公开(公告)号：US11797022B1

公开(公告)日：2023-10-24

申请号：US17305013

申请日：2021-06-29

Applicant: AMAZON TECHNOLOGIES, INC.

Inventor： James Ballantyne ,  Eric Foxlin ,  Lu Xia ,  Simon Edwards-Parton ,  Boshen Niu ,  Harish Annavajjala

IPC: G05D1/00 ,  G05D1/02 ,  G06T7/593 ,  G06T7/12 ,  G06T7/521 ,  G06T7/13

CPC classification number: G05D1/0251 ,  G05D1/0088 ,  G05D1/0214 ,  G06T7/12 ,  G06T7/13 ,  G06T7/521 ,  G06T7/593 ,  G06T2207/10012 ,  G06T2207/10028 ,  G06T2207/30261

Abstract: An autonomous mobile device (AMD) may move around a physical space while performing tasks. Sensor data is used to determine an occupancy map of the physical space. Some objects within the physical space may be difficult to detect because of characteristics that result in lower confidence in sensor data, such as transparent or reflective objects. To include difficult-to-detect objects in the occupancy map, image data is processed to identify portions of the image that includes features associated with difficult-to-detect objects. Given the portion that possibly includes difficult-to-detect objects, the AMD attempts to determine where in the physical space that portion corresponds to. For example, the AMD may use stereovision to determine the physical area associated with the features depicted in the portion. Objects in that area are included in an occupancy map annotated as objects that should persist unless confirmed to not be within the physical space.

公开(公告)号：US11785196B2

公开(公告)日：2023-10-10

申请号：US17487985

申请日：2021-09-28

Applicant: Johnson Controls Tyco IP Holdings LLP

Inventor： Stuart Boyle

IPC: H04N13/111 ,  G06T7/593 ,  G06T7/70 ,  H04N13/122 ,  G06V20/64 ,  G06V40/16 ,  G06V20/40 ,  G06T17/20 ,  H04N13/00

CPC classification number: H04N13/111 ,  G06T7/593 ,  G06T7/70 ,  G06T17/20 ,  G06V20/41 ,  G06V20/64 ,  G06V40/173 ,  H04N13/122 ,  G06T2207/20081 ,  G06V20/44 ,  H04N2013/0081 ,  H04N2213/002

Abstract: Apparatus and methods for enhanced 3D visualization includes receiving a plurality of images of an image scene from a plurality of image sensors. Depth information at locations of the image scene is received from a plurality of depth sensors. The depth information is combined with the plurality of images of the image scene using a machine learning model. A 3D representation of the image scene is generated based on the combined depth and image information.

公开(公告)号：US20230316740A1

公开(公告)日：2023-10-05

申请号：US17710503

申请日：2022-03-31

Applicant: Wing Aviation LLC

Inventor： Ali Shoeb

IPC: G06V20/17 ,  G06V20/10 ,  G06V10/75 ,  G06T7/593 ,  G05D1/10 ,  G05D1/04 ,  B64C39/02 ,  G06N5/04

CPC classification number: G06V20/17 ,  G06V20/176 ,  G06V10/751 ,  G06T7/593 ,  G05D1/106 ,  G05D1/042 ,  B64C39/024 ,  G06N5/04 ,  G06T2207/10012 ,  G06T2207/10032 ,  G06T2207/20061 ,  G06T2207/30261 ,  B64C2201/127 ,  B64C2201/128 ,  B64C2201/141

Abstract: A computer-implemented method comprises receiving, by an image processing system, a depth image captured by a stereo camera on an unmanned aerial vehicle (UAV). One or more pixels of the depth image are associated with corresponding depth values indicative of distances of one or more objects to the stereo camera. The image processing system determines that one or more pixels of the depth image are associated with invalid depth values. The image processing system infers, based on a distribution of the one or more pixels of the depth image that are associated with invalid depth values, a presence of a potential obstacle in an environment of the UAV. The UAV is controlled based on the inferred presence of the potential obstacle.

