Industrial vehicle with feature-based localization and navigation

• US 10,151,591 B2
• Filed: 05/02/2018
• Issued: 12/11/2018
• Est. Priority Date: 09/04/2015
• Status: Active Grant

• Current Assignee: Crown Equipment Corporation
• Original Assignee: Crown Equipment Corporation
• Inventors: Bell, Mark
• Primary Examiner(s): Wang, Carol
• Application Number:
  US15/968,971
• Publication Number:
  US 20180245926A1
• Time in Patent Office: 223 Days
• CPC Class Codes: G01C 21/206 specially adapted for indoor navigation
• CPC Class Codes: G05D 1/0246 using a video camera in combination with image processing means
• CPC Class Codes: G06F 18/213 Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/20016 Hierarchical, coarse-to-fine, multiscale or multiresolution image processing; Pyramid transform
• CPC Class Codes: G06T 2207/30241 Trajectory
• CPC Class Codes: G06T 2207/30244 Camera pose
• CPC Class Codes: G06T 2207/30252 Vehicle exterior; Vicinity of vehicle
• CPC Class Codes: G06T 5/20 using local operators
• CPC Class Codes: G06T 5/70 Denoising; Smoothing
• CPC Class Codes: G06T 7/73 using feature-based methods
• CPC Class Codes: G06V 10/462 Salient features, e.g. scale invariant feature transforms [SIFT]
• CPC Class Codes: G06V 10/52 Scale-space analysis, e.g. wavelet analysis multi-scale boundary representations G06V10/42
• CPC Class Codes: G06V 20/10 Terrestrial scenes scenes under surveillance with static cameras G06V20/52; scenes perceived from the exterior of a vehicle G06V20/56; scenes perceived from the interior of a vehicle G06V20/59
• CPC Class Codes: G06V 20/56 exterior to a vehicle by using sensors mounted on the vehicle

Abstract

An industrial vehicle is provided comprising a drive mechanism, a steering mechanism, a vehicle controller, a camera, and a navigation module. The camera is communicatively coupled to the navigation module, the vehicle controller is responsive to commands from the navigation module, and the drive mechanism and the steering mechanism are responsive to commands from the vehicle controller. The camera is configured to capture an input image of a warehouse ceiling comprising elongated skylights characterized by different rates of image intensity change along longitudinal and transverse axial directions, and ceiling lights characterized by a circularly symmetric rate of image intensity change. The navigation module is configured to distinguish between the ceiling lights and the skylights and send commands to the vehicle controller for localization, or to navigate the industrial vehicle through the warehouse based upon valid ceiling light identification, valid skylight identification, or both.

Claims

1. A system comprising a vehicle camera, and a navigation module, wherein:

the vehicle camera is communicatively coupled to the navigation module and is configured to capture input images of a warehouse;

the navigation module is configured to distinguish between object types in the input images by executing machine readable instructions to

create Gaussian scale space pyramids from the input images of the warehouse,

build determinant of Hessian response pyramids from the Gaussian scale space pyramids,

build trace of Hessian response pyramids from the Gaussian scale space pyramids,

utilize the determinant of Hessian response pyramids to identify candidate object types in the input images,

utilize the trace of Hessian response pyramids to identify candidate object types in the input images,

subject the identified candidate object types to candidate feature processing to identify valid object types in the warehouse, and

utilize navigational data based upon the valid object type identification.

2. The system of claim 1 wherein the Gaussian scale space pyramids are created by running a cascading series of image smoothing operations applied to the input images of a ceiling in the warehouse.

3. The system of claim 2 wherein the Gaussian scale space pyramids are approximated by convolution with binomial filter kernels.

4. The system of claim 1 wherein the Gaussian scale space pyramids are created by supplementing a cascading series of image smoothing operations with subsampling operations.

5. The system of claim 4 wherein the supplemental subsampling operations are implemented conditionally as a function of available navigation module computing power.

6. The system of claim 1 wherein the determinant of Hessian response pyramids and trace of Hessian response pyramids are calculated based on each Gaussian scale space image being convolved with second-order partial derivative filter kernels.

7. The system of claim 1 wherein the determinant of Hessian response pyramids are calculated by subtraction of a mixed second-order partial derivative term.

8. The system of claim 1 wherein the determinant of Hessian response pyramids suppress responses to objects characterized by different rates of image intensity change along longitudinal and transverse axial directions.

