ABNORMALITY DETECTION DEVICE, ABNORMALITY DETECTION METHOD, AND ABNORMALITY DETECTION SYSTEM

    公开(公告)号:US20230342903A1

    公开(公告)日:2023-10-26

    申请号:US18022427

    申请日:2020-09-25

    发明人: Keigo HASEGAWA

    IPC分类号: G06T7/00

    CPC分类号: G06T7/0004

    摘要: A technique is provided for detecting the presence or absence of an abnormality with respect to an object appearing in a target image with high accuracy without using AI, even in an environment in which luminance values and colors are likely to fluctuate. An abnormality detection device (230) includes: an image input unit (232) for inputting an input image indicating an abnormality detection target object; a gradient distribution generation unit (234) for dividing the input image into predetermined regions and generating, for each region, a gradient distribution that indicates a distribution of a luminance gradient direction of the region; and an abnormality determination unit (236) for determining the presence or absence of an abnormality by analyzing the gradient distribution generated for each region.

    IMAGE ANALYSIS SYSTEM AN UPDATE METHOD FOR MACHINE LEARNING MODEL

    公开(公告)号:US20230386188A1

    公开(公告)日:2023-11-30

    申请号:US18449730

    申请日:2023-08-15

    发明人: Keigo HASEGAWA

    摘要: An image analysis system and update method for a machine-learning model are to update a model in operation 111 to a retrained model 121, wherein in an image analysis server 1 which analyzes shot images, a first inference unit 11 performs inference using the trained model in operation 111, a relearning unit 14 performs relearning to generate a retrained model, a second inference unit 12 performs inference using a retrained model 121, and a comparison unit 15 compares the execution results of the first inference unit 11 and the second inference unit 12 to determine whether or not to update the model in operation 111 to the retrained model 121.

    PULSE RATE ESTIMATION METHOD, DEVICE, AND SYSTEM

    公开(公告)号:US20220322950A1

    公开(公告)日:2022-10-13

    申请号:US17638798

    申请日:2019-09-05

    发明人: Keigo HASEGAWA

    IPC分类号: A61B5/024 A61B5/00

    摘要: Provided is a method for estimating a pulse rate with high accuracy in the case that short-term burst noise is mixed in an estimation interval. Included are a pulse wave signal generating step of generating a pulse wave signal from an image of a pulse rate estimation target; a peak component suppression step of limiting an amplitude value of the pulse wave signal that is larger than a first threshold value to the first threshold value, and outputting a pulse wave analysis signal; and a frequency analysis step of outputting a frequency spectrum of the pulse wave analysis signal.

    WIRELESS COMMUNICATION TERMINAL
    4.
    发明申请
    WIRELESS COMMUNICATION TERMINAL 有权
    无线通信终端

    公开(公告)号:US20160309381A1

    公开(公告)日:2016-10-20

    申请号:US15198069

    申请日:2016-06-30

    发明人: Keigo HASEGAWA

    IPC分类号: H04W36/08 H04W36/22 H04W36/30

    摘要: The present invention provides a wireless communication terminal which can flexibly select a base station according to communication quality and a load status and improve communication quality which a user experiences in a wireless communication system which does not include a handover mechanism and is not notified of availability of radio resources from each base station.

    摘要翻译: 本发明提供一种无线通信终端,其可以根据通信质量和负载状态灵活地选择基站,并且提高用户在不包括切换机制的无线通信系统中经历的通信质量,并且没有通知可用性 每个基站的无线电资源。

    MONITORING SYSTEM, CAMERA, ANALYZING DEVICE, AND AI MODEL GENERATING METHOD

    公开(公告)号:US20230306711A1

    公开(公告)日:2023-09-28

    申请号:US18043198

    申请日:2020-09-17

    摘要: An Objective of the present invention is to improve the inter-camera cooperation in a monitoring system comprising multiple cameras each having a function to perform video analysis by use of an AI model. A monitoring system according to the present example comprises: multiple AI cameras 101 each having a function to perform video analysis by use of an AI mode; and an analyzing device 102 that generates the AI model used in the AI cameras 101. Each of the AI cameras 101 detects suspicious behaviors through video analysis using a particular-behavior detection AI model for detecting the suspicious behaviors. When suspicious behaviors are detected by any of the AI cameras 101, the analyzing device 102 generates a particular-person detection AI model for detecting a particular person (suspicious person) having done the suspicious behaviors, and transmits the particular-person detection AI model to each of the AI cameras 101. Each of the AI cameras 101 detects the suspicious person through video analysis using the particular-person detection AI model.

