公开(公告)号：US20200250434A1

公开(公告)日：2020-08-06

申请号：US16776432

申请日：2020-01-29

Applicant: HANWHA TECHWIN CO., LTD.

Inventor： Kyoungjeon JEONG

IPC: G06K9/00 ,  G06K9/36

Abstract: A method for generating a heat map from a video may include: detecting objects in the video; determining retention times of each of the objects in divided areas of the video; normalizing the retention times of each of the objects according to the sum of the retention times of the corresponding object in the divided areas; and generating a heat map based on the normalized retention times.

公开(公告)号：US20220006960A1

公开(公告)日：2022-01-06

申请号：US17475801

申请日：2021-09-15

Applicant: HANWHA TECHWIN CO., LTD.

Inventor： Hyun Ho KIM ,  Jinhyuk CHOI ,  Daebong KIM ,  Jaewoon BYUN ,  Sangwook LEE ,  Junsik KIM ,  Kyoungjeon JEONG ,  Eunyoung KIM

IPC: H04N5/232 ,  G06K9/78 ,  H04N5/247 ,  H04N5/262 ,  H04N17/00 ,  H04N7/025 ,  H04N7/18 ,  G06N20/00

Abstract: Provided is an operating method for an artificial intelligence (AI) camera that communicate with at least one another AI camera, the operating method including: configuring a cluster for the image analysis together with other AI camera by exchanging registration information with the other AI camera; sharing, with the other AI camera, registration information about normal cameras used to access the normal cameras; receiving, based on one of the normal cameras being allocated to AI camera, an image captured by the allocated normal camera by accessing the allocated normal camera; analyzing the received image using an AI processor in the AI camera; and transmitting a result of the analyzing the received image together with an identifier of the allocated normal camera to an external device.

公开(公告)号：US20210358516A1

公开(公告)日：2021-11-18

申请号：US17347496

申请日：2021-06-14

Applicant: HANWHA TECHWIN CO., LTD.

Inventor： Kyoungjeon JEONG

IPC: G10L25/78 ,  G10L15/00 ,  H04R5/04 ,  H04R1/40

Abstract: A voice recognition device includes a plurality of mics disposed toward different directions and a processor connected with the plurality of mics, wherein the processor is configured to determine, in a setup mode, a direction of a first sound received through the plurality of mics; set a non-detecting zone, which includes the direction of the first sound;
determine, in a normal mode, a direction of a second sound received through the plurality of mics; and skip voice recognition for the second sound or an operation based on the voice recognition depending on whether the direction of the second sound belongs to the non-detecting zone.