-
公开(公告)号：US11216967B2
公开(公告)日：2022-01-04
申请号：US16455621
申请日：2019-06-27
Applicant: VIVOTEK INC.
Inventor： Cheng-Chieh Liu , Chih-Yen Lin
Abstract: A queue information analyzing method is applied to an image analyzing apparatus. A monitoring image captured by the image analyzing apparatus has a triggering area. The queue information analyzing method includes identifying a first candidate object stayed within the triggering area, forming a sampling range via the first candidate object, determining whether a second candidate object stayed within the sampling range belongs to a queue of the first candidate object, and acquiring an amount and a accumulated time of candidate objects about the queue.
-
公开(公告)号：US20210174536A1
公开(公告)日：2021-06-10
申请号：US16831849
申请日：2020-03-27
Applicant: VIVOTEK INC.
Inventor： Cheng-Chieh Liu
Abstract: A queue analyzing method is applied to an image monitoring apparatus and can automatically generate an interval threshold according to position variation of objects. The queue analyzing method includes computing a plurality of intervals between all objects inside an image, dividing the plurality of intervals at least into a first group corresponding to a low interval range and a second group corresponding to a high interval range, computing an interval mean value and an interval amending value of objects inside the first group, utilizing the interval mean value and the interval amending value to generate the interval threshold, and marking some adjacent objects conforming to the interval threshold within the image.
-
公开(公告)号：US11030757B1
公开(公告)日：2021-06-08
申请号：US16708449
申请日：2019-12-10
Applicant: VIVOTEK INC.
Inventor： Cheng-Chieh Liu
Abstract: A queue analyzing method is applied to an image monitoring apparatus for determining whether a rear object belongs to a queue of a front object. The queue analyzing method includes computing an angle difference and an interval between the rear object and the front object, transforming an original interval threshold into an amended interval threshold via the angle difference, comparing the interval with the amended interval threshold, and determining the rear object and the front object belong to the same queue when the interval is smaller than the amended interval threshold.
-
公开(公告)号：US10769478B2
公开(公告)日：2020-09-08
申请号：US16197361
申请日：2018-11-21
Applicant: VIVOTEK INC.
Inventor： Cheng-Chieh Liu , Chia-Po Wei , Fu-Min Wang , Chia-Wei Chi
Abstract: A convolutional neutral network identification efficiency increasing method is applied to a related device. The convolutional neutral network identification efficiency increasing method includes analyzing an input image to acquire foreground information, utilizing the foreground information to generate a foreground mask, and transforming the input image into an output image via the foreground mask. The output image is used to be an input of the convolutional neutral network identification for preferred object identification efficiency.
-
15.发明申请公开(公告)号：US20200184216A1
公开(公告)日：2020-06-11
申请号：US16449480
申请日：2019-06-24
Applicant: VIVOTEK INC.
Inventor： Cheng-Chieh Liu
Abstract: A machine continuous learning method with a neural network object classifying function is applied to a monitoring camera apparatus having a processor with an object classifier. The machine continuous learning method includes utilizing the processor to receive an image, utilizing the object classifier to analyze the image for generating a first parameter and a second parameter, utilizing the processor to determine whether the first parameter belongs to at least one cluster established by human feedback, and utilizing the processor to output a label of the at least one cluster or the second parameter generated by the object classifier according to a determination result.
-
Patent Agency Ranking
16.发明授权公开(公告)号：US10453212B2
公开(公告)日：2019-10-22
申请号：US15603411
申请日：2017-05-23
Applicant: VIVOTEK INC.
Inventor： Cheng-Chieh Liu
IPC: G06T7/00 , G06T7/70 , G01S3/781 , G01S3/783 , G01S3/801 , G01S3/803 , G01S5/18 , G06T7/20 , G01S5/02 , G01S5/16
Abstract: A wireless transmitting/receiving system includes a transmitter, a first directional receiver, a camera, a storage device and a processor. The transmitter is disposed on a target object and transmits a wireless signal. The first directional receiver is disposed with respect to an entry/exit boundary. The first directional receiver receives the wireless signal and generates a first received signal strength indication. The camera captures an image of the entry/exit boundary. The storage device stores a mapping table of target object location and received signal strength. The processor is electrically connected to the storage device and determines a location of the target object and a moving direction of the target object with respect to the entry/exit boundary according to the image and the mapping table of target object location and received signal strength.