    IMAGE ANALYSIS SYSTEM, IMAGE ANALYSIS METHOD, AND IMAGE ANALYSIS PROGRAM

    公开(公告)号:US20230125890A1

    公开(公告)日:2023-04-27

    申请号:US17909458

    申请日:2021-03-11

    IPC分类号: G06V20/52 G06T7/00 G06T7/11

    摘要: There is provided an image analysis system having an image analysis server which analyzes an input image of a monitoring area and detects a state of a specific monitored object. The image analysis server is configured to divide, in the input image of the monitoring area, a portion of an area in which the monitored object is expected to be present into a plurality of grids, generate a trained model trained by associating “1” with an image of a grid in which the monitored object is present and “0” with an image of a grid in which the monitored object is not present for each grid, calculate, for the input image, a confidence of a presence of the monitored object for each grid using the trained model, determine a presence or absence of the monitored object in the monitoring area based on confidences of the plurality of grids, and detect an abnormality when a confidence value in at least one of the grids is inconsistent with the determination result.

    WIRELESS COMMUNICATION SYSTEM AND WIRELESS COMMUNICATION METHOD
    7.
    发明申请
    WIRELESS COMMUNICATION SYSTEM AND WIRELESS COMMUNICATION METHOD 有权
    无线通信系统和无线通信方法

    公开(公告)号:US20160227584A1

    公开(公告)日:2016-08-04

    申请号:US15021383

    申请日:2014-09-05

    IPC分类号: H04W74/08 H04W16/14

    摘要: Provided is a wireless communication system that is capable of preventing interference between secondary use systems that do not use a database. The wireless communication system uses a white space for opposing communication between a base station and a terminal station.At startup, the base station transmits a preamble over a cycle that is n-times a frame length (where n is an integer 2 or greater), changes a set frequency channel if ranging is not detected from a terminal station within a fixed time interval, and begins normal operation using the set frequency channel if ranging is detected.At startup, the terminal station detects a preamble within a received signal, changes a set frequency channel if a peak is detected at each frame length, and transmits a ranging signal if peaks are detected for cycles that are n-times the frame length and peaks are not detected for other cycles.

    摘要翻译: 提供能够防止不使用数据库的次要使用系统之间的干扰的无线通信系统。 无线通信系统使用白色空间来对抗基站和终端站之间的通信。 在启动时,基站在帧长度为n倍(n为2以上的整数)的周期上发送前导码,如果在固定时间间隔内没有从终端检测到测距,则改变设定的频道 ,并且如果检测到测距,则使用设置的频率信道开始正常操作。 在启动时,终端站检测到接收到的信号中的前导码,如果在每个帧长度处检测到峰值,则改变设定的频道,并且如果针对帧长度和峰值的n倍的周期检测到峰值,则发送测距信号 没有检测到其他周期。

    MACHINE-LEARNING MODEL FRAUD DETECTION SYSTEM AND FRAUD DETECTION METHOD

    公开(公告)号:US20200082056A1

    公开(公告)日:2020-03-12

    申请号:US16615619

    申请日:2018-04-10

    发明人: Keigo HASEGAWA

    摘要: A machine learning model fraud detection system and fraud detection method wherein a license/model management apparatus: generates a test data-trained model by inputting a pre-trained model and test data associated therewith from a licensor apparatus, carrying out learning using the test data on the pre-trained model; stores the test data-trained model in association with the output values obtained when the test data is executed in the test data-trained model; inputs the associated test data into a user model, executes the model when the user model is inputted from a user apparatus using the test data-trained model; compares the output data from the user model with the stored output values from the test data-trained model and detects the fraud if the resulting error is outside tolerance limits.

    METHOD FOR ADJUSTING TRANSMISSION TIMING IN MULTIPLE ACCESS SYSTEM
    10.
    发明申请
    METHOD FOR ADJUSTING TRANSMISSION TIMING IN MULTIPLE ACCESS SYSTEM 审中-公开
    用于调整多路访问系统中传输时序的方法

    公开(公告)号:US20170013582A1

    公开(公告)日:2017-01-12

    申请号:US15270223

    申请日:2016-09-20

    摘要: A method for adjusting a transmission timing of a terminal station, which is performed at a base station in a Time-Division Duplex communication system, is disclosed. The method includes (a) receiving ranging signals or other reference signals, transmitted from a terminal station; (b) determining whether transmission timing at the terminal station is appropriate or not, by referring to the ranging signals transmitted from the terminal station; and (c) transmitting a value for adjusting the transmission timing at the terminal station. The value of the transmission timing is a value of the integral multiples of the timing offset detection capability of the ranging signal, or a value calculated by referring to the received reference signals, which have assigned with a different interval from an interval of the ranging signals.

    摘要翻译: 公开了一种用于调整在时分双工通信系统中的基站执行的终端的发送定时的方法。 该方法包括:(a)接收从终端发送的测距信号或其他参考信号; (b)参照从终端发送的测距信号,确定终端的发送定时是否适合; 和(c)发送用于调整终端站的发送定时的值。 发送定时的值是测距信号的定时偏移检测能力的整数倍的值,或通过参考接收到的参考信号计算的值,该参考信号已经从测距信号的间隔分配了不同的间隔 。