Also, even for relatively well-studied areas, different field data sources can lead to dissimilar or biased results of species distributions and diversity. Such ground based methods require skilled individuals and significant amount of time in the field, making them. Exhaustive ground surveys and inventories of species in field to accumulate biogeographical data on species distributions. After segmentation or image classification results were analyzed to give the exact measure of greenness in terms of area in hectares or square kilometers calculated over years.īiogeographers are continuously researching methods to map species distributions and diversity that can have significant applications for conservation planning.
The input images were enhanced using the histogram equalization technique and then segmented using supervised and unsupervised classification with the help of ERDAS software. Both the methods are used for object detection and classification. This paper describes the analysis of supervised and unsupervised techniques of remotely sensed images for land cover classification and to evaluate greenness in terms of the area over a period of time. Both the techniques give different outputs and accuracy parameters. Image classification is categorized into two techniques, namely supervised and unsupervised techniques. A remotely sensed image is at first pre-processed to remove anomalies from it, thus resulting in a clear and informative image.
Satellite images are widely used in urban planning and growth analysis with different technology being developed.
0 kommentar(er)
