Abstract
Water body segmentation is a difficult task because of complex shapes, edges, sizes, and the surroundings. DeeplabV3+ has proven to perform well on segmentation tasks with multi-scale features. Atrous Spatial Pyramid Pooling (ASPP) module present in Deeplab models helps to increase the field of view for extracting multi-scale features. In this work, we analyze how the ASPP extracts multi-scale features in DeeplabV3+ by comparing the performance of Deeplabv3+ model with ASPP and without ASPP for water segmentation task. The dataset used for this study is a public dataset that contains RGB satellite images and corresponding masks from sentine1-2 A/B satellite. The evaluation metrics used for this study are IoU score, Dice score, Recall and Precision. The results obtained from the study shows that DeeplabV3+ model with ASPP extract the water bodies with different sizes. It also captures the boundaries accurately compared to the model without ASPP module.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have