Difference between revisions of "Barrel Detection"
Jump to navigation
Jump to search
(split up approaches into subsections) |
(→'''Image Acquisition & Color Identification (#2)''': progress update: initial implementation of algorithm is complete) |
||
| Line 14: | Line 14: | ||
* Find orange pixels (on barrel) with <tt>(Pixels) => Red - Green => High-Pass Threshold => (Orange pixels)</tt> | * Find orange pixels (on barrel) with <tt>(Pixels) => Red - Green => High-Pass Threshold => (Orange pixels)</tt> | ||
* Scan horizontal lines of image, starting from the bottom, and moving up. When currect scan line intersects a sufficient number of orange pixels, mark the orange segment of the line as being the bottom edge of a barrel. Once the bottom edge of a barrel is identified, ignore all pixels above the bottom edge. Continue scanning. | * Scan horizontal lines of image, starting from the bottom, and moving up. When currect scan line intersects a sufficient number of orange pixels, mark the orange segment of the line as being the bottom edge of a barrel. Once the bottom edge of a barrel is identified, ignore all pixels above the bottom edge. Continue scanning. | ||
| + | |||
| + | ==== Progress ==== | ||
| + | * I have written an experimental image filter called '''BarrelBlobFinder''', included in [[ImageFilterDemo]] [[:Image:ImageFilterDemo v1 2 3.zip|v1.2.3]], that implements this algorithm. It works quite well, although it could benefit from some more calibration. --[[User:DavidF|David]] 23:22, 19 Oct 2005 (EDT) | ||
=== '''Distance-Map Acquistion & Shape Identification''' === | === '''Distance-Map Acquistion & Shape Identification''' === | ||
Revision as of 22:25, 19 October 2005
Contents
Approaches
The following approaches have been considered:
Image Acquisition & Color Identification (#1)
Strategy
- Find orange pixels (on barrel) with (Pixels) => Red - Green => High-Pass Threshold => (Orange pixels)
- Find while pixels (on barrel) with (Pixels) => Saturation => Low-Pass Threshold => (White pixels)
- (Orange pixels) => Blob seperation => Orange stripes (Bounding Boxes)
- (Orange pixels) => Blob seperation => White stripes (Bounding Boxes)
- {Orange stripes (Bounding Boxes), White stripes (Bounding Boxes)} => Blob merging => Barrels (Bounding Boxes)
Image Acquisition & Color Identification (#2)
Strategy
- Find orange pixels (on barrel) with (Pixels) => Red - Green => High-Pass Threshold => (Orange pixels)
- Scan horizontal lines of image, starting from the bottom, and moving up. When currect scan line intersects a sufficient number of orange pixels, mark the orange segment of the line as being the bottom edge of a barrel. Once the bottom edge of a barrel is identified, ignore all pixels above the bottom edge. Continue scanning.
Progress
- I have written an experimental image filter called BarrelBlobFinder, included in ImageFilterDemo v1.2.3, that implements this algorithm. It works quite well, although it could benefit from some more calibration. --David 23:22, 19 Oct 2005 (EDT)
Distance-Map Acquistion & Shape Identification
Strategy
- Scan distances in front of robot by some method, obtaining a distance-map.
- Find/distinguish the "plateaus" of the graph. Mark each "plateau" as the near-edge/near-face of a barrel.
Methods to Obtain a Distance Map
- SICK
- Obtains a distance-map along a line projected away from the robot.
- Easy to implement programmatically.
- Expensive hardware. May be able to get from the CS department
- Stereoscopic Imaging
- Obtains a distance-map along a plane projected away from the robot.
- Difficult to implement programmatically.
- Requires two camcorders. Currently, we only have one.
A Note on Notation
In the above steps, items surrounded with parentheses are data. Other items are analyses or filters.
