公开(公告)号：US20240153249A1

公开(公告)日：2024-05-09

申请号：US18467455

申请日：2023-09-14

申请人： QUALCOMM Incorporated

发明人： Shubhankar Mangesh Borse ,  Marvin Richard Klingner ,  Varun Ravi Kumar ,  Senthil Kumar Yogamani ,  Fatih Murat Porikli

IPC分类号： G06V10/774 ,  G06V10/26 ,  G06V10/40 ,  G06V10/80 ,  G06V20/56

CPC分类号： G06V10/774 ,  G06V10/26 ,  G06V10/40 ,  G06V10/803 ,  G06V20/56

摘要： This disclosure provides systems, methods, and devices for image signal processing that support training object recognition models. In a first aspect, a method of image processing includes training a first modality imaging system; receiving time-synchronized first input data samples and second input data samples from the first modality imaging system and a second modality imaging system, respectively; processing the first input data samples in the first modality imaging system to generate first output; processing the second input data samples in the second modality imaging system to generate second output; and training the second modality imaging system based on the first output and the second output. Other aspects and features are also claimed and described.

公开(公告)号：US11941822B2

公开(公告)日：2024-03-26

申请号：US18180730

申请日：2023-03-08

申请人： QUALCOMM Incorporated

发明人： Jamie Menjay Lin ,  Fatih Murat Porikli

IPC分类号： G06T7/246 ,  G06F18/24 ,  G06T7/73

CPC分类号： G06T7/248 ,  G06F18/24 ,  G06T7/74 ,  G06T2207/10016

摘要： Systems and techniques are described herein for performing optical flow estimation for one or more frames. For example, a process can include determining an optical flow prediction associated with a plurality of frames. The process can include determining a position of at least one feature associated with a first frame and determining, based on the position of the at least one feature in the first frame and the optical flow prediction, a position estimate of a search area for searching for the at least one feature in a second frame. The process can include determining, from within the search area, a position of the at least one feature in the second frame.

公开(公告)号：US20220383114A1

公开(公告)日：2022-12-01

申请号：US17804842

申请日：2022-05-31

申请人： Qualcomm Incorporated

发明人： Farhad Ghazvinian Zanjani ,  Ilia Karmanov ,  Daniel Hendricus Franciscus Dijkman ,  Hanno Ackermann ,  Simone Merlin ,  Brian Michael Buesker ,  Ishaque Ashar Kadampot ,  Fatih Murat Porikli ,  Max Welling

IPC分类号： G06N3/08

摘要： Certain aspects of the present disclosure provide techniques for training and inferencing with machine learning localization models. In one aspect, a method, includes training a machine learning model based on input data for performing localization of an object in a target space, including: determining parameters of a neural network configured to map samples in an input space based on the input data to samples in an intrinsic space; and determining parameters of a coupling matrix configured to transport the samples in the intrinsic space to the target space.

公开(公告)号：US20220299649A1

公开(公告)日：2022-09-22

申请号：US17249967

申请日：2021-03-19

申请人： QUALCOMM Incorporated

发明人： Manoj Bhat ,  Shizhong Steve Han ,  Fatih Murat Porikli

IPC分类号： G01S17/931 ,  G01S7/481 ,  G01S7/48 ,  G01S17/06

摘要： In some aspects, a device may obtain point data from a lidar scanner. The point data may be associated with an angular subrange of a polar grid of the lidar scanner. The device may cause a transformer model to process the point data to identify a set of points based at least in part on the angular subrange, analyze the set of points based at least in part on a polar distance between the set of points and an origin of the polar grid, and indicate whether the set of points is associated with an object. The device may perform an action based at least in part on whether the transformer model indicates that the set of points is associated with the object. Numerous other aspects are described.