-
公开(公告)号:US11100350B2
公开(公告)日:2021-08-24
申请号:US16279975
申请日:2019-02-19
Applicant: Avigilon Corporation
Inventor: Kevin Piette , Pietro Russo , Mahesh Saptharishi , Bo Yang Yu
Abstract: Methods, systems, and techniques for classifying and/or detecting objects using visible and invisible light images. A visible light image and an invisible light image are received at a convolutional neural network (CNN). The visible light image depicts a region-of-interest imaged using visible light. The invisible light image depicts at least a portion of the region-of-interest imaged using invisible light, and at least one of the images depicts an object-of-interest within the portion of the region-of-interest shared between the images. The CNN then classifies and/or detects the object-of-interest using the images. The CNN may be trained to perform this classification and/or detection using pairs of visible and invisible light training images.
-
公开(公告)号:US11087610B2
公开(公告)日:2021-08-10
申请号:US16199107
申请日:2018-11-23
Applicant: Avigilon Corporation
Inventor: Peter Anderholm , Yanyan Hu , Kevin Piette , Pietro Russo , Bo Yang Yu
IPC: G01S13/04 , G08B21/04 , G07F19/00 , G06K9/00 , G08B21/02 , G01S13/88 , G08B13/196 , G08B13/181 , G01S13/86 , G08B25/10 , G08B21/22
Abstract: A computer-implemented method comprises detecting, with a presence detector such as a radar device, a presence of a person at a location such as an ATM vestibule. In response thereto, a timer is initiated. After initiating the timer, a portal sensor is used to detect a change in a status of a portal permitting access to the location. In response thereto, the timer is adjusted (for example the timer is reset). Thus, multiple consecutive normal usages of the vestibule do not unnecessarily trigger an alarm.
-
公开(公告)号:US11055837B2
公开(公告)日:2021-07-06
申请号:US16369812
申请日:2019-03-29
Applicant: Avigilon Corporation
Inventor: Kevin Piette , Pietro Russo , Bo Yang Yu
Abstract: A system is provided, including: a radar sensor configured to transmit and receive a radar signal from a person; a depth camera configured to receive a depth image of the person; one or more processors communicative with memory having stored thereon computer program code configured when executed by the one or more processors to cause the one or more processors to perform a method comprising: detect the person; determine depth information relating to the person using the depth image; determine a correlation between the depth information of the person and the radar signal received from the person; and in response to the correlation not within a range of expected values, generating an alert. The depth information may be a volume or surface area of the person.
-
-