Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020223313 - INDUSTRIAL VEHICLE WITH FEATURE-BASED LOCALIZATION AND NAVIGATION

Note: Text based on automatic Optical Character Recognition processes. Please use the PDF version for legal matters

[ EN ]

CLAIMS

1. An industrial 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;

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;

the camera is configured to capture an input image of a ceiling of a warehouse

comprising one or more skylights, one or more ceiling lights, one or more active targets, or combinations thereof; and

the navigation module is configured to identify the one or more skylights, the one or more ceiling lights, the one or more active targets, or combinations thereof, by executing machine readable instructions to

create a Gaussian scale space pyramid from the input image of the ceiling of the warehouse, wherein the Gaussian scale space pyramid comprises a plurality of scale space images,

calculate a trace of Hessian response for each scale space image of the plurality of scale space images within the Gaussian scale space pyramid, build a trace of Hessian response pyramid based on the Gaussian scale space pyramid,

build a multiscale candidate graph utilizing the trace of Hessian response

pyramid,

utilize the multiscale candidate graph to identify one or more candidates

comprising one or more skylight candidates, one or more ceiling light candidates, one or more active target candidates, or combinations thereof, in the input image of the ceiling,

subject the one or more candidates to candidate feature processing to identify a valid identification of the one or more candidates as the one or more skylights, the one or more ceiling lights, the one or more active targets, or combinations thereof, in the warehouse, and

send commands to the vehicle controller to navigate the industrial vehicle

through the warehouse based upon the valid identification.

2. The industrial vehicle of claim 1, wherein:

the navigation module executes the machine readable instructions to identify the valid identification of the one or more candidates as the one or more ceiling lights; and the one or more ceiling lights comprise one or more rectangular ceiling lights

characterized by different rates of image intensity change along longitudinal and transverse axial directions, one or more circular ceiling lights characterized by a symmetric rate of image intensity change, or combinations thereof.

3. The industrial vehicle of claim 1, wherein the navigation module executes the machine readable instructions to:

identify the valid identification of the one or more candidates as the one or more

skylights, the one or more ceiling lights, and the one or more active targets; identify the one or more skylights based on a recognition of different rates of image intensity change along longitudinal and transverse axial directions in the input image;

identify the one or more ceiling lights based on a recognition of a symmetric rate of image intensity change or by different rates of image intensity change along longitudinal and transverse axial directions in the input image; and identify the one or more active targets based on a recognition of a plurality of symmetric rates of intensity change within a threshold distance in the input image.

4. The industrial vehicle of claim 3, wherein the one or more active targets comprise one or more optical light emitting diode (LED) features.

5. The industrial vehicle of claim 1, wherein the navigation module is further configured to execute machine readable instructions to detect one or more light features of varying brightness of the one or more candidates, one or more light features of varying size of the one or more candidates, or combinations thereof.

6. The industrial vehicle of claim 1, wherein the navigation module is further configured to execute machine readable instructions to:

build the multiscale candidate graph based on each scale space image in the trace of Hessian response pyramid;

utilize the multiscale candidate graph to identify the one or more candidates by generating one or more bounding boxes for each scale space image and thresholding each scale space image in the trace of Hessian response pyramid against a threshold value to utilize each scale space image at or above the threshold value.

7. The industrial vehicle of claim 6, wherein:

the plurality of scale space images comprises a range from a low value fine scale index to a high value coarse scale index comprising a value higher than the low value fine scale index;

the navigation module builds the multiscale candidate graph by processing scale space images beginning from the high value coarse index to down to the low value fine scale index to build up inter-image graph edge connections between one or more graph nodes from each scale space image; and

the one or more graph nodes are associated with one or more bounding boxes in each scale space image.

8. The industrial vehicle of claim 1, wherein the navigation module is further configured to execute machine readable instructions to:

generate one or more best fit candidates from the one or more candidates;

input the one or more best fit candidates into a feature extraction function of the

candidate feature processing to generate one or more candidate feature extractions; and

utilize the one or more candidate feature extractions from the feature extraction function to identify the valid identification of the one or more candidates as the one or more skylights, the one or more ceiling lights, the one or more active targets, or combinations thereof.

9. The industrial vehicle of claim 8, wherein the one or more best fit candidates are categorized as the one or more candidates comprising the one or more skylight candidates, the one or more ceiling light candidates, the one or more active target candidates, or combinations thereof.

10. The industrial vehicle of claim 8, wherein the navigation module is further configured to execute machine readable instructions to:

apply a merge and split candidates function to merge and split one or more bounding boxes associated with the one or more skylight candidates to generate one or more split bounding boxes when the one or more best fit candidates are categorized as the one or more skylight candidates; and

extract one or more features from the one or more split bounding boxes to generate the one or more candidate feature extractions.

11. The industrial vehicle of claim 8, wherein the navigation module is further configured to execute machine readable instructions to filter the one or more best fit candidates when the one or more best fit candidates are categorized as the one or more ceiling light candidates.

12. The industrial vehicle of claim 8, wherein the navigation module is further configured to execute machine readable instructions to filter the one or more best fit candidates to generate the one or more candidate feature extractions.

