公开(公告)号：US20250147937A1

公开(公告)日：2025-05-08

申请号：US18522849

申请日：2023-11-29

Applicant: INSTITUTE FOR INFORMATION INDUSTRY

Inventor： Yu-Chen TSAI ,  Ming-Fang WENG

IPC: G06F16/215 ,  G06F16/25

Abstract: The present invention is a data cleaning device executing a data cleaning method. The data cleaning method includes executing an application, and executing a prompt plugin management program. The operation of executing the prompt plugin management program includes generating a prompt instruction based on an unformatted content via a first prompt template, transmitting the prompt instruction to a first device, and receiving a formatted content from the first device. The formatted content is generated by the first device based on the prompt instruction through a large language model.

公开(公告)号：US20250166289A1

公开(公告)日：2025-05-22

申请号：US18403742

申请日：2024-01-04

Applicant: INSTITUTE FOR INFORMATION INDUSTRY

Inventor： Min DI ,  Kuan-Yu CHEN ,  Jing Tong FU ,  Ming-Fang WENG

IPC: G06T15/20 ,  G06T7/11 ,  G06T7/174 ,  G06T7/70 ,  G06T17/20

Abstract: A video generating device and method are provided. The device analyzes a plurality of real-time images corresponding to a plurality of users to segment a target image from each of the real-time images. The device generates a three-dimensional portrait model corresponding to each of the users based on the target image of each of the real-time images. The device determines a first three-dimensional scenario template from the three-dimensional scenario templates based on a user quantity of the users and the position quantity corresponding to each of the three-dimensional scenario templates. The device composites the three-dimensional portrait models to the spatial label position of the first three-dimensional scenario template to generate a video corresponding to the users.

公开(公告)号：US20230148172A1

公开(公告)日：2023-05-11

申请号：US17575649

申请日：2022-01-14

Applicant: INSTITUTE FOR INFORMATION INDUSTRY

Inventor： Jhih-Rong CHEN ,  Jia-Wei HONG ,  Ming-Fang WENG

IPC: G06T11/00 ,  G06T7/73 ,  G06V10/44 ,  G06T3/00 ,  G06K9/62 ,  G06T7/33

CPC classification number: G06T11/00 ,  G06T7/73 ,  G06V10/443 ,  G06T3/0056 ,  G06K9/6215 ,  G06T7/337 ,  G06T2210/56

Abstract: An augmented reality processing device is provided, comprising an image capturing circuit and a processor. The processor is connected to the image capturing circuit, and execute operations of: generating an original point cloud image according to the first environment image and a physical object in the first environment image; generating an expanded point cloud image corresponding to the physical object from the second environment image according to the first environment image and the physical object point cloud set, and generating a superimposed point cloud image according to the expanded point cloud image and the original point cloud image; and generating a transformation matrix according to the original point cloud image and the expanded point cloud image, and superimposing a virtual object to the second environment image according to the superimposed point cloud image and the transformation matrix.

公开(公告)号：US20210134048A1

公开(公告)日：2021-05-06

申请号：US16791613

申请日：2020-02-14

Applicant: Institute For Information Industry

Inventor： Ming-Fang WENG ,  Bo-Chih CHEN

IPC: G06T15/10 ,  H04N13/271 ,  H04N13/128 ,  H04N13/111

Abstract: A computer device calculates an estimated depth for each of non-feature points of a sparse point cloud map of an image according to feature-point depths of feature points of the sparse point cloud map and pixel depths of pixels of an image depth map of the image, and generates a synthesized depth map according to the feature-point depths and the estimated depths.

公开(公告)号：US20180107875A1

公开(公告)日：2018-04-19

申请号：US15347356

申请日：2016-11-09

Applicant: Institute For Information Industry

Inventor： Ching-Wen LIN ,  Ming-Fang WENG

IPC: G06K9/00 ,  G06K9/46 ,  G06T7/00

CPC classification number: G06K9/00671 ,  G06K9/4604 ,  G06T7/0042 ,  G06T7/73 ,  G06T2207/10004 ,  G06T2207/30208

Abstract: A visual positioning apparatus, method, and non-transitory computer readable storage medium thereof are provided. The visual positioning apparatus derives an image by sensing a visual code marker in a space and performs the following operations: (a) identifying an identified marker image included in the image, (b) searching out the corner positions of the identified marker image, (c) deciding a marker structure of the identified marker image according to the corner positions, wherein the marker structure includes vertices, (d) selecting a portion of the vertices as first feature points, (e) searching out a second feature point for each first feature point, (f) updating the vertices of the marker structure according to the second feature points, (g) selecting a portion of the updated vertices as the third feature points, and (h) calculating the position of the visual positioning apparatus according to the third feature points.

