Sodar image segmentation by fuzzy c-means

Sodar facsimile records provide meteorological information of the atmospheric boundary layer (ABL). Segmentation of sodar image (digitised sodar record) is vital for subsequent interpretation of ABL structure. The problem of segmentation is presented here as classification problem. Fuzzy c-means classification algorithm has been adopted for segmentation purpose using a set of four feature vectors calculated over a mask such that they characterise the nature of local grey value distribution. The classified images are also compared to another segmentation technique. The results presented prove the definite merits of the proposed technique.