公开(公告)号：US20240176002A1

公开(公告)日：2024-05-30

申请号：US18551796

申请日：2023-02-10

Applicant: Panasonic Intellectual Property Management Co., Ltd.

Inventor： Seiya HIGUCHI ,  Masahiro ISHII ,  Hiroki URABE

IPC: G01S11/06 ,  G10L13/02 ,  H04B17/318

CPC classification number: G01S11/06 ,  G10L13/02 ,  H04B17/318

Abstract: A person detection system includes an obtainer and a processing unit. The obtainer obtains a signal strength of a radio wave transmitted by each of a plurality of transmitters and received by an antenna. The processing unit performs a detection process of detecting whether a person is present in a vicinity of the antenna, based on the signal strengths obtained by the obtainer. Each of the plurality of transmitters is classified into any one of a plurality of groups according to a position of the transmitter with respect to the antenna. In the detection process, the processing unit detects that a person is present in the vicinity of the antenna when each of the signal strengths obtained by the obtainer regarding, among the plurality of transmitters, two or more transmitters deviates from a normal range.

公开(公告)号：US20240020944A1

公开(公告)日：2024-01-18

申请号：US17867173

申请日：2022-07-18

Applicant: Panasonic Intellectual Property Management Co., Ltd.

Inventor： Ramdas KRISHNAKUMAR ,  Ariel BECK ,  Zong Sheng TANG ,  Khai Jun KEK ,  Satyam SATYAM ,  Masahiro ISHII ,  Yuto KITAGAWA

IPC: G06V10/72 ,  G06V10/762 ,  G06V10/764 ,  G06V10/74 ,  G06V10/98

CPC classification number: G06V10/72 ,  G06V10/762 ,  G06V10/764 ,  G06V10/761 ,  G06V10/993

Abstract: A method and system for sampling and augmenting a dataset associated with a first class and a second class, respectively, to balance the dataset of images is described. The method includes receiving a required number of reduced set of dataset images associated with the first class, creating a plurality of clusters from a set of images associated with the first class, and selecting a representative image from each cluster to provide a reduced set of images. Further, a median image and a non-defect artifact mask is generated corresponding to the set of images associated with the first class. Additionally, a defect foreground is extracted based on the median image and each defect image of another set of images associated with the second class. Finally, the at least one non-defect artifact is removed from the defect foreground to provide a new synthetic defect image for each defect image for augmentation.

公开(公告)号：US20240221720A1

公开(公告)日：2024-07-04

申请号：US17765668

申请日：2021-08-20

Applicant: Panasonic Intellectual Property Management Co., Ltd.

Inventor： Sara ASAI ,  Satoru MATSUNAGA ,  Hiroki URABE ,  Masahiro ISHII

IPC: G10L13/033

CPC classification number: G10L13/033

Abstract: A method for controlling an utterance device, a server (10), an utterance device (20), and a program control the utterance device (20). The server (10) receives utterance source information from an information source device (40), and set the utterance device (20) based on the utterance source information. Then, the server (10) provides an utterance sound source that has a sound source characteristic according to the utterance device (20) to the utterance device (20), and causes the utterance device (20) to utter using the utterance sound source.