公开(公告)号：US20220114789A1

公开(公告)日：2022-04-14

申请号：US17148509

申请日：2021-01-13

Applicant: INSTITUTE FOR INFORMATION INDUSTRY

Inventor： Li-Ting CHEN ,  Ming-Fang WENG

IPC: G06T19/00 ,  H04N13/332 ,  H04N13/239

Abstract: A virtual and real image fusion method is disclosed. The method comprises the following operations: obtaining a picture of a three dimensional space by a first camera, in which the picture comprises a screen picture and a tag picture of an entity tag and the screen picture is projected on the entity tag; obtaining a corresponding point data of the entity tag on the screen picture according to the picture by a processor; obtaining a spatial correction parameter according to the corresponding point data by the processor; and displaying an image on the screen picture according to the spatial correction parameter by the processor.

公开(公告)号：US20180302553A1

公开(公告)日：2018-10-18

申请号：US15487420

申请日：2017-04-13

Applicant: Institute For Information Industry

Inventor： Ming-Fang WENG ,  Ching-Wen LIN

IPC: H04N5/232 ,  G06T7/73 ,  G06T7/194 ,  G06T7/77

CPC classification number: H04N5/23222 ,  G06T7/194 ,  G06T7/74 ,  G06T7/77 ,  G06T2207/20021 ,  G06T2207/20076 ,  G06T2207/30201 ,  G06T2207/30244

Abstract: A camera system and an image-providing method are disclosed to overcome that conventional cameras cannot make a decision by themselves as for whether and/or how to capture images. The disclosed camera system includes a camera for capturing images and a computer device used to calculate an estimated camera location and pose for the camera. The camera system also includes a location adjusting device and a pose adjusting device to adjust the camera to the estimated camera location and pose.

公开(公告)号：US20210090339A1

公开(公告)日：2021-03-25

申请号：US16676074

申请日：2019-11-06

Applicant: INSTITUTE FOR INFORMATION INDUSTRY

Inventor： Jia-Wei HONG ,  Jing-Tong FU ,  Ming-Fang WENG

IPC: G06T19/00 ,  G06K9/00 ,  G06T7/73 ,  G06T7/13 ,  G06T7/60

Abstract: A virtuality-reality overlapping method is provided. A point cloud map related to a real scene is constructed. Respective outline border vertexes of a plurality of objects are located by using 3D object detection. According to the outline border vertexes of the objects, the point cloud coordinates of the final candidate outline border vertexes are located according to the screening result of a plurality of projected key frames. Then, the point cloud map is projected to the real scene for overlapping a virtual content with the real scene.

公开(公告)号：US20200013187A1

公开(公告)日：2020-01-09

申请号：US16049798

申请日：2018-07-30

Applicant: Institute For Information Industry

Inventor： Jia-Wei HONG ,  Shih-Kai HUANG ,  Ming-Fang WENG ,  Ching-Wen LIN

IPC: G06T7/73 ,  G01B11/00 ,  G06K9/00 ,  G06K9/62

Abstract: A space coordinate converting server and method thereof are provided. The space coordinate converting server receives a field video recorded with a 3D object from an image capturing device, and generates a point cloud model accordingly. The space coordinate converting server determines key frames of the field video, and maps the point cloud model to key images of the key frames based on rotation and translation information of the image capturing device for generating a characterized 3D coordinate set. The space coordinate converting server determines 2D coordinates of the 3D object in key images, and selects 3D coordinates from the characterized 3D coordinate set according to the 2D coordinates. The space coordinate converting server determines a space coordinate converting relation according to marked points of the 3D object and the 3D coordinates.

公开(公告)号：US20160042714A1

公开(公告)日：2016-02-11

申请号：US14504439

申请日：2014-10-02

Applicant: INSTITUTE FOR INFORMATION INDUSTRY

Inventor： Teng-Chang CHANG ,  Ming-Fang WENG

IPC: G09G5/00 ,  G06F3/03

CPC classification number: G09G5/005 ,  G06F3/03 ,  G09G5/026 ,  G09G2340/0464 ,  G09G2380/02

Abstract: A display system, an image compensation method and a non-transitory computer readable storage medium thereof are provided. The display system includes a flexible panel, a prediction unit, a compensation unit, an image synthesis unit and a control unit. The prediction unit predicts a prediction angle of the flexible panel in a final time. The compensation unit generates a first compensation image according to an initial display angle of the flexible panel in an initial time, and generates a second compensation image according to the prediction angle. The image synthesis unit synthesizes a first display image according to the first compensation image and the second compensation image. The control unit selectively substitutes the first display image for an image displayed on the flexible panel in the final time.

Abstract translation: 提供了显示系统，图像补偿方法和非暂时性计算机可读存储介质。 显示系统包括柔性面板，预测单元，补偿单元，图像合成单元和控制单元。 预测单元最终预测柔性面板的预测角度。 补偿单元根据初始时间的柔性面板的初始显示角度生成第一补偿图像，并根据预测角度生成第二补偿图像。 图像合成单元根据第一补偿图像和第二补偿图像合成第一显示图像。 控制单元在最终时间中选择性地将第一显示图像替换为在柔性面板上显示的图像。