Full text: Fusion of sensor data, knowledge sources and algorithms for extraction and classification of topographic objects

International Archives of Photogrammetry and Remote Sensing, Vol. 32, Part 7-4-3 W6, Valladolid, Spain, 3-4 June, 1999 
203 
Feature 
Val 
Color Featues 
Charmefl Mean 
91.05 
Charmed! Mean 
1200 
Charmed Mean 
1200 
CharmeW Mean 
75.00 
Charmed Mean 
50.00 
Charmefl StdDev. 
50 23 
Charmed StdDev. 
0.00 
Charmed StdDev. 
0.00 
CharmeW StdDev. 
0.00 
Charmed StdDev. 
0.00 
Form Features 
Area 
52900 
Length/Width 
1.00 
Border Length 
9200 
Boimdg Box / Object Border 
1.00 
Number of Ends 
moo 
Lme SO: length/width 
241 
LmeSO: width 
14.81 
Hierarchy Features 
Level 
1.00 
Nun Neighbours 
4.00 
Num Siiiobjects 
33.00 
N urn Sub Levels 
1.00 
The ‘active’ object is displayed as a black square. The pop-up window shows object information, amount of sub-objects (33) and 
further statistics of the image bands, e.g. for the panchromatic band a standard deviation of 50.23. Latter is very characteristic for this 
type of mountain forest in this particular area. 
Channel 1 = panchromatic band (orthophoto with 1 m resolution) 
Channel 2-5 = SPOT4 bands 1-4 (pixel size 23x23 m 2 ) 
Fig. 1. Screen copy of DELPHI2™. The panchromatic image with 1 m resolution is overlaid with the objects of SPOT4. The image 
shows a mountainous forest road with forest stands on the left and right side of the road. The image represents 423x512 m . 
A grid of SPOT4 pixels registered as outlined spatial objects, each containing 529 (= 23x23) orthophoto pixels, are lying on 
top of the sub-objects from the segmentation process using the panchromatic band.
	        
Waiting...

Note to user

Dear user,

In response to current developments in the web technology used by the Goobi viewer, the software no longer supports your browser.

Please use one of the following browsers to display this page correctly.

Thank you.