Method for near-realtime workspace mapping

Patent metadata

Field	Value
Publication number	US-9818198-B2
Application number	US-201514886600-A
Country	US
Kind code	B2
Filing date	Oct 19, 2015
Priority date	Oct 21, 2014
Publication date	Nov 14, 2017
Grant date	Nov 14, 2017

Abstract

Motorized machinery, such as overhead cranes, are widely used in industries all over the world. It is not easy to move crane payloads without oscillation, increasing the likelihood of obstacle collisions and other accidents. One possible solution to such problems could be aiding the operator with a dynamic map of the workspace that shows the current position of obstacles. This method discloses the use of a camera to take images of the workspace, using imaging blurring to smooth the obtained images, and drawing contours to produce an individual, near real-time map of the workspace. In one or more embodiments, known obstacles may be tagged in a manner which is readable by the camera. This image and historical images of the same workspace are layered on top of one another to produce a map of obstacles on the workspace floor. This imaging and layering can produce a near real-time map of obstacles that can be used to guide heavy motorized machinery around a workspace without incident.

First claim

The invention claimed is:

1. A method for providing workspace mapping comprising:
(a) employing a camera in a designated position in the workspace;
(b) when the camera is in the designated position, taking at least two images of the workspace with the camera wherein the workspace is divided into at least two segments and at least one image is taken at a designated position in each of the said at least two segments;
(c) using image blurring to smooth the at least two images thereby reducing noise in the at least two images;
(d) using foreground-background segmentation to detect and delineate obstacles in said at least two images;
(e) drawing contours of said obstacles to produce one map of the workspace whereupon said obstacles are depicted wherein said at least two images are stitched together to form the one map of the workspace and template matching to mask portions of the workspace image from inclusion in the one map.

2. The method of claim 1 wherein obstacles are detected through foreground-background segmentation.

3. The method of claim 1 wherein the foreground-background segmentation comprises the act of determining pixel frequency of various portions of the image to separate workspace flooring from obstacles.

4. The method of claim 1 wherein the camera is set to automatically take a picture when it is located in a designated position.

5. The method of claim 1 wherein at least one obstacle is tagged with a tag which corresponds to known information about the at least one obstacle, and wherein the tag is capable of being read.

6. The method of claim 5 wherein the tag is a Quick Response (“QR”) Code and wherein the system is capable of reading the QR Code to obtain the corresponding information.

7. The method of claim 6 further comprising the means of determining the location of the tagged obstacle by the reading of the QR Code.

8. The method of claim 5 wherein the camera is the QR scanner.

9. The method of claim 5 further comprising the step of providing a database of known information about the tagged obstacle wherein the information is selected from a group comprising the dimensions, shape, height, length, width of at least one tagged obstacle, or combinations thereof.

10. The method of claim 1 further comprising the step of determining whether older stored images of the workspace at the current position are available, wherein if such images are available taking the following steps: i) determining which stored images are newer than a memory factor; ii) determining which images should be incorporated based on the memory factor; iii) calculating the intensity of each individual image; and iv) overlaying individual images to produce a final map.

11. The method of claim 10 wherein the likelihood of finding an object in a particular area is illustrated based on the hue or intensity of object on the final map.

12. The method of claim 9 further comprising the steps of determining whether older stored images of the workspace at the current position are available, wherein if such images are available taking the following steps: i) determining which stored images are newer than a memory factor; ii) determining which images should be incorporated based on the memory factor; iii) calculating the intensity of each individual image; and iv) overlaying individual images to produce a final map.

13. A method for providing workspace mapping comprising:
(a) employing a camera in a designated position in the workspace;
(b) tagging known obstacles with a tag used to identify the obstacle;
(c) when the camera is in the designated position, taking at least two images of the workspace with the camera wherein the workspace is divided into at least two segments, wherein at least one image is taken at a designated position in each of the said at least two segments;
(d) using image blurring to smooth the at least one two images and thereby reducing noise in the at least two images;
(e) using foreground-background segmentation, recognition of the tag, or both to detect and delineate obstacles in said at least two images; and
(f) drawing contours of said obstacles to produce one map of the workspace whereupon said obstacles are depicted wherein said at least two images are stitched together to form the one map of the workspace;
(g) using template matching to mask portions of the workspace image from inclusion in the map.

14. The method of claim 13 further comprising the step of providing a database of information on potential tagged obstacles wherein the information is selected from a group comprising the dimensions, shape, height, length, width, or combinations thereof.

15. A method for providing workspace mapping comprising:
(a) a workspace comprising a floor and at least one obstacle;
(b) a database with information on at least one potential obstacle, wherein the information is selected from a group comprising the dimensions, shape, height, length, width of at least one tagged obstacle, or combinations thereof;
(c) tagging at least one obstacle in said workspace, wherein said tag corresponds to information contained in the database;
(d) employing a camera in a designated position to view at least a portion of the workspace;
(e) taking at least two images of the workspace with the camera when the camera is in a designated position, wherein said workspace is divided into at least two segments, wherein at least one image is taken at a designated position in each of the said at least two segments;
(f) using image blurring to smooth the at least two images thereby reducing noise in the at least two images;
(g) detecting and delineating obstacles in said at least two images through recognition of the tag, through foreground-background segmentation, or both;
(h) drawing contours of said at least one obstacle to produce one map of the workspace whereupon said obstacles are depicted wherein said at least two images are stitched together to form the one map of the workspace;
(i) using template matching to mask portions of the workspace image from inclusion in the one map; and
(j) determining whether older stored images of the workspace at the current position are available, wherein if such images are available taking the following steps: i) determining which stored images are newer than a memory factor; ii) determining which images should be incorporated based on the memory factor; iii) calculating the intensity of each individual image; and iv) overlaying individual images to produce a final map of the designated area.

16. The method of claim 15 wherein the tag is a QR Code and wherein the foreground-background segmentation is accomplished through a technique chosen from a group comprising watershed transformation, graph partitioning methods, region-growing methods, and integration of multiple cues.

17. The method of claim 2 wherein the foreground-background segmentation is accomplished through a method picked from the group comprising watershed transformation, graph partitioning methods, and region-growing methods, and integration of multiple cues.

Assignees

• Univ Louisiana At Lafayette

Inventors

• Vaughan Joshua
• Rahman Mohammad Sazzad

Classifications

• G06K9/00771

  Physics · mapped topic

• G06T2207/20152

  Watershed segmentation · CPC title

• G06T7/11

  Region-based segmentation · CPC title

• G06T2200/32

  involving image mosaicing · CPC title

• G06T2207/20032

  Median filtering · CPC title