210295541A1
公开(公告)日：2021-09-23
申请号：US17339390
申请日：2021-06-04
Applicant: Cisco Technology, Inc.
Inventor： Hugo Mike Latapie , Franck Bachet , Enzo Fenoglio , Sawsen Rezig , Carlos M. Pignataro , Guillaume Sauvage De Saint Marc
Abstract: Systems, methods, and computer-readable for multi-spatial scale object detection include generating one or more object trackers for tracking at least one object detected from on one or more images. One or more blobs are generated for the at least one object based on tracking motion associated with the at least one object. One or more tracklets are generated for the at least one object based on associating the one or more object trackers and the one or more blobs, the one or more tracklets including one or more scales of object tracking data for the at least one object. One or more uncertainty metrics are generated using the one or more object trackers and an embedding of the one or more tracklets. A training module for detecting and tracking the at least one object using the embedding and the one or more uncertainty metrics is generated using deep learning techniques.
-
Patent Agency Ranking
公开(公告)号：US11301690B2
公开(公告)日：2022-04-12
申请号：US16743598
申请日：2020-01-15
Applicant: Cisco Technology, Inc.
Inventor： Hugo Mike Latapie , Franck Bachet , Enzo Fenoglio , Sawsen Rezig , Carlos M. Pignataro , Guillaume Sauvage De Saint Marc
Abstract: Systems, methods, and computer-readable for multi-temporal scale analysis include obtaining two or more timescales associated with one or more images. A context associated with a monitoring objective is obtained, based on real time analytics or domain specific knowledge. The monitoring objective can include object detection, event detection, pattern recognition, or other. At least a subset of timescales for performing a differential analysis on the one or more images is determined based on the context. Multi timescale surprise detection and clustering are performed using the subset of timescales to determine whether any alerts are to be generated based on entropy based surprises. A set of rules can be created for the monitoring objective based on the differential analytics and alerts or entropy based surprises, if any.
-
公开(公告)号：US20180124812A1
公开(公告)日：2018-05-03
申请号：US15341099
申请日：2016-11-02
Applicant: Cisco Technology, Inc.
Inventor： Pascal Thubert , Simon Dyke , Franck Bachet , Guillaume Sauvage De Saint Marc
CPC classification number: H04W72/1263 , H04B1/69 , H04B1/713 , H04B2001/6908 , H04W40/00 , H04W72/0446
Abstract: In one embodiment, a device in a network receives a time-slotted channel hopping (TSCH) communication schedule. The TSCH communication schedule is divided into a plurality of macrocells, each macrocell comprising a plurality of TSCH cells. The device receives a packet from a routing protocol child node of the device during a particular macrocell of the TSCH communication schedule that is associated with propagation of the packet through the network. In response to receiving the packet, the device claims a token associated with the particular macrocell that authorizes the device to transmit during one or more cells of the macrocell. The device transmits the received packet to a second node in the network during the authorized one or more cells of the particular macrocell.
-
公开(公告)号：US11030755B2
公开(公告)日：2021-06-08
申请号：US16743522
申请日：2020-01-15
Applicant: Cisco Technology, Inc.
Inventor： Hugo Mike Latapie , Franck Bachet , Enzo Fenoglio , Sawsen Rezig , Carlos M. Pignataro , Guillaume Sauvage De Saint Marc
Abstract: Systems, methods, and computer-readable for multi-spatial scale object detection include generating one or more object trackers for tracking at least one object detected from on one or more images. One or more blobs are generated for the at least one object based on tracking motion associated with the at least one object. One or more tracklets are generated for the at least one object based on associating the one or more object trackers and the one or more blobs, the one or more tracklets including one or more scales of object tracking data for the at least one object. One or more uncertainty metrics are generated using the one or more object trackers and an embedding of the one or more tracklets. A training module for detecting and tracking the at least one object using the embedding and the one or more uncertainty metrics is generated using deep learning techniques.
-
公开(公告)号：US10231253B2
公开(公告)日：2019-03-12
申请号：US15341099
申请日：2016-11-02
Applicant: Cisco Technology, Inc.
Inventor： Pascal Thubert , Simon Dyke , Franck Bachet , Guillaume Sauvage De Saint Marc
Abstract: In one embodiment, a device in a network receives a time-slotted channel hopping (TSCH) communication schedule. The TSCH communication schedule is divided into a plurality of macrocells, each macrocell comprising a plurality of TSCH cells. The device receives a packet from a routing protocol child node of the device during a particular macrocell of the TSCH communication schedule that is associated with propagation of the packet through the network. In response to receiving the packet, the device claims a token associated with the particular macrocell that authorizes the device to transmit during one or more cells of the macrocell. The device transmits the received packet to a second node in the network during the authorized one or more cells of the particular macrocell.
-
公开(公告)号：US11580747B2
公开(公告)日：2023-02-14
申请号：US17339390
申请日：2021-06-04
Applicant: Cisco Technology, Inc.
Inventor： Hugo Mike Latapie , Franck Bachet , Enzo Fenoglio , Sawsen Rezig , Carlos M. Pignataro , Guillaume Sauvage De Saint Marc
Abstract: Systems, methods, and computer-readable for multi-spatial scale object detection include generating one or more object trackers for tracking at least one object detected from on one or more images. One or more blobs are generated for the at least one object based on tracking motion associated with the at least one object. One or more tracklets are generated for the at least one object based on associating the one or more object trackers and the one or more blobs, the one or more tracklets including one or more scales of object tracking data for the at least one object. One or more uncertainty metrics are generated using the one or more object trackers and an embedding of the one or more tracklets. A training module for detecting and tracking the at least one object using the embedding and the one or more uncertainty metrics is generated using deep learning techniques.
-
-
-
-
-
Search Results
6
records
(took 0.016 seconds)
