Barrel Detection - Revision history

Joldenburg6: Categorize

2018-06-14T02:07:46Z

Categorize

DavidF: /* '''Distance-Map Acquistion & Shape Identification''' */ extract part of "Progress" section into an "Implementations" section

2005-11-16T19:49:42Z

‎'''Distance-Map Acquistion & Shape Identification''': extract part of "Progress" section into an "Implementations" section

DavidF: /* '''Image Acquisition & Color Identification (#2)''' */ moved "Implementations" section up

2005-11-16T19:48:02Z

‎'''Image Acquisition & Color Identification (#2)''': moved "Implementations" section up

DavidF: /* '''Image Acquisition & Color Identification (#2)''' */ added "Implementations" subsection

2005-11-16T19:47:01Z

‎'''Image Acquisition & Color Identification (#2)''': added "Implementations" subsection

DavidF: /* Progress */ issues with adaptive thresholding when no barrels are present

2005-11-10T20:46:40Z

‎Progress: issues with adaptive thresholding when no barrels are present

DavidF: /* Progress */ updated link

2005-11-08T03:15:14Z

‎Progress: updated link

DavidF: added summary & link to the most promising approach (currently)

2005-11-06T03:00:32Z

added summary & link to the most promising approach (currently)

DavidF: /* Progress */

2005-11-06T02:37:10Z

‎Progress

DavidF: /* Strategy */ provided more detail regarding how the bottom edge of a barrel is determined

2005-11-06T02:34:52Z

‎Strategy: provided more detail regarding how the bottom edge of a barrel is determined

DavidF: /* '''Distance-Map Acquistion & Shape Identification''' */

2005-10-24T03:29:11Z

‎'''Distance-Map Acquistion & Shape Identification'''

← Older revision		Revision as of 02:07, 14 June 2018
Line 1:		Line 1:
		+	[[Category:IGVC]][[Category:2005-2006]]
	[[Image:IdentifiedBarrel.png\|thumb\|right\|A barrel, and its bounding box, as identified by '''BarrelBlobFinder''']]		[[Image:IdentifiedBarrel.png\|thumb\|right\|A barrel, and its bounding box, as identified by '''BarrelBlobFinder''']]

@@ Line 60: / Line 60: @@
 #** Difficult to implement programmatically.
 #** Requires two camcorders. Currently, we only have one.
 ==== Progress ====
-* [[User:SpencerC|Spencer]] already has a rudimentary implementation of a steroscopic imaging algorithm.
+* ''no further progress''
 == A Note on Notation ==
 In the above steps, items surrounded with parentheses are ''data''. Other items are ''analyses'' or ''filters''.

@@ Line 31: / Line 31: @@
 ** Once the bottom edge of a barrel is identified, scan horizontal line-segments above the bottom edge, starting from the bottom and moving up. When an insufficient percentage of the current scan line-segment contains orange/white pixels, mark the line-segment as being the top edge of the barrel.
 ** Once the top and bottom edges of a barrel have been identified, record the bounding box of the barrel and delete the barrel from the image (clear all of the pixels within the bounding box). Continue scanning.
 ==== Progress ====
@@ Line 37: / Line 40: @@
 * I am investigating the usage of [[Adaptive Thresholding|adaptive thresholding]] to dynamically determine appropriate values for the threshold-style parameters of the '''BarrelBlobFinder''' filter. --[[User:DavidF|David]] 20:48, 20 Oct 2005 (EDT)
 ** My experiments with adaptive thresholding have been quite successful in detecting barrels when they are present in an image. In images that contain no barrels, however, the adaptive thresholding algorithm performs very poorly. Until this issue is resolved, '''BarrelBlobFinder''' will continue to use static thresholds by default. --[[User:DavidF|David]] 15:46, 10 Nov 2005 (EST).
 === '''Distance-Map Acquistion & Shape Identification''' ===

@@ Line 37: / Line 37: @@
 * I am investigating the usage of [[Adaptive Thresholding|adaptive thresholding]] to dynamically determine appropriate values for the threshold-style parameters of the '''BarrelBlobFinder''' filter. --[[User:DavidF|David]] 20:48, 20 Oct 2005 (EDT)
 ** My experiments with adaptive thresholding have been quite successful in detecting barrels when they are present in an image. In images that contain no barrels, however, the adaptive thresholding algorithm performs very poorly. Until this issue is resolved, '''BarrelBlobFinder''' will continue to use static thresholds by default. --[[User:DavidF|David]] 15:46, 10 Nov 2005 (EST).
 === '''Distance-Map Acquistion & Shape Identification''' ===

