METHOD FOR REGISTRATION OF RANGE IMAGES FROM MULTIPLE LiDARS

• US 20130242285A1
• Filed: 02/26/2013
• Published: 09/19/2013
• Est. Priority Date: 03/15/2012
• Status: Active Grant

• Current Assignee: GM Global Technology Operations LLC (General Motors Company)
• Original Assignee: GM Global Technology Operations LLC (General Motors Company)
• Inventors: Zeng, Shuqing
• Granted Patent: US 9,329,269 B2
• Time in Patent Office: Days
• US Class Current: 356/28
• CPC Class Codes: G01S 17/58 Velocity or trajectory determination systems; Sense-of-movement determination systems
• CPC Class Codes: G01S 17/66 Tracking systems using electromagnetic waves other than radio waves
• CPC Class Codes: G01S 17/86 Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders
• CPC Class Codes: G01S 17/875 for determining attitude
• CPC Class Codes: G01S 17/931 of land vehicles

Abstract

A system and method for registering range images from objects detected by multiple LiDAR sensors on a vehicle. The method includes aligning frames of data from at least two LiDAR sensors having over-lapping field-of-views in a sensor signal fusion operation so as to track objects detected by the sensors. The method defines a transformation value for at least one of the LiDAR sensors that identifies an orientation angle and position of the sensor and provides target scan points from the objects detected by the sensors where the target scan points for each sensor provide a separate target point map. The method projects the target point map from the at least one sensor to another one of the LiDAR sensors using a current transformation value to overlap the target scan points from the sensors.

Claims

1. A method for fusing sensor signals from at least two LiDAR sensors having over-lapping field-of-views so as to track objects detected by the sensors, said method comprising:

defining a transformation value for at least one of the LiDAR sensors that identifies an orientation angle and position of the sensor;

providing target scan points from the objects detected by the sensors where the target scan points for each sensor provide a separate target point map;

projecting the target point map from the at least one sensor to another one of the LiDAR sensors using a current transformation value to overlap the target scan points from the sensors;

determining a plurality of weighting values using the current transformation value where each weighting value identifies a positional change of one of the scan points for the at least one sensor to a location of a scan point for the another one of the sensors;

calculating a new transformation value using the weighting values;

comparing the new transformation value to the current transformation value to determine a difference therebetween; and

revising the plurality of weighting values based on the difference between the new transformation value and the current transformation value until the new transformation value matches the current transformation value.

2. The method according to claim 1 wherein the LiDAR sensors are on a vehicle.

3. The method according to claim 1 further comprising selecting an initial transformation value for the at least one of the sensors that is initially used as the current transformation value.

4. The method according to claim 3 wherein selecting an initial transformation value includes selecting an initial transformation value from the group consisting of a manufacturer setting, zero and an estimated value.

5. The method according to claim 1 wherein determining a plurality of weighting values includes using the equation:

6. The method according to claim 1 further comprising determining that the current transformation value is greater than a predetermined threshold, wherein if the current transformation value is greater than the predetermined threshold, then the transformation value is defined based on a rotation matrix and translation vector.

7. The method according to claim 6 wherein defining a transformation value includes employing a particle swarm optimization process including generating a plurality of particles across a predetermined number of eligible transformation values, associating a normalized weight to each particle, setting a best transformation value for each particle and providing a nominal transformation value having a best match percentage from the at least one of the LiDAR sensors to the another one of the LiDAR sensors.

8. The method according to claim 1 further comprising determining that a change in the transformation value from one sample time to a next sample time is below a predetermined threshold, and if so, reducing computationally complexity for determining the current transformation value.

9. The method according to claim 8 wherein determining the current transformation value is below a predetermined threshold includes modeling the current transformation value as transformations between the scan points.

10. The method according to claim 1 wherein defining a transformation value includes using an expectation-maximization algorithm.

11. The method according to claim 1 wherein providing target scan points includes providing the target scan points as bipartite graphs.

12. The method according to claim 1 further comprising providing other types of sensors that operate to detect the objects and provide a cueing signal to initiate the sensor fusion operation.

13. The method according to claim 12 wherein the other types of sensors include radar sensors and vision systems.

14. A method for fusing sensor signals from at least two LiDAR sensors having over-lapping field-of-views so as to track objects detected by the sensors, said LiDAR sensors being on a vehicle, said method comprising:

defining a current transformation value for at least one of the LiDAR sensors that identifies an orientation angle and position of the sensor at one sample time;

providing target scan points from the objects detected by the sensors where the target scan points for each sensor provide a separate target point map;

projecting the target point map from the at least one sensor to another one of the LiDAR sensors using the current transformation value to overlap the target scan points from the sensors;

calculating a new transformation value at a next sample time;

comparing the new transformation value to the current transformation value to determine a difference therebetween; and

updating the current transformation value based on the difference.

15. The method according to claim 14 further comprising determining that the current transformation value is greater than a predetermined threshold, wherein if the current transformation value is greater than the predetermined threshold, then the transformation value is defined based on a rotation matrix and translation vector.

16. The method according to claim 15 wherein defining a transformation value includes employing a particle swarm optimization process including generating a plurality of particles across a predetermined number of eligible transformation values, associating a normalized weight to each particle, setting a best transformation value for each particle and providing a nominal transformation value having a best match percentage from the at least one of the LiDAR sensors to the another one of the LiDAR sensors.

17. The method according to claim 14 further comprising determining that a change in the transformation value from one sample time to a next sample time is below a predetermined threshold, and if so, reducing computationally complexity for determining the current transformation value.

18. The method according to claim 17 wherein determining the current transformation value is below a predetermined threshold includes modeling the current transformation value as transformations between the scan points.

19. The method according to claim 14 wherein defining a transformation value includes using an expectation-maximization algorithm.