System and method for adjusting bounding box dimensions

Patent metadata

Field	Value
Publication number	US-12181613-B2
Application number	US-202217731790-A
Country	US
Kind code	B2
Filing date	Apr 28, 2022
Priority date	Apr 28, 2022
Publication date	Dec 31, 2024
Grant date	Dec 31, 2024

Abstract

Systems and methods for adjusting the dimensions of point clouds are described herein. In one example, a system includes a processor and a memory having instructions that, when executed by the processor, cause the processor to generate a bounding box using a point cloud generated by a sensor and adjust a dimension of the bounding box based on a magnitude of a viewing angle of a side of the bounding box with respect to the sensor.

First claim

What is claimed is:

1. A system comprising:
a processor; and
a memory in communication with the processor, the memory storing an adjustment module having instructions that, when executed by the processor, cause the processor to:
generate a bounding box using a point cloud generated by a sensor, the bounding box representing an object,
determine a confidence factor based on a magnitude of a viewing angle of a side of the bounding box with respect to the sensor, and
adjust a dimension of the bounding box such that the side of the bounding box moves closer to the one or more points of the point cloud that correspond to the side of the bounding box by an adjustment distance, the adjustment distance being based on the confidence factor and is proportional to the confidence factor.

2. The system of claim 1 , wherein the adjustment module further includes instructions that, when executed by the processor, cause the processor to adjust the dimension of the bounding box such that the side of the bounding box moves closer to points of the point cloud used to generate the bounding box based on the magnitude of the viewing angle of the side of the bounding box with respect to the sensor.

3. The system of claim 1 , wherein the confidence factor is proportional to the magnitude of the viewing angle.

4. The system of claim 1 , wherein the sensor is a LIDAR sensor and the point cloud is a LIDAR point cloud.

5. The system of claim 1 , wherein the sensor is a camera sensor and the point cloud is a pseudo-LIDAR point cloud.

6. The system of claim 1 , wherein the sensor is mounted to a vehicle.

7. A method comprising steps of:
generating a bounding box using a point cloud generated by a sensor, the bounding box representing an object;
determining a confidence factor based on a magnitude of a viewing angle of a side of the bounding box with respect to the sensor; and
adjusting a dimension of the bounding box such that the side of the bounding box moves closer to the one or more points of the point cloud that correspond to the side of the bounding box by an adjustment distance, the adjustment distance being based on the confidence factor and is proportional to the confidence factor.

8. The method of claim 7 , further comprising the step of adjusting the dimension of the bounding box such that the side of the bounding box moves closer to points of the point cloud used to generate the bounding box based on the magnitude of the viewing angle of the side of the bounding box with respect to the sensor.

9. The method of claim 7 , wherein the confidence factor is proportional to the magnitude of the viewing angle.

10. The method of claim 7 , wherein the sensor is a LIDAR sensor and the point cloud is a LIDAR point cloud.

11. The method of claim 7 , wherein the sensor is a camera sensor and the point cloud is a pseudo-LIDAR point cloud.

12. The method of claim 7 , wherein the sensor is mounted to a vehicle.

13. A non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to
generate a bounding box using a point cloud generated by a sensor, the bounding box representing an object;
determine a confidence factor based on a magnitude of a viewing angle of a side of the bounding box with respect to the sensor; and
adjust a dimension of the bounding box such that the side of the bounding box moves closer to the one or more points of the point cloud that correspond to the side of the bounding box by an adjustment distance, the adjustment distance being based on the confidence factor and is proportional to the confidence factor.

14. The non-transitory computer-readable medium of claim 13 , further storing instructions that, when executed by the processor, cause the processor to adjust the dimension of the bounding box such that the side of the bounding box moves closer to points of the point cloud used to generate the bounding box based on the magnitude of the viewing angle of the side of the bounding box with respect to the sensor.

15. The non-transitory computer-readable medium of claim 13 , wherein the confidence factor is proportional to the magnitude of the viewing angle.

16. The non-transitory computer-readable medium of claim 13 , wherein the sensor is a LIDAR sensor and the point cloud is a LIDAR point cloud.

17. The non-transitory computer-readable medium of claim 13 , wherein the sensor is a camera sensor and the point cloud is a pseudo-LIDAR point cloud.

Assignees

• Toyota Res Inst Inc
• Toyota Motor Co Ltd

Inventors

• Serafin Jacopo

Classifications

• G01S17/42

  Simultaneous measurement of distance and other co-ordinates (indirect measurement G01S17/46) · CPC title

• G01S17/89 Primary

  for mapping or imaging · CPC title

• G01S17/86

  Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders · CPC title

• G01S7/4802

  using analysis of echo signal for target characterisation; Target signature; Target cross-section · CPC title

• G01S7/4808

  Evaluating distance, position or velocity data · CPC title