US 12,260,719 B2
Monitoring device and monitoring system
Shin Yamada, Kanagawa (JP); Kazuhiko Iwai, Kanagawa (JP); and Takeshi Watanabe, Kanagawa (JP)
Assigned to PANASONIC INTELLECTUAL PROPERTY MANAGEMENT CO., LTD., Osaka (JP)
Appl. No. 18/286,393
Filed by Panasonic Intellectual Property Management Co., Ltd., Osaka (JP)
PCT Filed Mar. 25, 2022, PCT No. PCT/JP2022/014458
§ 371(c)(1), (2) Date Oct. 11, 2023,
PCT Pub. No. WO2022/220072, PCT Pub. Date Oct. 20, 2022.
Claims priority of application No. 2021-067354 (JP), filed on Apr. 12, 2021.
Prior Publication US 2024/0203221 A1, Jun. 20, 2024
Int. Cl. G08B 13/196 (2006.01); G06V 20/52 (2022.01)
CPC G08B 13/19652 (2013.01) [G06V 20/52 (2022.01); G08B 13/19613 (2013.01)] 5 Claims
OG exemplary drawing
 
1. A monitoring device comprising a processor,
wherein the processor is configured to:
acquire a camera image, an image shot by a camera, of a no-entry zone, in which vehicles can travel, and a platform zone, in which passengers can board and exit vehicles;
detect an intrusion of a person into the no-entry zone based on the camera image; and
instruct the monitoring device to issue an alert of the person's intrusion,
wherein the processor is further configured to:
perform a first operation for detecting a person intruding from the platform zone into the no-entry zone based on the camera image;
perform a second operation for determining whether or not a vehicle is present in the no-entry zone based on the camera image; and
determine whether an alert needs to be issued or not based on a detection result of the first operation and a determination result of the second operation,
wherein a region which the camera can shoot is determined as a shooting region of the camera, and
wherein, when a deviation of the shooting region occurs such that a current shooting region deviates from an original shooting region, the processor performs an image conversion operation for converting a current camera image of the current shooting region to a converted camera image, which is an image that would be captured by the camera with the original shooting region, and uses the converted camera image as a basis for the first and second operations.