Abstract: An object attribution analyzing method applied to an object attribution analyzing device and includes dividing a plurality of continuous frames into a current frame and several previous frames, utilizing face detection to track and compute a first attribution predicted value of an object within the current frame, utilizing the face detection to acquire a feature parameter of the object within the current frame for setting a first weighting, acquiring a second attribution predicted value of the object within the several previous frames, setting a second weighting in accordance with the first weighting, and generating a first induction attribution predicted value of the object within the plurality of continuous frames via the first attribution predicted value weighted by the first weighting and the second attribution predicted value weighted by the second weighting.
Abstract: An image stitching method capable of effectively decreasing an amount of sampling points is applied to a first monitoring image and a second monitoring image overlapped with each other and generated by a monitoring camera device. The image stitching method includes acquiring a first sampling point and a second sampling point respectively on the first monitoring image and the second monitoring image, detecting a first specific parameter of the first monitoring image and a second specific parameter of the second monitoring image, determining whether the first sampling point is matched with the second sampling point according to the first specific parameter and the second specific parameter, and deciding whether to stitch the first monitoring image and the second monitoring image by the first sampling point and the second sampling point according a determination result.
Abstract: A metering compensation method for effectively increasing visibility of an image is applied to a monitoring camera apparatus. The metering compensation method includes acquiring a histogram of the image, setting a convergent target value and a minimal mapping value, utilizing the convergent target value and the minimal mapping value to set a weighting function, transforming the histogram into a weighted histogram via the weighting function for acquiring an intensity mean of the weighted histogram, and utilizing the convergent target value and the intensity mean to generate a first exposure compensation value. The first exposure compensation value can be used for determining whether to adjust an exposure parameter of the monitoring camera apparatus.
Abstract: An image processing method includes receiving image data and outputting an image stream including an initial group of pictures and a next group of pictures according to the image data. The initial group of pictures includes a first initial frame and at least one first non-initial frame. The next group of pictures includes a second initial frame and at least one second non-initial frame. The image processing method further includes obtaining a first ideal frame count of the next group of pictures according to a ratio relationship of frame sizes of the first initial frame and the at least one first non-initial frame of the initial group of pictures in a predetermined frame segment or a predetermined time segment and setting a frame count of the next group of pictures according to the first ideal frame count.
Abstract: A video synopsis method for overlapping videos generated in different periods is applied to a video synopsis device. The video synopsis method includes dividing a monitoring film into a plurality of videos, acquiring a pixel difference between frames respectively from the plurality of videos at identical time sequence, acquiring a weighting parameter according to the pixel difference, and utilizing the weighting parameter to overlap the frames respectively from the plurality of videos so as to generate a composite frame.
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.
Type:
Grant
Filed:
August 3, 2018
Date of Patent:
September 22, 2020
Assignee:
VIVOTEK INC.
Inventors:
Cheng-Chieh Liu, Szu-Mo Chang, Chih-Yen Lin
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.
Type:
Grant
Filed:
November 21, 2018
Date of Patent:
September 8, 2020
Assignee:
VIVOTEK INC.
Inventors:
Cheng-Chieh Liu, Chia-Po Wei, Fu-Min Wang, Chia-Wei Chi
Abstract: A stereo vision image calibration method is applied to an image capturing device having a first camera, a second camera and an image rectifying function. The first camera and the second camera are arranged along a first direction. The first camera and the second camera are respectively utilized to acquire a first image and a second image. The image rectifying function rectifies the first image and the second image by a stereo vision parameter. The stereo image calibration method includes selecting the rectified first image and the rectified second image to compute a global disparity vector between the adjust image and the reference image, and if a vector component of the global disparity vector along a second direction which is different from the first direction has non-zero value, processing a stereo vision calibration according to the vector component.
Abstract: A pedestrian detection method is applied to a monitoring camera. The pedestrian detection method includes forming a first detecting window on at least one monitoring frame via an object analysis function, utilizing a human form detection function to modulate the first detecting window for forming a second detecting window, analyzing the second detecting window via a human local detection function to mark an upper detecting window about a pedestrian on the monitoring frame, and determining whether to calibrate the second detecting window via analysis of the upper detecting window.
Type:
Grant
Filed:
November 13, 2018
Date of Patent:
July 21, 2020
Assignee:
VIVOTEK INC.
Inventors:
Sheng-Yuan Chen, Hsun-Shun Yu, Cheng-Chieh Liu
Abstract: An image displaying method capable of automatically adjusting a displaying speed according to content of the image is applied to an image displaying apparatus. The image displaying method includes acquiring video data containing a first group of images and a second group of images, acquiring a first time difference between a first beginning image frame of the first group of images and a second beginning image frame of the second group of images, comparing the first time difference with a predetermined threshold value, and adjusting the displaying speed of the first group of images in accordance with a comparison result. Each group of images is consisted of a beginning image frame and at least one non-beginning image frame.
Abstract: A motion detection method is applied to a monitoring camera apparatus with motion detection function. The motion detection method includes analyzing a pixel value of each frame from a video stream changed over time, defining a first period and a second period having the pixel value greater than a triggering threshold respectively as a first event and a second event, comparing a time length of the first period with a filtering threshold to acquire time difference between an end point of the first period and a beginning point of the second period, comparing the time difference with a merging threshold, and acquiring relation between the first event and the second event according to comparison results of the filtering threshold and the merging threshold, so as to determine a detecting period of the motion detection function for actuation.
Abstract: A lens detection system includes a system chip, and the system chip includes a first lens selection pin and a protocol path pin. A lens detection method includes performing a reset step by the system chip; enabling the first lens selection pin by the system chip; detecting a first lens identification code via the protocol path pin by the system chip; loading first lens data by the system chip and entering a first lens operation mode for controlling an externally connected first lens if the first lens identification code is detected; and disabling the first lens selection pin by the system chip if the first lens identification code is undetected.
Type:
Grant
Filed:
December 20, 2018
Date of Patent:
April 21, 2020
Assignee:
VIVOTEK INC.
Inventors:
Chien-Ming Yeh, Ting-Chia Chang, Ren-Wei Lin, Wen-Yuan Li
Abstract: An image processing method includes steps of receiving an image sequence; when at least one object appears in the image sequence, analyzing a moving trajectory of each object; extracting at least one characteristic point from each moving trajectory; classifying the at least one characteristic point of each moving trajectory within a predetermined time period into at least one cluster; and storing at least one characteristic parameter of each cluster.
Abstract: An object counting method having route distribution property is applied to an image processing device. The object counting method includes steps of recording an initial position datum and a final position datum of any object moving within an image frame, setting at least one detection line inside the image frame, determining whether a connection line between the initial position datum and the final position datum moves across the detection line, and drawing an object distribution diagram by relation between an amount of the object moving across the detection line and its detective period.