Estimation of panoramic camera orientation relative to a vehicle coordinate frame

• US 9,270,891 B2
• Filed: 03/12/2014
• Issued: 02/23/2016
• Est. Priority Date: 02/20/2009
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Anguelov, Dragomir, Filip, Daniel Joseph
• Primary Examiner(s): Le, Thao X
• Assistant Examiner(s): LE, LONG HUYNH
• Application Number:
  US14/206,577
• Publication Number:
  US 20140192145A1
• Time in Patent Office: 713 Days
• Field of Search: 348/36
• US Class Current: 1/1
• CPC Class Codes: G06T 2207/30252 Vehicle exterior; Vicinity of vehicle
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80
• CPC Class Codes: H04N 23/69 Control of means for changing angle of the field of view, e.g. optical zoom objectives or electronic zooming
• CPC Class Codes: H04N 23/698 for achieving an enlarged field of view, e.g. panoramic image capture
• CPC Class Codes: H04N 5/2628 Alteration of picture size, shape, position or orientation, e.g. zooming, rotation, rolling, perspective, translation

Abstract

A system and method are presented for estimating the orientation of a panoramic camera mounted on a vehicle relative to the vehicle coordinate frame. An initial pose estimate of the vehicle is determined based on global positioning system data, inertial measurement unit data, and wheel odometry data of the vehicle. Image data from images captured by the camera is processed to obtain one or more tracks, each track including a sequence of matched feature points stemming from a same three-dimensional location. A correction parameter determined from the initial pose estimate and tracks can then be used to correct the orientations of the images captured by the camera. The correction parameter can be optimized by deriving a correction parameter for each of a multitude of distinct subsequences of one or more runs. Statistical analysis can be performed on the determined correction parameters to produce robust estimates.

Claims

1. A method for estimating orientation of cameras mounted on vehicles, comprising:

determining, by one or more processors, an initial pose estimate of a vehicle having a camera mounted thereon, the initial pose estimate being a position and orientation of the vehicle relative to the world;

processing, by the one or more processors, image data from images captured by the camera to obtain one or more tracks, each track including a sequence of matched feature points stemming from a single three-dimensional location;

determining, by the one or more processors, from the initial pose estimate and the tracks, a correction parameter to correct orientations of the images captured by the camera for each of a plurality of subsequences of one or more runs, wherein determining the correction parameter, for each plurality of subsequences of one or more runs, includes evaluating a set of vehicle poses, three-dimensional locations from the one or more tracks, and an orientation of the camera relative to one or more sensors of the vehicle; and

performing statistical analysis on the determined correction parameters for each plurality of subsequences to determine a median value of the determined correction parameters.

2. The method of claim 1, wherein determining the correction parameter is done such that a reprojection error is minimized.

3. The method of claim 1, wherein the correction parameter is a camera rotation correction parameter that is determined for a particular portion of an uninterrupted data collection interval.

4. The method of claim 1, wherein the set of vehicle poses is obtained from location data, inertial measurement data, and wheel odometry data of the vehicle.

5. The method of claim 1, further comprising correcting orientations of the images by applying the correction parameter to the image data.

6. The method of claim 5, wherein the determining the correction parameter includes determining:

an optimized pose of the vehicle;

a location of points of the tracks in three dimensions; and

a camera to vehicle pose rotation.

7. The method of claim 1, the median value of the determined correction parameters is the optimized correction parameter.

8. The method of claim 7, wherein determining the median value omits determined correction parameters for subsequences of the plurality of subsequences of one or more runs in which acceleration of the vehicle is above a predetermined value or outside of a predetermined range.

9. The method of claim 7, wherein determining the median value omits determined correction parameters for subsequences of the plurality of subsequences of one or more runs in which the vehicle is moving outside of a predetermined velocity range.

10. The method of claim 1, wherein determining the correction parameter for each of the plurality of subsequences of the one or more runs includes performing a cost function to chooses subsequences of the selected run that conform to a predetermined rule.

11. The method of claim 1, wherein the determining the median value of the determined correction parameters includes:

for each run of the one or more runs, determining a first median of the correction parameters for each of a closest set of runs backward in time and determining a second median of the correction parameters for each of a closest set of runs forward in time; and

selecting either the first median or the second median as the optimized correction parameter based on which of the first or second median is closest to the correction parameter determined for that run.

12. A system, comprising:

one or more processors configured to;

determine an initial pose estimate of a vehicle having a camera mounted thereon, the initial pose estimate being a position and orientation of the vehicle relative to the world;

process image data from images captured by the camera to obtain one or more tracks, each track including a sequence of matched feature points stemming from a single three-dimensional location;

determine, from the initial pose estimate and the tracks, a correction parameter to correct orientations of the images captured by the camera for each of a plurality of subsequences of one or more runs, wherein determining the correction parameter, for each plurality of subsequences of one or more runs, includes evaluating a set of vehicle poses, three-dimensional locations from the one or more tracks, and an orientation of the camera relative to one or more sensors of the vehicle; and

perform statistical analysis on the determined correction parameters for each plurality of subsequences to determine a median value of the determined correction parameters.

13. The system of claim 12, wherein the one or more processors are further configured to correct orientations of the images by applying the correction parameter to the image data.

14. The system of claim 13, wherein the one or more processors are configured to determine the correction parameter by determining:

an optimized pose of the vehicle;

a location of points of the tracks in three dimensions; and

a camera to vehicle pose rotation.

15. The system of claim 13, wherein:

the one or more processors are configured to determine the correction parameter for each plurality of subsequences of one or more runs; and

the one or more processors are further configured to perform statistical analysis on the determined correction parameters for different subsequences to determine an optimized correction parameter.

16. The system of claim 13, wherein:

the one or more processors are configured to determine the correction parameter for each plurality of subsequences of one or more runs; and

the one or more processors are further configured to perform statistical analysis on the determined correction parameters across the one or more runs to determine an optimized correction parameter.

17. The system of claim 16, wherein performing the statistical analysis by the one or more processors includes:

for each of the one or more runs, determining a first median of the correction parameters for each of a closest set of runs backward in time and determining a second median of the correction parameters for each of a closest set of runs forward in time; and

selecting either the first median or the second median as the optimized correction parameter based on which of the first or second median is closest to the correction parameter determined for that run.

18. A non-transitory computer-readable storage medium on which computer readable instructions of a program are stored, the instructions, when executed by one or more processors, cause the one or more processors to perform a method for estimating orientation of cameras mounted on vehicles, the method comprising:

determining an initial pose estimate of a vehicle having a camera mounted thereon, the initial pose estimate being a position and orientation of the vehicle relative to the world;

processing image data from images captured by the camera to obtain one or more tracks, each track including a sequence of matched feature points stemming from a single three-dimensional location;

determining from the initial pose estimate and the tracks, a correction parameter to correct orientations of the images captured by the camera for each of a plurality of subsequences of one or more runs, wherein determining the correction parameter, for each plurality of subsequences of one or more runs, includes evaluating a set of vehicle poses, three-dimensional locations from the one or more tracks, and an orientation of the camera relative to one or more sensors of the vehicle; and

performing statistical analysis on the determined correction parameters for each plurality of subsequences to determine a median value of the determined correction parameters.