@@ Line 34: / Line 34: @@
 ==== Progress ====
 * I have written an experimental image filter called '''BarrelBlobFinder''', included in [[ImageFilterDemo]] [[:Image:ImageFilterDemo v1 2 3.zip|v1.2.3]], that implements a more complex version of this algorithm. It works quite well, although it could benefit from some more calibration. --[[User:DavidF|David]] 23:22, 19 Oct 2005 (EDT)
 * I am investigating the usage of [[Adaptive Thresholding|adaptive thresholding]] to dynamically determine appropriate values for the threshold-style parameters of the '''BarrelBlobFinder''' filter. --[[User:DavidF|David]] 20:48, 20 Oct 2005 (EDT)
-* I have enhanced '''BarrelBlobFinder''' to determine the width of barrels a ''lot'' more accurately. Check it out in [[ImageFilterDemo]] [[:Image:ImageFilterDemo_v1_2_5.zip|v1.2.5]]. --[[User:DavidF|David]] 21:38, 5 Nov 2005 (EST)
+** My experiments with adaptive thresholding have been quite successful in detecting barrels when they are present in an image. In images that contain no barrels, however, the adaptive thresholding algorithm performs very poorly. Until this issue is resolved, '''BarrelBlobFinder''' will continue to use static thresholds by default. --[[User:DavidF|David]] 15:46, 10 Nov 2005 (EST).
 === '''Distance-Map Acquistion & Shape Identification''' ===

← Older revision		Revision as of 03:00, 6 November 2005
Line 1:		Line 1:
	[[Image:IdentifiedBarrel.png\|thumb\|right\|A barrel, and its bounding box, as identified by '''BarrelBlobFinder''']]		[[Image:IdentifiedBarrel.png\|thumb\|right\|A barrel, and its bounding box, as identified by '''BarrelBlobFinder''']]
		+
		+	'''Objective:''' Determine bounding boxes for the barrels visible in a camera image.
		+
		+	Jump to the [[#Image Acquisition & Color Identification (#2)\|most promising approach]] for detecting barrels.

	== Approaches ==		== Approaches ==

@@ Line 22: / Line 22: @@
 * '''Algorithm'''
-** Scan horizontal lines of image, starting from the bottom, and moving up. When current scan line intersects a sufficient number of orange pixels, mark the orange segment of the line as being the bottom edge of a barrel.
+** Scan horizontal lines of image, starting from the bottom, and moving up. When current scan line intersects a sufficient number of orange pixels, mark the scan line as containing the bottom edge of one or more barrels.
-** Once the bottom edge of a barrel is identified, scan horizontal line-segments above the bottom edge, starting from the bottom and moving up. When an insufficient percentage of current scan line-segment contains orange/white pixels, mark the line-segment as being the top edge of the barrel.
+** Find the interval of orange pixels on the scan line within the X% and (100-X)% quartiles (where X is a parameter - typically 5%). Mark this interval as being the bottom edge of a barrel. (The usage of quartiles is to ensure robustness in the prescense of orange pixel noise.)
 ** Once the top and bottom edges of a barrel have been identified, record the bounding box of the barrel and delete the barrel from the image (clear all of the pixels within the bounding box). Continue scanning.

@@ Line 45: / Line 45: @@
 #* Obtains a distance-map along a ''plane'' projected away from the robot.
 #* ''Pros''
-#** [[User:SpencerC|Spencer]] already has a rudimentary implementation of a steroscopic imaging algorithm.
+#** none significant
 #* ''Cons''
 #** Difficult to implement programmatically.
@@ Line 51: / Line 51: @@
 ==== Progress ====
-* ''none so far''
+* [[User:SpencerC|Spencer]] already has a rudimentary implementation of a steroscopic imaging algorithm.
 == A Note on Notation ==
 In the above steps, items surrounded with parentheses are ''data''. Other items are ''analyses'' or ''filters''.