2026-05-24T22:34:46Z https://meral.edu.mm/oai

oai:meral.edu.mm:recid/6324 2021-12-13T04:26:40Z 1582963342780:1605779935331 user-uit

Object-based Urban Land Use Classification using Deep Belief Network Su Wai Tun Khin Mo Mo Tun Urban land use information is very important for urban planning, regional administration and management. Classification of urban land use from high resolution images remains a challenging task, due to the extreme difficulties in differentiating complex spatial patterns to derive high-level semantic labels. Deep learning is a powerful state-of-the-art technique for image processing including remote sensing images. The Deep Belief Networks (DBN) model is a widely investigated and deployed deep learning architecture. It combines the advantages of unsupervised and supervised learning and can archive good classification performance. In this paper, deep belief network model is used to improve the performance of object-based land use classification. First, to achieve an object-based image representation, the original image is segmented into objects by graphbased minimal-spanning-tree segmentation algorithm. Second, spectral, spatial and texture features for each object are extracted. Then all features are put into deep belief network and the parameters of the network using training samples are trained. Finally, all objects are classified by network. 2018-11-02 http://hdl.handle.net/20.500.12678/0000006324 https://meral.edu.mm/records/6324