13. The industrial vehicle of claim 1 wherein the navigation module is further configured to execute machine readable instructions to:

generate one or more isolated light feature extractions from the one or more ceiling light candidates comprising one or more isolated light candidates;

generate one or more skylight feature extractions from the one or more skylight

candidates; and

remove the one or more isolated light candidates comprising the one or more isolated light feature extraction that intersect with the one or more skylight feature extractions.

14. The industrial vehicle of claim 1, wherein the navigation module is further configured to execute machine readable instructions to generate a feature candidate bounding box for each of the one or more candidates in the candidate feature processing.

15. The industrial vehicle of claim 14, wherein the navigation module is further configured to execute machine readable instructions to extract one or more features from each feature candidate bounding box.

16. The industrial vehicle of claim 1, wherein the navigation module is further configured to execute machine readable instructions to:

generate feature coordinates of the one or more candidates based on the valid

identification; and

send commands to the vehicle controller to navigate the industrial vehicle through the warehouse based upon the valid identification and the feature coordinates.

17. An industrial 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;

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;

the camera is configured to capture an input image of a ceiling of a warehouse

comprising one or more skylights, one or more ceiling lights, one or more active targets, or combinations thereof; and

the navigation module is configured to identify the one or more skylights, the one or more ceiling lights, the one or more active targets, or combinations thereof, by executing machine readable instructions to

create a Gaussian scale space pyramid from the input image of the ceiling of the warehouse, wherein the Gaussian scale space pyramid comprises a plurality of scale space images,

calculate a trace of Hessian response for each scale space image of the plurality of scale space images within the Gaussian scale space pyramid, build a trace of Hessian response pyramid based on the Gaussian scale space pyramid,

utilize the trace of Hessian response pyramid to identify one or more candidates comprising one or more skylight candidates, one or more ceiling light candidates, and one or more active target candidates in the input image of the ceiling by generating one or more bounding boxes for each scale space image and thresholding each scale space image in the trace of Hessian response pyramid against a threshold value to utilize each scale space image at or above the threshold value,

detect one or more light features of varying brightness of the one or more

candidates, one or more light features of varying size of the one or more candidates, or combinations thereof,

subject the one or more candidates to candidate feature processing to identify a valid identification of the one or more candidates as the one or more skylights, the one or more ceiling lights, and the one or more active targets in the warehouse, and

send commands to the vehicle controller to navigate the industrial vehicle

through the warehouse based upon the valid identification.

18. The industrial vehicle of claim 17, wherein the navigation module is further configured to execute machine readable instructions to:

build a multiscale candidate graph based on each scale space image in the trace of

Hessian response pyramid, wherein

the plurality of scale space images comprises a range from a low value fine scale index to a high value coarse scale index comprising a value higher than the low value fine scale index;

the navigation module builds the multiscale candidate graph by processing scale space images beginning from the high value coarse index to down to the low value fine scale index to build up inter-image graph edge connections between one or more graph nodes from each scale space image; and the one or more graph nodes are associated with one or more bounding boxes in each scale space image.

19. The industrial vehicle of claim 17, wherein the navigation module is further configured to execute machine readable instructions to:

generate one or more best fit candidates from the one or more candidates;

input the one or more best fit candidates into a feature extraction function of the

candidate feature processing to generate one or more candidate feature extractions; and

utilize the one or more candidate feature extractions from the feature extraction function to identify the valid identification of the one or more candidates as the one or more skylights, the one or more ceiling lights, and the one or more active targets. 20. A method for navigating an industrial vehicle, the method comprising:

operating the industrial vehicle in a warehouse, the industrial vehicle comprising a drive mechanism, a steering mechanism, a vehicle controller, a camera, and a navigation module, wherein (i) the camera is communicatively coupled to the navigation module, (ii) the vehicle controller is responsive to commands from the navigation module, and (iii) the drive mechanism and the steering mechanism are responsive to commands from the vehicle controller;

capturing an input image of a ceiling of the warehouse comprising one or more skylights, one or more ceiling lights, one or more active targets, or combinations thereof by the camera;

creating a Gaussian scale space pyramid from the input image of the ceiling of the

warehouse utilizing the navigation module, wherein the Gaussian scale space pyramid comprises a plurality of scale space images;

calculating a trace of Hessian response for each scale space image of the plurality of scale space images within the Gaussian scale space pyramid;

building a trace of Hessian response pyramid based on the Gaussian scale space pyramid; building a multiscale candidate graph utilizing the trace of Hessian response pyramid; utilizing the multiscale candidate graph to identify one or more candidates comprising one or more skylight candidates, one or more ceiling light candidates, one or more active target candidates, or combinations thereof, in the input image of the ceiling using the navigation module;

subjecting the one or more candidates to candidate feature processing to identify as a valid identification of the one or more candidates as the one or more skylights, the one or more ceiling lights, the one or more active targets, or combinations thereof, in the warehouse using the navigation module; and

send commands from the navigation module to the vehicle controller to navigate the industrial vehicle through the warehouse based upon the valid identification.