-
公开(公告)号：US20240029285A1
公开(公告)日：2024-01-25
申请号：US18476363
申请日：2023-09-28
Applicant: Ambarella International LP
Inventor： Jian Tang , Tao Liu , Jingyang Qiu
CPC classification number: G06T7/586 , H04N7/0117 , G06T3/40 , G06T2207/30201
Abstract: An apparatus comprising an interface, a light projector and a processor. The interface may be configured to receive pixel data. The light projector may be configured to generate a structured light pattern. The processor may be configured to process the pixel data arranged as video frames comprising the structured light pattern, perform computer vision operations to detect a size of a face area of the video frames, determine a scale ratio in response to the size of the face area, extract the structured light pattern from the video frames, generate a downscaled structured light image and generate a depth map in response to the downscaled structured light image and a downscaled reference image. A downscale operation may be performed in response to the scale ratio to generate the downscaled structured light image. The scale ratio may enable the generation of the downscaled structured light image with sufficient depth pixels.
-
公开(公告)号：US11880992B2
公开(公告)日：2024-01-23
申请号：US17694726
申请日：2022-03-15
Applicant: Ambarella International LP
Inventor： Jian Tang , Tao Liu , Jingyang Qiu
CPC classification number: G06T7/586 , G06T3/40 , H04N7/0117 , G06T2207/30201
Abstract: An apparatus comprising an interface, a light projector and a processor. The interface may be configured to receive pixel data. The light projector may be configured to generate a structured light pattern. The processor may be configured to process the pixel data arranged as video frames comprising the structured light pattern, perform computer vision operations to detect a size of a face area of the video frames, determine a scale ratio in response to the size of the face area, extract the structured light pattern from the video frames, generate a downscaled structured light image and generate a depth map in response to the downscaled structured light image and a downscaled reference image. A downscale operation may be performed in response to the scale ratio to generate the downscaled structured light image. The scale ratio may enable the generation of the downscaled structured light image with sufficient depth pixels.
-
公开(公告)号：US20240013416A1
公开(公告)日：2024-01-11
申请号：US18363437
申请日：2023-08-01
Applicant: TRINAMIX GMBH
Inventor： Patrick SCHINDLER
Abstract: A method for determining a depth map of at least one object, the method including:
a) illuminating a scene including the object by using at least one flood light source; and imaging at least one pixelated flood image of the scene by using at least one camera;
b) projecting at least one illumination pattern on the scene by using at least one projector and imaging at least one pixelated reflection image using the at least one camera;
c) evaluating the flood image by using at least one evaluation device thereby determining reflectance R(x) for each pixel position x of the flood image;
d) evaluating the reflection image by using the evaluation device;
e) assigning and extrapolating with the evaluation device; and
f) determining the depth map with the evaluation device.-
公开(公告)号：US20230386061A1
公开(公告)日：2023-11-30
申请号：US18448575
申请日：2023-08-11
Applicant: Samsung Electronics Co., Ltd.
Inventor： Yongchan KEH , Byeonghoon PARK , Kihuk LEE , Hwayong KANG
Abstract: An electronic device is provided. The electronic device includes an optical output module, an image sensor configured to receive a reflected light that originates from a light output by the optical output module, and to obtain image data, a memory, and a processor operatively coupled to the optical output module, the image sensor, and the memory, wherein the processor is configured to control the optical output module to output a spotlight at a first time point, control the optical output module to output a floodlight at a second time point, produce a first depth map based on first image data associated with a first reflected light that originates from the spotlight, produce a second depth map based on second image data associated with a second reflected light that originates from the floodlight, and produce a third depth map based on the first depth map and the second depth map.
-
公开(公告)号：US11803104B2
公开(公告)日：2023-10-31
申请号：US17537614
申请日：2021-11-30
Applicant: Lumileds LLC
Inventor： Arjen Gerben Van der Sijde , Nicola Bettina Pfeffer , Pieter Johannes Quintus van Voorst Vader , Yourii Martynov
IPC: H04N5/235 , G03B15/05 , G06V10/141 , G06V10/147 , G06V20/10 , G06V20/64 , G06V40/16 , H04N23/74 , H04N23/56 , H04N23/71 , H04N5/33 , G06T7/586 , H04N23/69
CPC classification number: G03B15/05 , G06T7/586 , G06V10/141 , G06V10/147 , G06V20/10 , G06V20/64 , G06V40/166 , G06V40/172 , H04N5/33 , H04N23/56 , H04N23/71 , H04N23/74 , G03B2215/0567 , H04N23/69
Abstract: A method according to embodiments of the invention includes creating a three-dimensional profile of a scene, calculating a relative amount of light for each portion of the scene based on the three-dimensional profile, and activating a light source to provide a first amount of light to a first portion of the scene, and a second amount of light to a second portion of the scene. The first amount and the second amount are different. The first amount and the second amount are determined by calculating a relative amount of light for each portion of the scene.
-
Patent Agency Ranking
6.发明公开公开(公告)号：US20230326058A1
公开(公告)日：2023-10-12
申请号：US18331203
申请日：2023-06-08
Applicant: ELBIT SYSTEMS LTD.