公开(公告)号：US11775614B2

公开(公告)日：2023-10-03

申请号：US17954903

申请日：2022-09-28

Applicant: Ambarella International LP

Inventor： Zhikan Yang

IPC: G06V10/00 ,  G06F18/21 ,  G06T7/285 ,  G06T7/593 ,  G06N3/088 ,  G06V10/88 ,  G06V10/46 ,  G06F18/214 ,  G06F18/241 ,  G06N3/045

CPC classification number: G06F18/2193 ,  G06F18/214 ,  G06F18/2155 ,  G06F18/241 ,  G06N3/045 ,  G06N3/088 ,  G06T7/285 ,  G06T7/593 ,  G06V10/462 ,  G06V10/88 ,  G06T2207/10021 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: An apparatus includes an interface and a processor. The interface may be configured to receive pixel data from a capture device. The processor may be configured to (i) process the pixel data arranged as one or more video frames, (ii) extract features from the one or more video frames, (iii) generate fused maps for at least one of disparity and optical flow in response to the features extracted, (iv) generate regenerated image frames by performing warping on a first subset of the video frames based on (a) the fused maps and (b) first parameters, (v) perform a classification of a sample image frame based on second parameters, and (vi) update the first parameters and the second parameters in response to whether the classification is correct. The classification generally comprises indicating whether the sample image frame is one of a second subset of the video frames or one of the regenerated image frames.

公开(公告)号：US20230306622A1

公开(公告)日：2023-09-28

申请号：US17656605

申请日：2022-03-25

Applicant: Adobe Inc.

Inventor： Jianming Zhang

IPC: G06T7/593 ,  G06N20/00 ,  G06F17/11

CPC classification number: G06T7/593 ,  G06N20/00 ,  G06F17/11

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for training and/or implementing machine learning models utilizing compressed log scene measurement maps. For example, the disclosed system generates compressed log scene measurement maps by converting scene measurement maps to compressed log scene measurement maps by applying a logarithmic function. In particular, the disclosed system uses scene measurement distribution metrics from a digital image to determine a base for the logarithmic function. In this way, the compressed log scene measurement maps normalize ranges within a digital image and accurately differentiates between scene elements objects at a variety of depths. Moreover, for training, the disclosed system generates a predicted scene measurement map via a machine learning model and compares the predicted scene measurement map with a compressed log ground truth map. By doing so, the disclosed system trains the machine learning model to generate accurate compressed log depth maps.

公开(公告)号：US20230298192A1

公开(公告)日：2023-09-21

申请号：US18012861

申请日：2021-06-24

Applicant: GIDEON BROTHERS LTD.

Inventor： Nikola Banic ,  Kruno Lenac ,  Dario Ljubic ,  Luka Pevec

IPC: G06T7/593

CPC classification number: G06T7/593 ,  G06T2207/20084 ,  G06T2207/20081 ,  G06T2207/10012

Abstract: In a method for subpixel disparity calculation, image data for various images each representing a field of view of an input device is received by a processor, and the image data is applied to a machine learning model. The machine learning module uses the image data to compute an output representing calculated subpixel disparity between the various images. In an example of the method, the machine learning model is a neural network that produces accurate and reliable subpixel disparity estimation in real-time using synthetically generated data.

公开(公告)号：US11758109B2

公开(公告)日：2023-09-12

申请号：US17164679

申请日：2021-02-01

Applicant: OMNIVISION TECHNOLOGIES, INC.

