Land Cover Image Segmentation Based on Individual Class Binary Masks
Document Type
Article
Publication Date
12-30-2021
Abstract
Remote sensing techniques have been developed over the past decades to acquire data without being in contact of the target object or data source. Their application on land-cover image segmentation has attracted significant attention during recent years. With the help of satellites, scientists and researchers can collect and store high-resolution image data that can be further be processed, segmented, and classified. However, these research results have not yet been synthesized to provide coherent guidance on the effect of variant land-cover segmentation processes. In this paper, we present a novel model that augments segmentation using smaller networks to segment individual classes. The combined network is trained on the same data but with the masks, combined and trained using categorical cross entropy. Experimental results show that the proposed method produces the highest mean IoU (Intersection of Union) as compared against several existing state-of-the-art models on the DeepGlobe dataset.
Identifier
85121141956 (Scopus)
Publication Title
International Journal of Pattern Recognition and Artificial Intelligence
External Full Text Location
https://doi.org/10.1142/S0218001421540343
ISSN
02180014
Issue
16
Volume
35
Recommended Citation
Somasunder, Sathyanarayanan and Shih, Frank Y., "Land Cover Image Segmentation Based on Individual Class Binary Masks" (2021). Faculty Publications. 3573.
https://digitalcommons.njit.edu/fac_pubs/3573