公开(公告)号：US20240249435A1

公开(公告)日：2024-07-25

申请号：US18417742

申请日：2024-01-19

Applicant: TuSimple, Inc.

Inventor： Shane David Griffith

IPC: G06T7/73 ,  G06T7/246 ,  G06T7/38

CPC classification number: G06T7/74 ,  G06T7/248 ,  G06T7/38 ,  G06T2207/30244 ,  G06T2207/30256

Abstract: System and method for using dynamic objects for camera pose estimation are disclosed. In one aspect, the method includes receiving a first image from a camera of an autonomous vehicle and acquiring first camera pose constraints based on one or more static objects detected in the first image. The method further includes receiving a second image from the camera and acquiring second camera pose constraints based on one or more static objects detected in the second image. The method further includes acquiring third camera pose constraints based on one or more dynamic objects detected in the first and the second image. The method finally includes an estimation of at least one pose of the camera that satisfies the first camera pose constraints, the second camera pose constraints, and the third camera pose constraints.

公开(公告)号：US11702089B2

公开(公告)日：2023-07-18

申请号：US17150271

申请日：2021-01-15

Applicant: TUSIMPLE, INC.

Inventor： Shane David Griffith ,  Chenghao Gong ,  Chenzhe Qian

IPC: B60W50/06 ,  G01S19/42 ,  G06T7/80 ,  B60W60/00 ,  G06V20/56

CPC classification number: B60W50/06 ,  B60W60/001 ,  G01S19/42 ,  G06T7/85 ,  G06V20/588 ,  B60W2420/42 ,  B60W2552/53 ,  G06T2207/30256

Abstract: Techniques for performing a sensor calibration using sequential data is disclosed. An example method includes receiving, from a first camera located on a vehicle, a first image comprising at least a portion of a road comprising lane markers, where the first image is obtained by the camera at a first time; obtaining a calculated value of a position of an inertial measurement (IM) device at the first time; obtaining an optimized first extrinsic matrix of the first camera by adjusting a function of a first actual pixel location of a location of a lane marker in the first image and an expected pixel location of the location of the lane marker; and performing autonomous operation of the vehicle using the optimized first extrinsic matrix of the first camera when the vehicle is operated on another road or at another time.