公开(公告)号：US20240233331A1

公开(公告)日：2024-07-11

申请号：US18542408

申请日：2023-12-15

Applicant: QUALCOMM Incorporated

Inventor： Avdhut JOSHI ,  Sajal MAHESHWARI ,  Ahmed Kamel SADEK

IPC: G06V10/764 ,  G06V10/82 ,  G06V20/58

CPC classification number: G06V10/764 ,  G06V10/82 ,  G06V20/58

Abstract: Disclosed are systems, apparatuses, processes, and computer-readable media for processing image data. For example, an apparatus can compute initial embeddings from a plurality of images. The apparatus can construct a graph comprising nodes representing the initial embeddings. The apparatus can further perform, based on the graph, a plurality of message passing steps successively to generate final embeddings. The apparatus can classify, using a classification engine, one or more objects in each of the plurality of images based on the final embeddings. The apparatus can further compute a classification loss based on the classifying of the one or more objects.

公开(公告)号：US20240144416A1

公开(公告)日：2024-05-02

申请号：US18477893

申请日：2023-09-29

Applicant: QUALCOMM Incorporated

Inventor： Makesh Pravin JOHN WILSON ,  Radhika Dilip GOWAIKAR ,  Volodimir SLOBODYANYUK ,  Avdhut JOSHI ,  James POPLAWSKI

IPC: G06T3/00 ,  G06N20/00 ,  G06T7/11 ,  G08G1/04

CPC classification number: G06T3/00 ,  G06N20/00 ,  G06T7/11 ,  G08G1/04 ,  G06T2207/20081 ,  G06T2207/30236

Abstract: An occupancy grid determination method includes: determining a predicted occupancy grid based on a previous occupancy grid, the predicted occupancy grid comprising a plurality of first cells corresponding to sub-regions of a region, each of the plurality of first cells including a plurality of predicted indications of probability each indicative of a predicted probability of a respective possible type of occupier of the respective first cell; determining, using machine learning and based on the first sensor measurements, an observed occupancy grid comprising a plurality of second cells corresponding to the sub-regions of the region; and determining an updated occupancy grid based on the observed occupancy grid and the predicted occupancy grid.

公开(公告)号：US20240101158A1

公开(公告)日：2024-03-28

申请号：US18336840

申请日：2023-06-16

Applicant: QUALCOMM Incorporated

Inventor： Shivam AGARWAL ,  Avdhut JOSHI ,  Jayakrishnan UNNIKRISHNAN ,  Yoga Y NADARAAJAN ,  Sree Sesha Aravind VADREVU ,  Gautam SACHDEVA

IPC: B60W60/00

CPC classification number: B60W60/0027 ,  B60W2420/42 ,  B60W2554/4041

Abstract: Systems and techniques are described herein for determining at least one location of at least one target vehicle relative to a lane. For instance, a method for determining at least one location of at least one target vehicle relative to a lane is provided. The method may include obtaining a position of a target vehicle within an image; obtaining one or more positions of a lane boundary within the image; determining a distance between the target vehicle and the lane boundary based on the position of the target vehicle within the image and the one or more positions of the lane boundary within the image; and adjusting a position of the target vehicle in a map based on the distance between the target vehicle and the lane boundary and a position of the lane boundary in the map

公开(公告)号：US20230162597A1

公开(公告)日：2023-05-25

申请号：US17455853

申请日：2021-11-19

Applicant: QUALCOMM Incorporated

Inventor： Gopi Krishna TUMMALA ,  Tianqi YE ,  Avdhut JOSHI ,  Monu SURANA

IPC: G08G1/01 ,  H04W4/40 ,  B60W40/04 ,  B60W30/00

CPC classification number: G08G1/0125 ,  H04W4/40 ,  B60W40/04 ,  B60W30/00 ,  B60W2556/45 ,  B60W2556/10

Abstract: Various embodiments include methods and systems for managing vehicle behavior. In some embodiments, a vehicle processor of the first vehicle may receive dynamic traffic flow feature information relevant to movements of a second vehicle within a predetermined proximity to the host vehicle, determine probabilities of a plurality of potential behaviors of the second vehicle based on the received dynamic traffic flow feature information, predict a future path of the second vehicle, and use the predicted future path of the second vehicle in a vehicle control function. In some embodiments, the vehicle processor of the first vehicle may predict a behavior of a third vehicle based on received intention information about the second vehicle, and may adjust a behavior of the first vehicle based on the predicted behavior of the third vehicle.

公开(公告)号：US20230023126A1

公开(公告)日：2023-01-26

申请号：US17812340

申请日：2022-07-13

Applicant: QUALCOMM Incorporated

Inventor： Amin ANSARI ,  Avdhut JOSHI ,  Gautam SACHDEVA ,  Ahmed Kamel SADEX

IPC: G06T7/521 ,  G06T7/70

Abstract: Certain aspects of the present disclosure provide techniques for machine learning. A depth output from a depth model is generated based on an input image frame. A depth loss for the depth model is determined based on the depth output and an estimated ground truth for the input image frame, the estimated ground truth comprising estimated depths for a set of pixels of the input image frame. A total loss for the depth model is determined based at least in part on the depth loss. The depth model is updated based on the total loss, and a new depth output, generated using the updated depth model, is output.

公开(公告)号：US20210209785A1

公开(公告)日：2021-07-08

申请号：US17142199

申请日：2021-01-05

Applicant: QUALCOMM Incorporated

Inventor： Jayakrishnan UNNIKRISHNAN ,  Avdhut JOSHI ,  Shivam AGARWAL ,  Yoga Y NADARAAJAN ,  Amir SALIMI ,  Urs NIESEN ,  Sree Sesha Aravind VADREVU ,  Gautam SACHDEVA

IPC: G06T7/62 ,  G06T7/73 ,  G01S13/06 ,  G01S13/89

Abstract: Techniques and systems are provided for determining one or more sizes of one or more objects. For example, a bounding region identifying a first object detected in an image can be obtained. A map including map points can also be obtained. The map points correspond to one or more reference locations in a three-dimensional space. The bounding region identifying the first object can be associated with at least one map point of the map points included in the map. Using the bounding region and the at least one map point, an estimated three-dimensional position and an estimated size of the first object detected in the image can be determined. In some examples, other information can be used to estimate the estimated three-dimensional position and an estimated size of the first object, such as radar information and/or other information.