公开(公告)号：US20230162480A1

公开(公告)日：2023-05-25

申请号：US17535122

申请日：2021-11-24

Applicant: GM Global Technology Operations LLC

Inventor： Jordan B. Chipka ,  Wei Tong

IPC: G06V10/774 ,  G06V10/776 ,  G06V10/82 ,  G06V10/77 ,  G06V10/88 ,  G06N3/04 ,  G06N3/08

CPC classification number: G06V10/774 ,  G06N3/04 ,  G06N3/08 ,  G06V10/82 ,  G06V10/89 ,  G06V10/776 ,  G06V10/7715

Abstract: A system comprises a computer including a processor and a memory. The memory includes instructions such that the processor is programmed to: receive, at a neural network, frequency filtered spatial domain data, compare an output generated by the neural network to a loss function including a frequency-based feature consistency constraint, and update at least one weight of the neural network according to the loss function.

公开(公告)号：US11940537B2

公开(公告)日：2024-03-26

申请号：US17545194

申请日：2021-12-08

Applicant: GM Global Technology Operations LLC

Inventor： Wei Zeng ,  Huabing Zhu ,  Shuqing Zeng ,  Jordan B. Chipka

IPC: G01S17/89 ,  G01B11/22 ,  G01S17/931 ,  G06T7/11 ,  G06T7/521 ,  G06T7/55 ,  H04N23/90

CPC classification number: G01S17/89 ,  G01B11/22 ,  G01S17/931 ,  G06T7/11 ,  G06T7/521 ,  G06T7/55 ,  H04N23/90 ,  G06T2207/10024 ,  G06T2207/10028 ,  G06T2207/30252

Abstract: A virtual LiDAR sensor system fora motor vehicle includes a plurality of camera modules and algorithms that generate a depth image, a RGB image, and a segmentation information image. The system is implemented with an algorithm that associates the backscattered signals with information from a color-reflectivity table, incident angle determination and depth information.

公开(公告)号：US20230176218A1

公开(公告)日：2023-06-08

申请号：US17545194

申请日：2021-12-08

Applicant: GM Global Technology Operations LLC

Inventor： Wei Zeng ,  Huabing Zhu ,  Shuqing Zeng ,  Jordan B. Chipka

IPC: G01S17/89 ,  G01S17/931 ,  G01B11/22 ,  G06T7/521 ,  G06T7/11 ,  G06T7/55 ,  H04N5/247

CPC classification number: G01S17/89 ,  G01S17/931 ,  G01B11/22 ,  G06T7/521 ,  G06T7/11 ,  G06T7/55 ,  H04N5/247 ,  G06T2207/10028 ,  G06T2207/10024 ,  G06T2207/30252

Abstract: A virtual LiDAR sensor system fora motor vehicle includes a plurality of camera modules and algorithms that generate a depth image, a RGB image, and a segmentation information image. The system is implemented with an algorithm that associates the backscattered signals with information from a color-reflectivity table, incident angle determination and depth information.

公开(公告)号：US11989947B2

公开(公告)日：2024-05-21

申请号：US17367847

申请日：2021-07-06

Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor： Shuqing Zeng ,  Jordan B. Chipka ,  Thanura R. Elvitigala

IPC: G06V20/58 ,  B60R11/04 ,  G06N3/08 ,  G06T3/40 ,  G06V10/25

CPC classification number: G06V20/58 ,  B60R11/04 ,  G06N3/08 ,  G06T3/40 ,  G06V10/25

Abstract: A perception system is adapted to receive visual data from a camera and includes a controller having a processor and tangible, non-transitory memory on which instructions are recorded. A subsampling module, an object detection module and an attention module are each selectively executable by the controller. The controller is configured to sample an input image from the visual data to generate a rescaled whole image frame, via the subsampling module. The controller is configured to extract feature data from the rescaled whole image frame, via the object detection module. A region of interest in the rescaled whole image frame is identified, based on an output of the attention module. The controller is configured to generate a first image based on the rescaled whole image frame and a second image based on the region of interest, the second image having a higher resolution than the first image.

公开(公告)号：US20240134022A1

公开(公告)日：2024-04-25

申请号：US18047102

申请日：2022-10-17

Applicant: GM Global Technology Operations LLC

Inventor： Wei Zeng ,  Shuqing Zeng ,  Huabing Zhu ,  Jordan B. Chipka

IPC: G01S7/497 ,  G01S17/00 ,  G01S17/89 ,  G01S17/931

CPC classification number: G01S7/497 ,  G01S17/006 ,  G01S17/89 ,  G01S17/931 ,  G01S2007/4975

Abstract: A method of modeling precipitation effects in a virtual LiDAR sensor, the method includes receiving a point cloud model representing three-dimensional coordinates of objects as the objects would be sensed by a LiDAR sensor. The method further includes generating a stochastic model of rainfall or snowfall, estimating a probability that a light source from the LiDAR sensor hits a raindrop or a snowflake based on the stochastic model, and modifying the received point cloud model to include effects induced by the modeled rainfall or snowfall based on the probability that light sourced from the LiDAR sensor encounters a raindrop or a snowflake.

公开(公告)号：US20230010239A1

公开(公告)日：2023-01-12

申请号：US17367847

申请日：2021-07-06

Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor： Shuqing Zeng ,  Jordan B. Chipka ,  Thanura R. Elvitigala

IPC: G06K9/00 ,  G06K9/32 ,  G06T3/40 ,  G06N3/08 ,  B60R11/04

Abstract: A perception system is adapted to receive visual data from a camera and includes a controller having a processor and tangible, non-transitory memory on which instructions are recorded. A subsampling module, an object detection module and an attention module are each selectively executable by the controller. The controller is configured to sample an input image from the visual data to generate a rescaled whole image frame, via the subsampling module. The controller is configured to extract feature data from the rescaled whole image frame, via the object detection module. A region of interest in the rescaled whole image frame is identified, based on an output of the attention module. The controller is configured to generate a first image based on the rescaled whole image frame and a second image based on the region of interest, the second image having a higher resolution than the first image.