公开(公告)号：US20230206613A1

公开(公告)日：2023-06-29

申请号：US17561299

申请日：2021-12-23

Applicant: QUALCOMM INCORPORATED

Inventor： Upal MAHBUB ,  Gokce DANE

IPC: G06V10/82 ,  G06V10/25 ,  G06V10/72 ,  G06V10/764

CPC classification number: G06V10/82 ,  G06V10/25 ,  G06V10/72 ,  G06V10/764 ,  G06V40/107

Abstract: Methods, systems, and apparatuses are provided to automatically detect objects within images. For example, an image capture device may capture an image, and may apply a trained neural network to the image to generate an object value and a class value for each of a plurality of portions of the image. Further, the image capture device may determine, for each of the plurality of image portions, a confidence value based on the object value and the class value corresponding to each image portion. The image capture device may also detect an object within at least one image portion based on the confidence values. Further, the image capture device may output a bounding box corresponding to the at least one image portion. The bounding box defines an area of the image that includes one or more objects.

公开(公告)号：US20230080803A1

公开(公告)日：2023-03-16

申请号：US17476283

申请日：2021-09-15

Applicant: QUALCOMM Incorporated

Inventor： Wesley James HOLLAND ,  Micha GALOR GLUSKIN ,  Venkata Ravi Kiran DAYANA ,  Upal MAHBUB ,  Scott BARKER

IPC: H04N5/232 ,  G06T3/40

Abstract: Systems and techniques are provided for processing one or more frames. For example, a process can include obtaining a first plurality of frames associated with a first settings domain from an image capture system, wherein the first plurality of frames is captured prior to obtaining a capture input. The process can include obtaining a reference frame associated with a second settings domain from the image capture system, wherein the reference frame is captured proximate to obtaining the capture input. The process can include obtaining a second plurality of frames associated with the second settings domain from the image capture system, wherein the second plurality of frames is captured after the reference frame. The process can include, based on the reference frame, transforming at least a portion of the first plurality of frames to generate a transformed plurality of frames associated with the second settings domain.

公开(公告)号：US20220277489A1

公开(公告)日：2022-09-01

申请号：US17189105

申请日：2021-03-01

Applicant: QUALCOMM Incorporated

Inventor： Ashar ALI ,  Gokce DANE ,  Upal MAHBUB ,  Samuel SUNARJO ,  Gerhard REITMAYR

IPC: G06T7/00 ,  G06T7/80 ,  G06T17/20 ,  G06N3/08

Abstract: Systems and techniques are provided for modeling three-dimensional (3D) meshes using images. An example method can include receiving, via a neural network system, an image of a target and metadata associated with the image and/or a device that captured the image; determining, based on the image and metadata, first 3D mesh parameters of a first 3D mesh of the target, the first 3D mesh parameters and first 3D mesh corresponding to a first reference frame associated with the image and/or the device; and determining, based on the first 3D mesh parameters, second 3D mesh parameters for a second 3D mesh of the target, the second 3D mesh parameters and second 3D mesh corresponding to a second reference frame, the second reference frame including a 3D coordinate system of a real-world scene where the target is located.

公开(公告)号：US20220076059A1

公开(公告)日：2022-03-10

申请号：US17455883

申请日：2021-11-19

Applicant: QUALCOMM Incorporated

Inventor： Upal MAHBUB ,  Rakesh NATTOJI RAJARAM ,  Vasudev BHASKARAN

IPC: G06K9/62 ,  G06N3/04 ,  G06K9/00 ,  G06T7/11 ,  G06T5/00

Abstract: Embodiments include systems and methods that may be performed by a processor of a computing device. Embodiments may be applied for keypoint detection in an image. In embodiments, the processor of the computing device may apply to an image a first-stage neural network to define and output a plurality of regions, apply to each of the plurality of regions a respective second-stage neural network to output a plurality of keypoints in each of the plurality of regions, and apply to the plurality of keypoints a third-stage neural network to determine a correction for each of the plurality of keypoints to provide corrected keypoints.