25 October 2010 Unmixing techniques for better segmentation of urban zones, roads, and open pit mines
Author Affiliations +
In this paper the linear unmixing method has been applied in classification of manmade objects, namely urbanized zones, roads etc. The idea is to exploit to larger extent the possibilities offered by multispectral imagers having mid spatial resolution in this case TM/ETM+ instruments. In this research unmixing is used to find consistent regression dependencies between multispectral data and those gathered in-situ and airborne-based sensors. The correct identification of the mixed pixels is key element for the subsequent segmentation forming the shape of the artificial feature is determined much more reliable. This especially holds true for objects with relatively narrow structure for example two-lane roads for which the spatial resolution is larger that the object itself. We have combined ground spectrometry of asphalt, Landsat images of RoI, and in-situ measured asphalt in order to determine the narrow roads. The reflectance of paving stones made from granite is highest compared to another ones which is true for open and stone pits. The potential for mapping is not limited to the mid-spatial Landsat data, but also may be used if the data has higher spatial resolution (as fine as 0.5 m). In this research the spectral and directional reflection properties of asphalt and concrete surfaces compared to those of paving stone made from different rocks have been measured. The in-situ measurements, which plays key role have been obtained using the Thematically Oriented Multichannel Spectrometer (TOMS) - designed in STIL-BAS.
© (2010) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Hristo Nikolov, Hristo Nikolov, Denitsa Borisova, Denitsa Borisova, Doyno Petkov, Doyno Petkov, } "Unmixing techniques for better segmentation of urban zones, roads, and open pit mines", Proc. SPIE 7831, Earth Resources and Environmental Remote Sensing/GIS Applications, 78311L (25 October 2010); doi: 10.1117/12.865027; https://doi.org/10.1117/12.865027

Back to Top