-
Patent Agency Ranking
公开(公告)号：US20190281224A1
公开(公告)日：2019-09-12
申请号：US15756545
申请日：2017-07-31
Applicant: GOERTEK INC.
Inventor： Weiyu CAO , Xiang CHEN , Dachuan ZHAO
Abstract: The present application provides a method for tracking and shooting a moving target and a tracking device, firstly, feature points of a template image corresponding to each shooting angle is extracted in advance, after that, only a feature point of a currently shot target image needs to be calculated when matching, and then the feature points of the target image is matched with the feature points of the template image corresponding to each shooting angle, the shooting angel corresponding to the matched template image is determined as the shooting angle of the currently shot target image; if the shooting angel of the currently shot target image does not coincide with the preset shooting angle of the target, the tracking device is moved to track and shoot the target, so that the shooting angel of the target coincides with the preset shooting angle of the target, greatly reducing the calculation amount of the detection and matching of the feature point and improving the real-time performance of the tracking and shooting.
-
公开(公告)号：US20210374390A1
公开(公告)日：2021-12-02
申请号：US16461718
申请日：2018-06-26
Applicant: Goertek Inc.
Inventor： Tianrong DAI , Yuge ZHU , Dachuan ZHAO , Xiang CHEN
Abstract: An image processing method comprises: acquiring an actual image of a specified target from a video stream collected by a camera; identifying an area not shielded by the VR HMD and an area shielded by the VR HMD of the face of the specified target from the actual image, and acquiring first facial image data corresponding to the area not shielded; obtaining second facial image data matching the first facial image data according to the first facial image data and a preset facial expression model, wherein the second facial image data correspond to the area shielded; and fusing the first facial image data and the second facial image data to generate a composite image. An image processing device comprises a first acquiring unit, an identifying unit, a second acquiring unit and a generating unit, and is for performing the steps of the method described above.
-
公开(公告)号：US20190354171A1
公开(公告)日：2019-11-21
申请号：US15761144
申请日：2017-11-16
Applicant: GOERTEK INC.
Inventor： Tianrong DAI , Yuge ZHU , Dachuan ZHAO , Xiang CHEN
IPC: G06F3/01 , G02B27/00 , G06K9/00 , H04N19/167
Abstract: An input method and apparatus of a device. The method includes: tracking and recording movement of an eyeball gaze point of a user on a display screen of the device, to obtain a current eyeball gaze point movement trajectory; judging whether the current eyeball gaze point movement trajectory matches with a preset eyeball gaze point movement trajectory in a movement trajectory database; wherein the preset eyeball gaze point movement trajectories indicate paths of the movement of the eyeball gaze point on the display screen according to a preset length range within a preset time period; if matched, determining a corresponding input instruction by using the matched eyeball gaze point movement trajectory, and completing an input operation according to the input instruction; and if not matched, not conducting an input operation. The input method and apparatus of a device can conduct input according to the eyeball movement of the user.
-
公开(公告)号：US20190335034A1
公开(公告)日：2019-10-31
申请号：US15775053
申请日：2017-11-15
Applicant: GOERTEK INC.
Inventor： Tianrong DAI , Yuge ZHU , Dachuan ZHAO , Xiang CHEN
Abstract: An input method, device and system applied to a mobile smart terminal. The method includes: establishing communication connection with a virtual reality device; collecting input information of a user on the mobile smart terminal; and generating a corresponding operating instruction according to the input information and a corresponding matching relationship between preset instruction and input information in a preset instruction database, and sending the generated operating instruction to the virtual reality device, to enable the virtual reality device to execute a corresponding operation according to the operating instruction. An input device and an input system corresponding to the method are also provided. According to the input method, device and system, a corresponding operating instruction is generated by using the user input signal received on the mobile smart terminal to control the virtual reality device, thereby avoiding purchasing a gamepad, saving users money, facilitating the use, and improving the user experience.
-
公开(公告)号：US20210279504A1
公开(公告)日：2021-09-09
申请号：US16620790
申请日：2018-07-24
Applicant: GOERTEK INC.
Inventor： Weiyu CAO , Xiang CHEN , Dachuan ZHAO
Abstract: Disclosed are a method and an apparatus for processing feature point matching result, the first image and the second image are placed reversely, and the matching feature point pair between the first image and the second image is determined by using the feature point matching algorithm; the straight-line equation between each of the feature point pair is made mathematically, and the intersection between each straight line and other straight line is determined; the valid intersection group and the geometric center point thereof are determined according to the distance between each of the intersection and other intersection; and the judgment area of the feature point pair is determined according to the geometric center point, and whether the feature point pair is a correct matching result or not is determined according to whether a straight line between the feature point pair passes through the judgment area or not.
-
-
-
-
Search Results
5
records
(took 0.011 seconds)
