DEEP INFORMATION PROCESSING METHOD AND DEEP INFORMATION PROCESSING SYSTEM USING THE SAME

    公开(公告)号:US20240144508A1

    公开(公告)日:2024-05-02

    申请号:US18386151

    申请日:2023-11-01

    Inventor: Chi-Feng LEE

    Abstract: A depth information processing method and a depth information processing system using the same are provided. The method includes the following steps. A pixel shifting process is performed on a first image and a second image of an original image group to obtain a zero-shifted first image and a shifted second image of a shifted image group. The original image group and the shifted image group are combined to obtain a combined image. A depth information processing is performed on the combined image to obtain an initial depth information. The initial depth information has a basic depth information corresponding to the original image group and a compensated depth information corresponding to the shifted image group. A numerical restoration process is performed on the compensated depth information to obtain a restored depth information. The basic depth information and the restored depth information are fused to obtain a fused depth information.

    CALIBRATION SYSTEM AND CALIBRATION METHOD FOR MULTI-CAMERA SYSTEM

    公开(公告)号:US20230377198A1

    公开(公告)日:2023-11-23

    申请号:US18319503

    申请日:2023-05-18

    Inventor: Chi-Feng Lee

    Abstract: A calibration system for a multi-camera system is disclosed. The calibration system includes a connection device, a storage device, and a processor. The processor is configured to control each camera of the multi-camera system to capture a calibration image of a calibration board having a pattern including multiple conventional features and at least one non-conventional feature in which an FOV of the calibration image of at least one camera does not contain at least one conventional feature of the pattern, detect the conventional features and the non-conventional feature in the calibration image and record positions thereof in the storage device, transform a position of each conventional feature into absolute coordinates relative to reference coordinates by using a position of the non-conventional feature as the reference coordinates, and according to the absolute coordinates of the transformed conventional features, match the conventional features in the calibration images captured by the cameras to calibrate the cameras.

    Image device utilizing non-planar projection images to generate a depth map

    公开(公告)号:US11508082B2

    公开(公告)日:2022-11-22

    申请号:US17109055

    申请日:2020-12-01

    Inventor: Chi-Feng Lee

    Abstract: An image device utilizing non-planar projection images to generate a depth map includes two image capturers and a depth engine. The two image capturers are used for generating two non-planar projection images, wherein when each non-planar projection image of the two non-planar projection images is projected to a space corresponding to an image capturer corresponding to the each non-planar projection image, projection positions of each row of pixels of the each non-planar projection image in the space and optical centers of the two image capturers share a plane. The depth engine is used for generating a depth map according to the two non-planar projection images.

    IMAGE CAPTURE DEVICE AND DEPTH INFORMATION CALCULATION METHOD THEREOF

    公开(公告)号:US20220311985A1

    公开(公告)日:2022-09-29

    申请号:US17364385

    申请日:2021-06-30

    Abstract: The present invention discloses an image capture device and depth information calculation method thereof. The depth information calculation method includes: acquiring, a stereo camera module, an image information; and determining a re-projection mode according to a usage scenario, and transforming the image information to a depth information corresponding to the re-projection mode according to the re-projection mode. The re-projection mode is planar mode, cylinder mode or spherical mode, and the corresponding coordinate systems are planar coordinate system, cylinder coordinate system and spherical coordinate system respectively.

    IMAGE RENDERING DEVICE AND IMAGE RENDERING METHOD

    公开(公告)号:US20220122315A1

    公开(公告)日:2022-04-21

    申请号:US17501834

    申请日:2021-10-14

    Abstract: An image rendering device and an image rendering method are disclosed. For the elements of the image rendering device, a first sensor and a second sensor are configured to sense a target object in a two-dimensional (2D) mode and three-dimensional (3D) mode to generate a first surface-color-signal, a first 3D-depth-signal, a second surface-color-signal and a second 3D-depth-signal respectively. An IR projector is configured to generate an IR-dot-pattern. A processor is configured to control the IR projector to project the IR-dot-pattern on the target object in the 3D mode, and configured to process the first surface-color-signal, the second surface-color-signal, the first 3D-depth-signal and the second 3D-depth-signal to obtain a color 3D model of the target object.

    Image device utilizing non-planar projection images to generate a depth map and related method thereof

    公开(公告)号:US10885650B2

    公开(公告)日:2021-01-05

    申请号:US15903055

    申请日:2018-02-23

    Inventor: Chi-Feng Lee

    Abstract: An image device utilizing non-planar projection images to generate a depth map includes two image capturers and a depth engine. The two image capturers are used for generating two non-planar projection images, wherein when each non-planar projection image of the two non-planar projection images is projected to a space corresponding to an image capturer corresponding to the each non-planar projection image, projection positions of each row of pixels of the each non-planar projection image in the space and optical centers of the two image capturers share a plane. The depth engine is used for generating a depth map according to the two non-planar projection images.

    Image processor and related image system

    公开(公告)号:US10805514B2

    公开(公告)日:2020-10-13

    申请号:US15989218

    申请日:2018-05-25

    Inventor: Chi-Feng Lee

    Abstract: An image system for generating depth maps and color images includes a plurality of image sensors, at least one image processor, and at least one depth map generator. An image processor of the at least one image processor is coupled to at least one image sensor of the plurality of image sensors for generating luminance information represented by a first bit number and at least one color image represented by a second bit number according to at least one image captured by the at least one image sensor, wherein the at least one color image corresponds to the at least one image. A depth map generator of the at least one depth map generator is coupled to the image processor for generating a depth map corresponding to the at least one image according to the luminance information represented by the first bit number.

    Remote control system and method of generating a control command according to at least one static gesture

    公开(公告)号:US10802594B2

    公开(公告)日:2020-10-13

    申请号:US15096286

    申请日:2016-04-12

    Inventor: Chi-Feng Lee

    Abstract: A remote control system includes an object detection unit, an object determination unit, and a static gesture processing unit. The object detection unit detects an object corresponding to an operator according to a depth image including the operator and a face detection result corresponding to the operator. The object determination unit utilizes a combination of a gesture database, a color image of the object, and a two-dimensional image corresponding to the depth map to determine a gesture formed by the object when the operator moves the object to a predetermined position. The operator moves the object to the predetermined position and pulls the object after the operator moves the object to the predetermined position within a first predetermined period. The static gesture processing unit generates a first control command to control an electronic device according to at least one static gesture determined by the object determination unit.

    IMAGE DEVICE FOR GENERATING VELOCITY MAPS
    9.
    发明申请

    公开(公告)号:US20200013173A1

    公开(公告)日:2020-01-09

    申请号:US16502039

    申请日:2019-07-03

    Inventor: Chi-Feng Lee

    Abstract: An embodiment of the present invention provides an image device for generating velocity maps. The image device includes an image capturing group, a depth map generator, an optical flow generator, and a velocity map generator. The image capturing group includes at least one image capturer, each image capturer of the image capturing group captures a first image at a first time and a second image at a second time. The depth map generator generates a first depth map according to the first image and a second depth map according to the second image. The optical flow generator generates first optical flow according to the first image and the second image. The velocity map generator generates a first velocity map according to the first depth map, the second depth map and the first optical flow, wherein the first velocity map corresponds to the first image.

Patent Agency Ranking