ALGORITHM2 - Revision history

Admin at 11:11, 10 March 2021

2021-03-10T11:11:33Z

Admin at 10:29, 10 March 2021

2021-03-10T10:29:56Z

Admin at 10:25, 10 March 2021

2021-03-10T10:25:04Z

Admin at 10:23, 10 March 2021

2021-03-10T10:23:38Z

Admin at 10:12, 10 March 2021

2021-03-10T10:12:54Z

Admin at 10:11, 10 March 2021

2021-03-10T10:11:33Z

Admin at 10:10, 10 March 2021

2021-03-10T10:10:41Z

Admin at 10:09, 10 March 2021

2021-03-10T10:09:29Z

Admin at 10:09, 10 March 2021

2021-03-10T10:09:08Z

← Older revision		Revision as of 11:11, 10 March 2021
Line 24:		Line 24:
	[[File:alg2_wf.jpg\|centre\|800px\|border]]		[[File:alg2_wf.jpg\|centre\|800px\|border]]

		+
		+	====<u>''In a nutshell''</u>====
		+	The key strength of '''Algorithm 2''' is the automatic identification of flooded areas in the SAR data using '''hierarchical tile-based thresholding''' and the optimization of the classification by combining various information sources using '''fuzzy-logic theory''' and '''region growing'''.


	'''For further details the Reader is referred to the dedicated section of the Product Description Document: https://www.gfm_pdd.org/Algorithm2'''		'''For further details the Reader is referred to the dedicated section of the Product Description Document: https://www.gfm_pdd.org/Algorithm2'''
−

@@ Line 29: / Line 29: @@
-----
 ====<u>''References''</u>====
 <sup>[1]</sup> [https://www.sciencedirect.com/science/article/pii/S0924271614001981 <u>Martinis, S., Twele, A., Kersten, J., (2015). A fully automated TerraSAR-X based flood service. ISPRS Journal of Photogrammetry and Remote Sensing, 104, 203-212.</u>] <br>

← Older revision		Revision as of 10:25, 10 March 2021
Line 19:		Line 19:
	The membership degree strongly depends on the position of the crossover point xc (i.e. the half of the width of the fuzzy curve), which is defined by the fuzzy thresholds ''x1'' and ''x2''.The fuzzy threshold values for each element are either determined according to statistical computations or are set empirically. The membership degree of the subsequently, the flood mask is derived through a threshold defuzzification step, which transforms each image element with a membership degree > ''0.6'' into a discrete thematic class. Furthermore, the region-growing tolerance criterion is defined by a relaxed fuzzy threshold of > ''0.45'' based on the composite fuzzy set.		The membership degree strongly depends on the position of the crossover point xc (i.e. the half of the width of the fuzzy curve), which is defined by the fuzzy thresholds ''x1'' and ''x2''.The fuzzy threshold values for each element are either determined according to statistical computations or are set empirically. The membership degree of the subsequently, the flood mask is derived through a threshold defuzzification step, which transforms each image element with a membership degree > ''0.6'' into a discrete thematic class. Furthermore, the region-growing tolerance criterion is defined by a relaxed fuzzy threshold of > ''0.45'' based on the composite fuzzy set.
	Uncertainty information is contained in the fuzzy mask generated over classified water pixels, which takes on values ranging from ''0'' and ''1''.		Uncertainty information is contained in the fuzzy mask generated over classified water pixels, which takes on values ranging from ''0'' and ''1''.
		+
		+
		+	====<u>''Workflow of the algorithm''</u>====
		+	[[File:alg2_wf.jpg\|centre\|800px\|border]]
		+

@@ Line 17: / Line 17: @@
   ''The automatic tile-based thresholding procedure is applied to a given SAR image to select for representative tiles therein. A sub-histogram is generated for a selected tile, based on the backscatter values, one of the parameters of the fuzzy set (left); the corresponding fuzzy standard Z function for backscatter is shown (middle), along with the resulting fuzzy mask and classification maps (right; adapted from Martinis et al. (2015)<sup>[1]</sup>).''
-The membership degree strongly depends on the position of the crossover point xc (i.e. the half of the width of the fuzzy curve), which is defined by the fuzzy thresholds x1 and x2.The fuzzy threshold values for each element are either determined according to statistical computations or are set empirically. The membership degree of the subsequently, the flood mask is derived through a threshold defuzzification step, which transforms each image element with a membership degree > 0.6 into a discrete thematic class. Furthermore, the region-growing tolerance criterion is defined by a relaxed fuzzy threshold of > 0.45 based on the composite fuzzy set.
+The membership degree strongly depends on the position of the crossover point xc (i.e. the half of the width of the fuzzy curve), which is defined by the fuzzy thresholds ''x1'' and ''x2''.The fuzzy threshold values for each element are either determined according to statistical computations or are set empirically. The membership degree of the subsequently, the flood mask is derived through a threshold defuzzification step, which transforms each image element with a membership degree > ''0.6'' into a discrete thematic class. Furthermore, the region-growing tolerance criterion is defined by a relaxed fuzzy threshold of > ''0.45'' based on the composite fuzzy set.
-Uncertainty information is contained in the fuzzy mask generated over classified water pixels, which takes on values ranging from 0 and 1.
+Uncertainty information is contained in the fuzzy mask generated over classified water pixels, which takes on values ranging from ''0'' and ''1''.

@@ Line 19: / Line 19: @@
 The membership degree strongly depends on the position of the crossover point xc (i.e. the half of the width of the fuzzy curve), which is defined by the fuzzy thresholds x1 and x2.The fuzzy threshold values for each element are either determined according to statistical computations or are set empirically. The membership degree of the subsequently, the flood mask is derived through a threshold defuzzification step, which transforms each image element with a membership degree > 0.6 into a discrete thematic class. Furthermore, the region-growing tolerance criterion is defined by a relaxed fuzzy threshold of > 0.45 based on the composite fuzzy set.
 Uncertainty information is contained in the fuzzy mask generated over classified water pixels, which takes on values ranging from 0 and 1.
 '''For further details the Reader is referred to the dedicated section of the Product Description Document: https://www.gfm_pdd.org/Algorithm2'''

@@ Line 12: / Line 12: @@
-The average of the individual membership degrees is computed for each pixel in order to combine all fuzzy elements into a single composite fuzzy set.
+The average of the individual membership degrees is computed for each pixel in order to combine all fuzzy elements into a single composite fuzzy set (see figure below).
-[[File:alg2.jpg|centre|800px|border|balalalalalalal]]
+[[File:alg2.jpg|centre|800px|border]]
 The membership degree strongly depends on the position of the crossover point xc (i.e. the half of the width of the fuzzy curve), which is defined by the fuzzy thresholds x1 and x2.The fuzzy threshold values for each element are either determined according to statistical computations or are set empirically. The membership degree of the subsequently, the flood mask is derived through a threshold defuzzification step, which transforms each image element with a membership degree > 0.6 into a discrete thematic class. Furthermore, the region-growing tolerance criterion is defined by a relaxed fuzzy threshold of > 0.45 based on the composite fuzzy set.