公开(公告)号：US20250065907A1

公开(公告)日：2025-02-27

申请号：US18456218

申请日：2023-08-25

Applicant: QUALCOMM Incorporated

Inventor： Venkatraman NARAYANAN ,  Varun RAVI KUMAR ,  Senthil Kumar YOGAMANI

IPC: B60W60/00 ,  G06N3/08

Abstract: Certain aspects of the present disclosure provide techniques and apparatus for improved machine learning. A set of object detections, each respective object detection in the set of object detections corresponding to a respective object detected in an environment, is accessed. Based on the set of object detections, a graph representation comprising a plurality of nodes is generated, where each respective node in the plurality of nodes corresponds to a respective object detection in the set of object detections. A set of output features is generated based on processing the graph representation using a trained message passing network. A predicted object relationship graph is generated based on processing the set of output features using a layer of a trained machine learning model.

公开(公告)号：US20250131742A1

公开(公告)日：2025-04-24

申请号：US18492617

申请日：2023-10-23

Applicant: QUALCOMM Incorporated

Inventor： Varun RAVI KUMAR ,  Senthil Kumar YOGAMANI ,  Heesoo MYEONG

IPC: G06V20/56 ,  G06V10/26 ,  G06V10/764 ,  G06V10/82

Abstract: Aspects presented herein may improve the accuracy and reliability of object detections performed by multiple object detection models. In one aspect, a UE detects (1) a set of polylines from at least one of a set of bird's eye view (BEV) features or a set of perspective view (PV) features associated with a set of images and (2) a set of three-dimensional (3D) objects in the set of BEV features. The UE associates the set of polylines with the set of 3D objects. The UE updates the set of polylines based on a set of nearby 3D objects or updates the set of 3D objects based on a set of nearby polylines. The UE outputs an indication of the updated set of polylines or the updated set of 3D objects.

公开(公告)号：US20240070541A1

公开(公告)日：2024-02-29

申请号：US18365664

申请日：2023-08-04

Applicant: QUALCOMM Incorporated

Inventor： Shubhankar Mangesh BORSE ,  Varun RAVI KUMAR ,  David UNGER ,  Senthil Kumar YOGAMANI ,  Fatih Murat PORIKLI

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: Techniques and systems are provided for training a machine learning (ML) model. A technique can include generating a first set of features for objects in images, predicting image feature labels for the first set of features, comparing the predicted image feature labels to ground truth image feature labels to evaluate a first loss function, perform a perspective transform on the first set of features to generate a birds eye view (BEV) projected image features, combining the BEV projected image features and a first set of flattened features to generate combined image features, generating a segmented BEV map of the environment based on the combined image features, comparing the segmented BEV map to a ground truth segmented BEV map to evaluate a second loss function, and training the ML model for generation of segmented BEV maps based on the evaluated first loss function and the evaluated second loss function.

公开(公告)号：US20250095168A1

公开(公告)日：2025-03-20

申请号：US18468637

申请日：2023-09-15

Applicant: QUALCOMM Incorporated

Inventor： Julia KABALAR ,  Kiran BANGALORE RAVI ,  Nirnai ACH ,  Mireille Lucette Laure GREGOIRE ,  Varun RAVI KUMAR ,  Senthil Kumar YOGAMANI

IPC: G06T7/33 ,  G01S17/89 ,  G06V20/56 ,  G06V20/58

Abstract: Systems and techniques are described herein for processing data. For instance, a method for processing data is provided. The method may include obtaining source features generated based on first sensor data captured using a first set of sensors; obtaining source semantic attributes related to the source features; obtaining target features generated based on second sensor data captured using a second set of sensors; obtaining map information; obtaining location information of a device comprising the second set of sensors; obtaining target semantic attributes from the map information based on the location information; aligning the target features with a set of the source features, based on the source semantic attributes and the target semantic attributes, to generate aligned target features; and processing the aligned target features to generate an output.

公开(公告)号：US20250035448A1

公开(公告)日：2025-01-30

申请号：US18360615

申请日：2023-07-27

Applicant: QUALCOMM Incorporated

Inventor： Heesoo MYEONG ,  Senthil Kumar YOGAMANI ,  Varun RAVI KUMAR

IPC: G01C21/32

Abstract: Disclosed are techniques for localization of an object. For example, a device can generate, based on sensor data obtained from sensor(s) associated with an object, a predicted map comprising predicted nodes associated with a predicted location of the object within an environment. The device can receive a high definition (HD) map comprising HD nodes associated with a HD location of the object within the environment. The device can further match the predicted nodes with the HD nodes to determine pair(s) of matched nodes between the predicted map and the HD map. The device can determine, based on a comparison between nodes in each pair of the pair(s) of matched nodes, a respective node score for each pair of the pair(s) of matched nodes. The device can determine, based on the respective node score for each pair of the pair(s) of matched nodes, a location of the object within the environment.