9. The system of claim 1 wherein the determinant of Hessian response pyramids are utilized for multiscale non-maximum suppression wherein local maxima are located within a window comprising scale and spatial dimensions.

10. The system of claim 9 wherein an absolute minimum threshold is applied to prevent excessive noisy false positive determinant responses.

11. The system of claim 1 wherein the determinant of Hessian response pyramids are utilized in a filtering keypoints function for removing candidate points that do not likely correspond to ceiling lights.

12. The system of claim 11 wherein the filtering keypoints function utilizes other filters on candidate points to check against empirically set thresholds.

13. The system of claim 12 wherein the other filters comprise scales at which keypoints are detected, a spatial location of a keypoint, a magnitude of a determinant of Hessian response pyramid at the keypoint location, a machine-learning classifier, or an average trace of Hessian response pyramid values of a surrounding area.

14. The system of claim 1 wherein the determinant of Hessian response pyramids are utilized in a refining keypoints function for refining spatial position and scale of ceiling light candidate keypoints.

15. The system of claim 1 wherein the trace of Hessian response pyramids are utilized in a sum large-scale trace of Hessian response images function for summing a selection of trace of Hessian response images from a trace of Hessian response pyramid into an integrated trace of Hessian response image.

16. The system of claim 15 wherein skylight regions are searched for within a trace of Hessian response pyramid.

17. The system of claim 1 wherein the trace of Hessian response pyramids are further processed by a threshold integrated trace of Hessian response function, wherein a trace of Hessian response is smoothed and a threshold is applied.

18. The system of claim 17 wherein the threshold is fixed.

19. The system of claim 17 wherein the threshold is not fixed.

20. The system of claim 1 wherein the trace of Hessian response pyramids are utilized in a connected component filtering function for extracting and filtering connected components based on a binary thresholded integrated trace of Hessian response image.

21. The system of claim 20 wherein the connected component filtering function filters for size and aspect ratio to select rectangular regions.

22. The system of claim 1 wherein:

candidate object types in the input images that are characterized by different rates of image intensity change along a plurality of axial directions correspond to elongated skylights; and

candidate object types in the input images that are characterized by a circularly symmetric rate of image intensity change correspond to ceiling lights.

23. A system comprising a vehicle camera, and a navigation module, wherein:

the vehicle camera is communicatively coupled to the navigation module and is configured to capture input images of a ceiling in a warehouse; and

the navigation module is configured to distinguish between object types in the input images by executing machine readable instructions to

create Gaussian scale space pyramids from the input images of the warehouse-ceiling,

build determinant of Hessian response pyramids from the Gaussian scale space pyramids,

build trace of Hessian response pyramids from the Gaussian scale space pyramids,

utilize the trace of Hessian response pyramids to identify candidate object types in the input images that are characterized by different rates of image intensity change along a plurality of axial directions,

utilize the determinant of Hessian response pyramids to identify candidate object types in the input images that are characterized by a circularly symmetric rate of image intensity change,

subject the identified candidate object types to candidate feature processing to identify valid object types in the warehouse, and

utilize navigational data based upon the valid object type identification.

24. A vehicle comprising a drive mechanism, a steering mechanism, a vehicle controller, a camera, and a navigation module, wherein:

the camera is communicatively coupled to the navigation module and is configured to capture input images of a ceiling in a warehouse;

the vehicle controller is responsive to commands from the navigation module;

the drive mechanism and the steering mechanism are responsive to commands from the vehicle controller; and

the navigation module is configured to distinguish between object types in the input images by executing machine readable instructions to

create Gaussian scale space pyramids from the input images of the warehouse-ceiling,

build determinant of Hessian response pyramids from the Gaussian scale space pyramids,

build trace of Hessian response pyramids from the Gaussian scale space pyramids,

utilize the trace of Hessian response pyramids to identify candidate object types in the input images that are characterized by different rates of image intensity change along a plurality of axial directions,

utilize the determinant of Hessian response pyramids to identify candidate object types in the input images that are characterized by a circularly symmetric rate of image intensity change,

subject the identified candidate object types to candidate feature processing to identify valid object types in the warehouse, and

send commands to the vehicle controller to navigate the vehicle through the warehouse based upon the valid object type identification.