公开(公告)号：US12299903B2

公开(公告)日：2025-05-13

申请号：US17929242

申请日：2022-09-01

Applicant: QUALCOMM Incorporated

Inventor： Louis Joseph Kerofsky ,  Geert Van Der Auwera ,  Marta Karczewicz ,  Kuan-Ting Shen ,  Dangdang Shao ,  Khalid Tahboub ,  Bing Han

IPC: H04N23/62 ,  G06T5/80 ,  G06T7/20 ,  G06T7/238 ,  G06T7/246 ,  G06T7/70 ,  G06T7/73 ,  G06T7/80 ,  B60R1/20 ,  B60R11/04 ,  G06T7/231 ,  G06V20/52 ,  G06V20/58

Abstract: Certain aspects of the present disclosure provide techniques for global motion modeling. Embodiments include receiving a first image and a second image from a camera attached to a moving object. Embodiments include identifying a pixel in the first image. Embodiments include determining, based on one or more parameters associated with the camera, a vector representing a range of locations in which a real-world point corresponding to the pixel is likely to be found in the second image, wherein the parameters associated with the camera comprise: a first parameter related to a location of the camera relative to a ground surface; a second parameter related to motion of the moving object; and a third parameter related to an orientation of the camera relative to the ground surface. Embodiments include determining, using the vector, a location of the real-world point in the second image.

公开(公告)号：US20250095379A1

公开(公告)日：2025-03-20

申请号：US18468399

申请日：2023-09-15

Applicant: QUALCOMM Incorporated

Inventor： Madhumitha Sakthi ,  Louis Joseph Kerofsky ,  Senthil Kumar Yogamani

IPC: G06V20/56 ,  B60W50/14 ,  G06T7/20 ,  G06T7/70 ,  G06V10/75

Abstract: This disclosure provides systems, methods, and devices for vehicle driving assistance systems that support image processing. In a first aspect, a method includes receiving a first image frame from the first camera and a second image frame from the second camera. The method may also include determining a first set of optical flows between the first image frame and the second image frame and determining a second set of optical flows based on the first set of optical flows and positions of the first camera and the second camera on the vehicle. Position data may be determined for objects in an area surrounding the vehicle based on the second set of optical flows. Other aspects and features are also claimed and described.

公开(公告)号：US12192311B2

公开(公告)日：2025-01-07

申请号：US17342249

申请日：2021-06-08

Applicant: QUALCOMM Incorporated

Inventor： Bappaditya Ray ,  Geert Van der Auwera ,  Adarsh Krishnan Ramasubramonian ,  Louis Joseph Kerofsky ,  Marta Karczewicz

IPC: G06T9/00 ,  H04L47/12 ,  H04L65/70 ,  H04L69/04 ,  H04N19/186 ,  H04N19/70

Abstract: An example method of encoding a point cloud includes determining that residual values for all components except one component of an attribute of a point in the point cloud are equal to zero; based on the determination that the residual values for all components except the one component of the attribute are equal to zero, determining a value for the one component that is equal to a magnitude of a residual value of the one component of the attribute minus an offset; encoding the value of the one component; and signaling the encoded value in a bitstream.

公开(公告)号：US12003768B2

公开(公告)日：2024-06-04

申请号：US17657867

申请日：2022-04-04

Applicant: QUALCOMM Incorporated

Inventor： Adarsh Krishnan Ramasubramonian ,  Luong Pham Van ,  Bappaditya Ray ,  Louis Joseph Kerofsky ,  Geert Van der Auwera ,  Marta Karczewicz

IPC: H04N19/597 ,  H04N19/105 ,  H04N19/124 ,  H04N19/136 ,  H04N19/156 ,  H04N19/184 ,  H04N19/30

CPC classification number: H04N19/597 ,  H04N19/105 ,  H04N19/124 ,  H04N19/136 ,  H04N19/156 ,  H04N19/184 ,  H04N19/30

Abstract: A method of decoding point cloud data comprises obtaining a bitstream that is encoded to comply with one or more constraints and decoding the bitstream, wherein decoding the bitstream comprises: determining a residual value of a first component of an attribute of a point; generating a predicted value of a second component of the attribute of the point; and reconstructing the second component as a sum of the predicted value of the second component and a multiplication product of a scale factor for the second component and the residual value of the first component, wherein the constraints include a constraint that limits the first component of the attribute of the point, the residual value of the first component of the attribute of the point, the second component of the attribute, and the residual value of the second component of the attribute of the point to one or more predefined bitdepths.

公开(公告)号：US11924428B2

公开(公告)日：2024-03-05

申请号：US17355904

申请日：2021-06-23

Applicant: QUALCOMM Incorporated

Inventor： Adarsh Krishnan Ramasubramonian ,  Louis Joseph Kerofsky ,  Bappaditya Ray ,  Geert Van der Auwera ,  Marta Karczewicz

IPC: H04N19/124 ,  H04N19/187 ,  H04N19/20 ,  H04N19/70

CPC classification number: H04N19/124 ,  H04N19/187 ,  H04N19/20 ,  H04N19/70

Abstract: A G-PCC encoder and G-PCC decoder may quantize and scale, respectively, a position of a child node. The G-PCC encoder may control the precision of the quantization and scaling using a quantization parameter (QP) value and a parameter value k, wherein the parameter value k specifies a number of QP points per doubling of a scaling step size to be used at the G-PCC decoder.

