公开(公告)号：US10757377B2

公开(公告)日：2020-08-25

申请号：US15608109

申请日：2017-05-30

Applicant: PIXART IMAGING INC.

Inventor： Guo-Zhen Wang

IPC: H04N7/18 ,  G06K9/00 ,  H04N5/232 ,  G08B13/196

Abstract: The disclosure is related to a surveillance system and an operation method thereof. The surveillance system includes an auxiliary sensor module that is in full-time operation, and a main sensor module that is in a power-saving mode at a normal state. The main sensor is in operation only if the signals generated by the auxiliary sensor module meet a criterion of surveillance. The surveillance system can reduce power consumption since the more powerful main sensor module stays in the power-saving mode without actuation. The surveillance system can process the surveillance data generated by the auxiliary sensor module since it adopts the steps of ROI detection, feature extraction, and object recognition in an early stage of a whole surveillance process.

公开(公告)号：US20180276447A1

公开(公告)日：2018-09-27

申请号：US15985632

申请日：2018-05-21

Applicant: PixArt Imaging Inc.

Inventor： Guo-Zhen Wang

IPC: G06K9/00 ,  H04N5/232 ,  G06F3/01 ,  G02B27/01 ,  G06F3/00

CPC classification number: G06K9/0061 ,  G02B27/0093 ,  G02B27/017 ,  G02B2027/0138 ,  G02B2027/014 ,  G02B2027/0178 ,  G06F3/005 ,  G06F3/013 ,  G06F3/017 ,  G06K9/00597 ,  H04N5/23219 ,  H04N5/23222

Abstract: An eye state detecting method, which comprises: (a) capturing a detecting image; (b) computing a brightness variation tendency for a peripheral part of a darkest part of the detecting image; and (c) determining whether a user's eye is in an opening state or in a closing state according to the brightness variation tendency

公开(公告)号：US09977129B2

公开(公告)日：2018-05-22

申请号：US14821966

申请日：2015-08-10

Applicant: PIXART IMAGING INC.

Inventor： Guo-Zhen Wang ,  Ming-Tsan Kao

IPC: G01C3/08 ,  G01S17/89 ,  G01S17/46

CPC classification number: G01S17/89 ,  G01S17/46

Abstract: Disclosed are a distance measuring method and a distance measuring apparatus. During the distance measuring, an image is obtained. If the location of a center of gravity of the image is within a first segment, the calculating unit calculates a distance between the object and the distance measuring apparatus corresponding to the projection point, according to a first mapping relationship and the location of a center of gravity of the image. If the location of a center of gravity of the image is within a second segment, the calculating unit calculates a distance between the object and the distance measuring apparatus corresponding to the projection point according to a second mapping relationship and the location of a center of gravity of the image.

公开(公告)号：US20180060687A1

公开(公告)日：2018-03-01

申请号：US15670511

申请日：2017-08-07

Applicant: PIXART IMAGING INC.

Inventor： Guo-Zhen Wang

IPC: G06K9/46 ,  G06N99/00 ,  G06N3/08

Abstract: The present disclosure discloses an image recognition method and system based on deep learning. The image recognition method trains a recognizing engine for high resolution images and a recognizing engine for low resolution image separately. The two recognizing engines generate two independent feature groups specifically for high resolution and low resolution images respectively. A categorizing engine categorizes a testing image to a high resolution mode or a low resolution mode, and then the testing image is recognized by the appropriate recognizing engine. Therefore, the present disclosure increases the accuracy of image recognition under various conditions.

公开(公告)号：US20170131800A1

公开(公告)日：2017-05-11

申请号：US15155294

申请日：2016-05-16

Applicant: PIXART IMAGING INC.

Inventor： Guo-Zhen Wang ,  HSUAN-KU CHEN

IPC: G06F3/0354 ,  G06F3/03

CPC classification number: G06F3/03543 ,  G06F3/0304 ,  G06F3/0317

Abstract: The present disclosure illustrates an optical navigation apparatus with defocused image compensation function and a compensation circuit thereof The optical navigation apparatus comprises a light source, an image sensing circuit and a compensation circuit. The light source is configured to illuminate a work surface. The image sensing circuit captures a first image related to the work surface. The compensation circuit is configured to transform the first image and a point spread function of the light source into a first conversion result and a second conversion result in frequency domain, respectively, and then transform a result multiplied by the first conversion result and a reciprocal of the second conversion result from frequency domain to time domain to generate a second image.

公开(公告)号：US20170061185A1

公开(公告)日：2017-03-02

申请号：US15262633

申请日：2016-09-12

Applicant: PIXART IMAGING INC.

Inventor： Guo-Zhen Wang ,  EN-FENG HSU

IPC: G06K7/14 ,  G06K7/10

CPC classification number: G06K7/1417 ,  G06K7/10722 ,  G06K7/1452

Abstract: Disclosed are a QR code detection device and an operation method thereof. The QR code detection device comprises a body, a barcode detector and a barcode decoder. The barcode detector captures and processes a code image outside the body, and accumulates a number of times when a predetermined pattern feature is recognized in the code image. The predetermined pattern feature is a predetermined distance ratio. The barcode detector chooses a near-distance detection rule or a far-distance detection rule according to the processed code image to determine whether the predetermined pattern feature is recognized in the QR code image. When the barcode decoder determines that the code image is a QR code image because the number of times equals to a threshold number, the barcode decoder is automatically turned on to capture and decode the QR code image outside the body.

Abstract translation: 公开了一种QR码检测装置及其操作方法。 QR码检测装置包括主体，条形码检测器和条形码解码器。 条形码检测器捕获并处理身体外的代码图像，并且在代码图像中识别出预定图案特征时累积多次。 预定图案特征是预定距离比。 条形码检测器根据处理的代码图像选择近距离检测规则或远距离检测规则，以确定在QR码图像中是否识别出预定图案特征。 当条形码解码器由于次数等于阈值而确定代码图像是QR码图像时，自动打开条形码解码器以捕获并解码身体外部的QR码图像。

公开(公告)号：US20160187485A1

公开(公告)日：2016-06-30

申请号：US14864809

申请日：2015-09-24

Applicant: PixArt Imaging Inc.

Inventor： Guo-Zhen Wang

IPC: G01S17/48 ,  G01S7/48

CPC classification number: G01S17/48 ,  G01S7/4912

Abstract: An optical distance measurement method includes: acquiring a plurality of sensed values based on detecting light; performing a filtering operation to select a plurality of selected sensed values from the plurality of sensed values; determining a location of a center of gravity according to the plurality of selected sensed values; and calculating a plurality of depth values with respect to a plurality of detection points according to the location of the center of gravity and a plurality of depth information transformation functions respectively corresponding to the detection points.

Abstract translation: 光学距离测量方法包括：基于检测光获取多个感测值; 执行滤波操作以从所述多个感测值中选择多个所选择的感测值; 根据所述多个选择的感测值确定重心的位置; 以及根据重心的位置和分别对应于检测点的多个深度信息变换函数来计算关于多个检测点的多个深度值。