Co-Authors:
Cohen, Y., Dept. of Transp. and GeoInfo. Eng., Faculty of Civil/Environmental Eng., Technion - Israel Inst. of Technol., Haifa 32000, Israel, Institute of Agricultural Eng., Agricultural Res. Organization, Volcani Center, Bet Dagan 50250, Israel
Shoshany, M., Dept. of Transp. and GeoInfo. Eng., Faculty of Civil/Environmental Eng., Technion - Israel Inst. of Technol., Haifa 32000, Israel
Doytsher, Y., Dept. of Transp. and GeoInfo. Eng., Faculty of Civil/Environmental Eng., Technion - Israel Inst. of Technol., Haifa 32000, Israel
Abstract:
A pseudo-hydrologic method was developed for road extraction from medium-resolution satellite images. Transformation of image brightness into a Pseudo Digital Elevation Model (PDEM) allows emulation of hydrologic flow. Flow direction and flow accumulation are then calculated for each image pixel using hydrological GIS routines. Road segments are recognized by setting a minimal threshold to the pseudo-flow accumulation. Implementation of the technique to extract major roads and railways from a Spot-panchromatic image yielded high recognition accuracy (90 percent). In another experiment, this technique was used to extract roads in dense urban areas from multispectral IKONOS images. Moderate success (70 percent) was achieved in this task.
תפריט נגישות
ניגודיות עדינה
מונוכרום
הדגשת קישורים
חסימת אנימציה
פונט קריא
סגור
איפוס הגדרות נגישות
להורדת מודול נגישות חינם
