System and method for trailer pose estimation
The present teaching relates to method, system, medium, and implementations for trailer pose estimation. At least a dimension of a trailer connected to a vehicle is obtained where the vehicle and the trailer have respective opposing surfaces facing one another. A first set of feature points is identified from a first image of a target present on one the opposing surfaces acquired at a first time instant by a sensor deployed on the other the opposing surfaces. A second set of corresponding feature points is identified from a second image of the target acquired at a subsequent time instant by the sensor. Based on the first and second sets of feature points, a first transformation is determined and used to compute a second transformation that the trailer undergoes from the first to the second time instants. A pose of the trailer at the second time instant is estimated based on the second transformation and the dimension.
1. A method implemented on at least one machine including at least one processor, memory, and communication platform capable of connecting to a network for pose estimation, the method comprising:
obtaining at least a dimension of a trailer connected to a vehicle, wherein the vehicle and the trailer have respective opposing surfaces facing one another;
identifying a first set of feature points from a first image of a fiducial marker present on a first of the opposing surfaces acquired at a first time instant by a sensor deployed on a second of the opposing surfaces;
identifying a second set of feature points from a second image of the fiducial marker acquired at a second time instant by the sensor, wherein each of the second set of feature points corresponds to one of the first set of feature points;
determining, based on the first and second sets of feature points, a first transformation;
computing a second transformation that the trailer undergoes from the first to the second time instants in accordance with the first transformation; and
estimating, for autonomous driving of the vehicle, a pose of the trailer at the second time instant based on the second transformation and the dimension.
2. The method of claim 1 , wherein
the first of the opposing surfaces is the rear surface of the vehicle; and
the second of the opposing surfaces is the front surface of the trailer.
3. The method of claim 1 , wherein
the first of the opposing surfaces is the front surface of the trailer; and
the second of the opposing surfaces is the rear surface of the vehicle.
4. The method of claim 1 , wherein the pose of the trailer is represented by one or more coordinates of corresponding one or more points located on the trailer.
5. The method of claim 1 , wherein the first time instant corresponds to one of:
an initialization time instant where the vehicle and the trailer are aligned in a straight line; and
any time instant prior to the second time instant so that the estimated pose for the second time instant represents a change in trailer's pose as compared to that at the first time instant.
6. The method of claim 1 , wherein the pose of the trailer is estimated based on planar homography.
7. Machine readable and non-transitory medium having information recorded thereon for pose estimation, wherein the information, when read by the machine, causes the machine to perform:
obtaining at least a dimension of a trailer connected to a vehicle, wherein the vehicle and the trailer have respective opposing surfaces facing one another;
identifying a first set of feature points from a first image of a fiducial marker present on a first of the opposing surfaces acquired at a first time instant by a sensor deployed on a second of the opposing surfaces;
identifying a second set of feature points from a second image of the fiducial marker acquired at a second time instant by the sensor, wherein each of the second set of feature points corresponds to one of the first set of feature points;
determining, based on the first and second sets of feature points, a first transformation;
computing a second transformation that the trailer undergoes from the first to the second time instants in accordance with the first transformation; and
estimating, for autonomous driving of the vehicle, a pose of the trailer at the second time instant based on the second transformation and the dimension.
8. The medium of claim 7 , wherein
the first of the opposing surfaces is the rear surface of the vehicle; and
the second of the opposing surfaces is the front surface of the trailer.
9. The medium of claim 7 , wherein
the first of the opposing surfaces is the front surface of the trailer; and
the second of the opposing surfaces is the rear surface of the vehicle.
10. The medium of claim 7 , wherein the pose of the trailer is represented by one or more coordinates of corresponding one or more points located on the trailer.
11. The medium of claim 7 , wherein the first time instant corresponds to one of:
an initialization time instant where the vehicle and the trailer are aligned in a straight line; and
any time instant prior to the second time instant so that the estimated pose for the second time instant represents a change in trailer's pose as compared to that at the first time instant.
12. The medium of claim 7 , wherein the pose of the trailer is estimated based on planar homography.
13. A system for pose estimation, comprising:
a configuration unit configured for obtaining at least a dimension of a trailer connected to a vehicle, wherein the vehicle and the trailer have respective opposing surfaces facing one another;
a fiducial marker image feature extractor configured for:
identifying a first set of feature points from a first image of a fiducial marker present on a first of the opposing surfaces acquired at a first time instant by a sensor deployed on a second of the opposing surfaces, and
identifying a second set of feature points from a second image of the fiducial marker acquired at a second time instant by the sensor, wherein each of the second set of feature points corresponds to one of the first set of feature points;
a transformation generation unit configured for determining, based on the first and second sets of feature points, a first transformation; and
a trailer pose estimator configured for:
computing a second transformation that the trailer undergoes from the first to the second time instants in accordance with the first transformation, and
estimating, for autonomous driving of the vehicle, a pose of the trailer at the second time instant based on the second transformation and the dimension.
14. The system of claim 13 , wherein
the first of the opposing surfaces is the rear surface of the vehicle; and
the second of the opposing surfaces is the front surface of the trailer.
15. The system of claim 13 , wherein
the first of the opposing surfaces is the front surface of the trailer; and
the second of the opposing surfaces is the rear surface of the vehicle.
16. The system of claim 13 , wherein the pose of the trailer is represented by one or more coordinates of corresponding one or more points located on the trailer.
17. The system of claim 13 , wherein the first time instant corresponds to one of:
an initialization time instant where the vehicle and the trailer are aligned in a straight line; and
any time instant prior to the second time instant so that the estimated pose for the second time instant represents a change in trailer's pose as compared to that at the first time instant.
18. The system of claim 13 , wherein the pose of the trailer is estimated based on planar homography.