Inventor： Wenshou Chen ,  Yiyi Ren ,  Guansong Liu ,  Badri Padmanabhan ,  Alireza Bonakdar ,  Richard Mann

IPC: H04N13/218 ,  G06T7/593 ,  H04N23/55 ,  H04N13/00

CPC classification number: H04N13/218 ,  G06T7/593 ,  H04N23/55 ,  G06T2207/10012 ,  H04N2013/0081

Abstract: In some embodiments, an image sensor is provided. The image sensor comprises a plurality of photodiodes arranged as a photodiode array. The photodiodes of the photodiode array are arranged into a first quadrant, a second quadrant, a third quadrant, and a fourth quadrant. A first polarization filter and a first telecentric lens are aligned with the first quadrant. A second polarization filter and a second telecentric lens are aligned with the second quadrant. A third polarization filter and a third telecentric lens are aligned with the third quadrant. A fourth telecentric lens is aligned with the fourth quadrant.

公开(公告)号：US20230281852A1

公开(公告)日：2023-09-07

申请号：US17684580

申请日：2022-03-02

Applicant: Volvo Car Corporation

Inventor： Sihao Ding ,  Jianhe Yuan

IPC: G06T7/593 ,  G06V20/56 ,  G06V10/774

CPC classification number: G06T7/593 ,  G06V10/774 ,  G06V20/56 ,  B60W60/001 ,  G06T2207/10021 ,  G06T2207/10028 ,  G06T2207/20081 ,  G06T2207/20228 ,  G06T2207/30252

Abstract: Methods and systems for unsupervised depth estimation for fisheye cameras using spatial-temporal (and, optionally, modal) consistency. This unsupervised depth estimation works directly on raw, distorted stereo fisheye images, such as those obtained from the four fisheye camera disposed around a vehicle in rigid alignment. Temporal consistency involves training a depth estimation model using a sequence of frames as input, while spatial consistency involves training the depth estimation model using overlapping images from synchronized stereo camera pairs. Images from different stereo camera pairs can also be used at different times. Modal consistency, when applied, dictates that different sensor types (e.g., camera, lidar, etc.) must also agree. The methods and systems of the present disclosure utilize a fisheye camera projection model that projects a disparity map into a point cloud map, which aides in the rectification of stereo pairs.

公开(公告)号：US20230274454A1

公开(公告)日：2023-08-31

申请号：US18019697

申请日：2020-08-03

Applicant: Hewlett-Packard Development Company, L.P.

Inventor： Stephen Bernard Pollard ,  Fraser John Dickin ,  Guy de Warrenne Bruce Adams ,  Faisal Azhar

IPC: G06T7/593 ,  G01B11/25

CPC classification number: G06T7/593 ,  G01B11/2504 ,  G01B11/2522 ,  G06T2207/10028

Abstract: Disclosed herein are methods, apparatus, and computer program code for determining a correcting mapping, comprising: locating a test object having a known linear dimension at a plurality of positions within a volume; at each of the plurality of positions, capturing a three-dimensional scan of the test object using a three-dimensional imaging device; and determining a difference between the known linear dimension and the linear dimension as obtained from the captured scan; and determining a correction mapping for the volume based on the determined differences, the correction mapping indicating variation from an expected location of the location as captured by the imaging device.

公开(公告)号：US20230274450A1

公开(公告)日：2023-08-31

申请号：US18143524

申请日：2023-05-04

Applicant: Purdue Research Foundation

Inventor： Jie Shan ,  Xiangxi Tian

IPC: G06T7/41 ,  G06T7/593

CPC classification number: G06T7/41 ,  G06T7/593 ,  G06T2207/20021 ,  G06T2207/10028 ,  G06T2207/10021

Abstract: A method of determining macrotexture of an object is disclosed which includes obtaining a plurality of stereo images from an object by an imaging device, generating a coordinate system for each image of the plurality of stereo images, detecting one or more keypoints each having a coordinate in each image of the plurality of stereo images, wherein the coordinate system is based on a plurality of ground control points (GCPs) with apriori position knowledge of each of the plurality of GCPs, generating a sparse point cloud based on the one or more keypoints, reconstructing a 3D dense point cloud of the object based on the generated sparse point cloud and based on neighboring pixels of each of the one or more keypoints and calculating the coordinates of each pixel of the 3D dense point cloud, and obtaining the macrotexture based on the reconstructed 3D dense point cloud of the object.