-
公开(公告)号：US10438060B2
公开(公告)日：2019-10-08
申请号：US15279435
申请日：2016-09-29
Applicant: VIVOTEK INC.
Inventor： Cheng-Chieh Liu
Abstract: A video flow analyzing method and a related camera device are applied to determine whether an object passes through a monitoring area. The video flow analyzing method includes drawing two boundaries on a video image correlative to the monitoring area to form a counting path, utilizing endpoints of the two boundaries to define an inlet and an outlet of the counting path, setting an initial point while the object moves into the counting path by crossing one of the boundaries, the inlet and the outlet, setting a final point while the object moves out of the counting path by crossing one of the boundaries, the inlet and the outlet, and utilizing the initial point and the final point to determine whether the object passes through the counting path.
-
公开(公告)号：US20190208097A1
公开(公告)日：2019-07-04
申请号：US16228576
申请日：2018-12-20
Applicant: VIVOTEK INC.
Inventor： Cheng-Chieh Liu , Wen-Pin Hsieh , Ting-Wei Hsu
IPC: H04N5/225 , H04N5/232 , G08B13/196 , G06T7/73
Abstract: An image analysis method is applied to estimating a mounting position of a camera and includes utilizing the camera to capture an image toward a target region. The image includes at least one object of interest. The object of interest has a pixel height in the image. The image analysis method further includes obtaining an inclining angle and a rolling angle of the camera relative to the target region, calculating a mounting height of the camera relative to the target region according to an input height and the pixel height of the object of interest, an image capturing parameter of the camera, the inclining angle and the rolling angle, and performing video content analysis on the image according to the image capturing parameter, the inclining angle, the rolling angle and the mounting height of the camera.
-
公开(公告)号：US20190057518A1
公开(公告)日：2019-02-21
申请号：US16053809
申请日：2018-08-03
Applicant: VIVOTEK INC.
Inventor： Cheng-Chieh Liu , Szu-Mo Chang , Chih-Yen Lin
Abstract: An object counting device includes an image capturer and a processor. The image capturer captures an image sequence related to a gate within a field of view. When an object in the image sequence passes through an entry/exit reference corresponding to the gate, the processor determines a moving direction of the object. When the processor determines that the object moves from a first side of the gate towards a second side of the gate, the processor counts the object into a first accumulated number. When the object exits from the field of view, the processor records an exit position of the object. The processor determines whether to count the object into a second accumulated number according to the exit position.
-
公开(公告)号：US20170148138A1
公开(公告)日：2017-05-25
申请号：US15350098
申请日：2016-11-13
Applicant: VIVOTEK INC.
Inventor： Cheng-Chieh Liu , Wei-Ming Liu
CPC classification number: G06T3/4038 , G06T7/33 , G06T2200/32 , G06T2207/30232 , H04N5/23238 , H04N5/247 , H04N7/181
Abstract: An image stitching method is applied to a camera system with an image stitching function, so as to combine monitoring images captured from different view angles. The camera system includes two image capturing units respectively having a first coordinate system and a second coordinate system, and monitoring regions of the two image capturing units are adjacent and include an overlapped monitoring region. The image stitching method includes detecting at least one moving object within the overlapped monitoring region, calculating at least one set of transforming parameters of the first coordinate system relative to the second coordinate system, acquiring a reliability level according to comparison result generated by mutual comparisons between several sets of transforming parameters and then further comparing with a threshold respectively, determining a final transform parameter by the reliability level, and utilizing the final transform parameter to stitch the monitoring images captured by the two image capturing units.
-
-
-
-
-
-
-
-
-
Search Results
67
records
(took 0.014 seconds)