Inventor： Yoav OPHIR
CPC classification number: G06T7/586 , G06T11/00 , G06T2207/20092 , G06T2207/10048
Abstract: A method and system for providing depth perception to a two-dimensional (2D) representation of a given three-dimensional (3D) object within a 2D non-visible spectrum image of a scene is provided. The method comprises: capturing the 2D non-visible spectrum image at a capture time, by at least one non-visible spectrum sensor; obtaining 3D data regarding the given 3D object independently of the 2D non-visible spectrum image; generating one or more depth cues based on the 3D data; applying the depth cues on the 2D representation to generate a depth perception image that provides the depth perception to the 2D representation; and displaying the depth perception image.
-
7.发明公开公开(公告)号：US20230298358A1
公开(公告)日：2023-09-21
申请号：US18036011
申请日：2021-11-09
Applicant: BRIGHTWAY VISION LTD
Inventor： Eyal Yaakob LEVI , Ofer Bruce DAVID
CPC classification number: G06V20/58 , H04N23/56 , G06T7/586 , G06T7/507 , G06V10/25 , G06T2207/10028 , G06T2207/30261
Abstract: Embodiments pertain to a system that can be employed or that is included in a platform for detecting an obstacle to the platform in a scene. The system comprises, in an embodiment, a plurality of illuminators arranged at different locations of the platform; at least one imager; a processor; and a memory configured to store data and software code. The software code is executable by the processor to perform the following: illuminating the scene from at least two different directions by the plurality of illuminators; acquiring, by the at least one imager, a plurality of images of the illuminated scene; comparing at least one image of the scene illuminated from a first direction with at least one image of the scene illuminated from a second direction which is different from the first direction; and determining, based on the comparing, at least one shadow-related characteristic of the scene.
-
公开(公告)号：US11763474B2
公开(公告)日：2023-09-19
申请号：US17443757
申请日：2021-07-27
Inventor： Feilong Yan , Jin Fang , Tongtong Zhao , Chi Zhang , Liang Wang , Yu Ma , Ruigang Yang
CPC classification number: G06T7/521 , G06T7/586 , G06T7/73 , G06V20/58 , G06T2207/10028
Abstract: A method for generating simulated point cloud data, a device, and a storage medium includes: acquiring at least one frame of point cloud data collected by a road collecting device in an actual environment without a dynamic obstacle as static scene point cloud data; setting, least one dynamic obstacle in a coordinate system matching the static scene point cloud data; simulating in the coordinate system, a plurality of simulated scanning lights emitted by a virtual scanner located at an origin of the coordinate system; updating the static scene point cloud data according to intersections of the plurality of simulated scanning lights and the at least one dynamic obstacle to obtain the simulated point cloud data comprising point cloud data of the dynamic obstacle; and at least one of adding a set noise to the simulated point cloud data, and, deleting point cloud data corresponding to the dynamic obstacle according to a set ratio.
-
公开(公告)号：US20230186502A1
公开(公告)日：2023-06-15
申请号：US18164940
申请日：2023-02-06
Applicant: Nanotronics Imaging, Inc.
Inventor： Matthew C. Putman , Vadim Pinskiy , Tanaporn Na Narong , Denis Sharoukhov , Tonislav Ivanov
CPC classification number: G06T7/586 , G06N3/08 , G06N3/04 , G02B21/367 , H04N23/56 , G06T2207/10152 , G06T2207/20081 , G06T2207/10056 , G06T2207/20084
Abstract: An imaging system is disclosed herein. The imaging system includes an imaging apparatus and a computing system. The imaging apparatus includes a plurality of light sources positioned at a plurality of positions and a plurality of angles relative to a stage configured to support a specimen. The imaging apparatus is configured to capture a plurality of images of a surface of the specimen. The computing system in communication with the imaging apparatus. The computing system configured to generate a 3D-reconstruction of the surface of the specimen by receiving, from the imaging apparatus, the plurality of images of the surface of the specimen, generating, by the imaging apparatus via a deep learning model, a height map of the surface of the specimen based on the plurality of images, and outputting a 3D-reconstruction of the surface of the specimen based on the height map generated by the deep learning model.
-
公开(公告)号：US11657495B2
公开(公告)日：2023-05-23
申请号：US17485638
申请日：2021-09-27
Applicant: HIVE VISION CO., LTD.
Inventor： In Soo Kweon , Yeo Hak Yoon , Ung Jun Chun , Su Yeol Park
CPC classification number: G06T7/0006 , G06T5/40 , G06T7/33 , G06T7/35 , G06T7/44 , G06T7/586 , G06T7/60 , G06V30/19073 , G06T2207/10152 , G06T2207/30164
Abstract: A non-Lambertian surface inspection system for line scan is proposed. Such a system includes: a surface inspection part including a frame provided with a curved mounting hole formed on at least one of one surface and the other surface thereof and a photographing hole formed at an upper end thereof, and a plurality of first and second illumination modules installed in the mounting hole and output light in oblique lines toward an inspection object placed on a bottom surface thereof; a camera positioned above the photographing hole to photograph the inspection object positioned on the bottom surface through the photographing hole and receive an entire reception image including first and second illumination images; and a controller to control operation of the camera, selectively operate the first illumination module and the second illumination module, and extract the first illumination image and the second illumination image.
-
-
-
-
-
-
-
-
-
Search Results
360
records
(took 0.025 seconds)