公开(公告)号：US20250031089A1

公开(公告)日：2025-01-23

申请号：US18357014

申请日：2023-07-21

Applicant: QUALCOMM Incorporated

Inventor： Ming-Yuan YU ,  Senthil Kumar YOGAMANI ,  Varun RAVI KUMAR

IPC: H04W28/02

Abstract: Aspects presented herein may enable a UE to detect and identify a weather condition of an environment based on the sparsity of FFT/DWT coefficients derived from a set of range images associated with the environment. In one aspect, a UE converts a set of point clouds associated with an environment to a set of range images based on a spherical projection. The UE applies at least one of FFT or DWT to the set of range images to obtain a set of FFT coefficients or a set of DWT coefficients. The UE identifies a level of a condition for the environment based on a sparsity of the set of FFT coefficients or the set of DWT coefficients.

公开(公告)号：US20250094535A1

公开(公告)日：2025-03-20

申请号：US18469424

申请日：2023-09-18

Applicant: QUALCOMM Incorporated

Inventor： Shivansh RAO ,  Sweta PRIYADARSHI ,  Varun RAVI KUMAR ,  Senthil Kumar YOGAMANI ,  Arunkumar NEHRUR RAVI ,  Vasudev BHASKARAN

IPC: G06F18/213 ,  H04W4/38 ,  H04W4/46

Abstract: According to aspects described herein, a device can extract first features from frames of first sensor data and second features from frames of second sensor data (captured after the first sensor data). The device can obtain first weighted features based on the first features and second weighted features based on the second features. The device can aggregate the first weighted features to determine a first feature vector and the second weighted features to determine a second feature vector. The device can obtain a first transformed feature vector (based on transforming the first feature vector into a coordinate space) and a second transformed feature vector (based on transforming the second feature vector into the coordinate space). The device can aggregate first transformed weighted features (based on the first transformed feature vector) and second transformed weighted features (based on the second transformed feature vector) to determine a fused feature vector.

公开(公告)号：US20240412534A1

公开(公告)日：2024-12-12

申请号：US18330203

申请日：2023-06-06

Applicant: QUALCOMM Incorporated

Inventor： Senthil Kumar YOGAMANI ,  Varun RAVI KUMAR ,  Deeksha DIXIT

IPC: G06V20/56 ,  B60W60/00 ,  G06V10/82 ,  G06V20/58

Abstract: Systems and techniques are described herein for determining road profiles. For instance, a method for determining a road profiles is provided. The method may include extracting image features from one or more images of an environment, wherein the environment includes a road; generating a segmentation mask based on the image features; determining a subset of the image features based on the segmentation mask; generating image-based three-dimensional features based on the subset of the image features; obtaining point-cloud-based three-dimensional features derived from a point cloud representative of the environment; combining the image-based three-dimensional features and the point-cloud-based three-dimensional features to generate combined three-dimensional features; and generating a road profile based on the combined three-dimensional features.

公开(公告)号：US20240312188A1

公开(公告)日：2024-09-19

申请号：US18186003

申请日：2023-03-17

Applicant: QUALCOMM Incorporated

Inventor： Venkatraman NARAYANAN ,  Varun RAVI KUMAR ,  Senthil Kumar YOGAMANI

IPC: G06V10/774 ,  G06T15/20 ,  G06T17/00 ,  G06V10/776 ,  G06V20/64

CPC classification number: G06V10/774 ,  G06T15/20 ,  G06T17/00 ,  G06V10/776 ,  G06V20/64 ,  G06T2210/56

Abstract: Systems and techniques are described herein for training an object-detection model. For instance, a method for training an object-detection model is provided. The method may include obtaining a light detection and ranging (LIDAR) capture; obtaining a first LIDAR-based representation of an object as captured from a first distance; obtaining a second LIDAR-based representation of the object as captured from a second distance; augmenting the LIDAR capture using the first LIDAR-based representation of the object and the second LIDAR-based representation of the object to generate an augmented LIDAR capture; and training a machine-learning object-detection model using the augmented LIDAR capture.

公开(公告)号：US20240428441A1

公开(公告)日：2024-12-26

申请号：US18339559

申请日：2023-06-22

Applicant: QUALCOMM Incorporated

Inventor： Balaji Shankar BALACHANDRAN ,  Varun RAVI KUMAR ,  Senthil Kumar YOGAMANI

IPC: G06T7/73 ,  G06T7/55

Abstract: In some aspects, a device may obtain, via a camera associated with the device, an image that includes one or more objects located within an area of the device. The device may generate a first three-dimensional output based at least in part on the image. The device may obtain, via an audio component associated with the device, an audio input associated with the one or more objects. The device may generate a second three-dimensional output based at least in part on the audio input. The device may detect the one or more objects based at least in part on the first three-dimensional output and the second three-dimensional output. Numerous other aspects are described.