公开(公告)号：US20230379503A1

公开(公告)日：2023-11-23

申请号：US18362832

申请日：2023-07-31

Applicant: QUALCOMM Incorporated

Inventor： Adarsh Krishnan Ramasubramonian ,  Bappaditya Ray ,  Geert Van der Auwera ,  Louis Joseph Kerofsky ,  Marta Karczewicz

IPC: H04N19/70 ,  H04N19/119 ,  H04N19/597 ,  H04N19/136 ,  H04N19/174

CPC classification number: H04N19/70 ,  H04N19/119 ,  H04N19/597 ,  H04N19/136 ,  H04N19/174

Abstract: An example device for decoding point cloud data includes memory configured to store the point cloud data and one or more processors implemented in circuitry and coupled to the memory. The one or more processors are configured to determine dimensions of a region box and determine dimensions of a slice bounding box. The one or more processors are also configured to decode a slice of the point cloud data associated with the slice bounding box. The dimensions of the region box are constrained to not exceed the dimensions of the slice bounding box.

公开(公告)号：US11580672B2

公开(公告)日：2023-02-14

申请号：US17224709

申请日：2021-04-07

Applicant: QUALCOMM Incorporated

Inventor： Geert Van der Auwera ,  Louis Joseph Kerofsky ,  Bappaditya Ray ,  Adarsh Krishnan Ramasubramonian ,  Marta Karczewicz

IPC: G06T9/40

Abstract: A method of decoding point cloud data comprises obtaining a bitstream that includes an arithmetically encoded syntax element indicating a vertical point position offset within a node of a tree that represents 3-dimensional positions of points in a point cloud represented by the point cloud data; and decoding the vertical point position offset, wherein decoding the vertical point position offset comprises: determining a laser index of a laser candidate in a set of laser candidates, wherein the determined laser index indicates a laser beam that intersects the node; determining a context index based on whether the laser beam is above a first distance threshold, between the first distance threshold and a second distance threshold, between the second distance threshold and a third distance threshold, or below the third distance threshold; and arithmetically decoding a bin of the vertical point position offset using a context indicated by the determined context index.

公开(公告)号：US20210409714A1

公开(公告)日：2021-12-30

申请号：US17355904

申请日：2021-06-23

Applicant: QUALCOMM Incorporated

Inventor： Adarsh Krishnan Ramasubramonian ,  Louis Joseph Kerofsky ,  Bappaditya Ray ,  Geert Van der Auwera ,  Marta Karczewicz

IPC: H04N19/124 ,  H04N19/70 ,  H04N19/187 ,  H04N19/20

Abstract: A G-PCC encoder and G-PCC decoder may quantize and scale, respectively, a position of a child node. The G-PCC encoder may control the precision of the quantization and scaling using a quantization parameter (QP) value and a parameter value k, wherein the parameter value k specifies a number of QP points per doubling of a scaling step size to be used at the G-PCC decoder.

公开(公告)号：US20210327095A1

公开(公告)日：2021-10-21

申请号：US17224608

申请日：2021-04-07

Applicant: QUALCOMM Incorporated

Inventor： Geert Van der Auwera ,  Louis Joseph Kerofsky ,  Bappaditya Ray ,  Adarsh Krishnan Ramasubramonian ,  Marta Karczewicz

IPC: G06T9/00 ,  G06T9/40 ,  G06T17/20 ,  G01S17/89

Abstract: A method of decoding point cloud data comprises obtaining a bitstream that includes an arithmetically encoded syntax element indicating a vertical plane position of a planar mode of a node; and decoding the vertical plane position of the planar mode in the node, wherein decoding the vertical plane position of the planar mode comprises: determining a laser index of a laser candidate in a set of laser candidates, wherein the determined laser index indicates a laser beam that intersects the node; determining a context index based on whether the laser beam is above a first distance threshold, between the first distance threshold and a second distance threshold, between the second distance threshold and a third distance threshold, or below the third distance threshold; and arithmetically decoding the vertical plane position of the planar mode using a context indicated by the determined context index.

公开(公告)号：US20210326734A1

公开(公告)日：2021-10-21

申请号：US17224551

申请日：2021-04-07

Applicant: QUALCOMM Incorporated

Inventor： Geert Van der Auwera ,  Louis Joseph Kerofsky ,  Bappaditya Ray ,  Adarsh Krishnan Ramasubramonian ,  Marta Karczewicz

IPC: G06N7/00 ,  G06F7/48

Abstract: A method comprises obtaining a first laser angle; obtaining a second laser angle; obtaining a laser angle difference for a third laser angle; determining a predicted value based on the first laser angle and the second laser angle; and determining the third laser angle based on the predicted value and the laser angle difference for the third laser angle.