Land cover classification with multi-source data using evidential reasoning approach

Abstract

Land cover classification is the core of converting satellite imagery to available geographic data. However, spectral signatures do not always provide enough information in classification decisions. Thus, the application of multi-source data becomes necessary. This paper presents an evidential reasoning (ER) approach to incorporate Landsat TM imagery, altitude and slope data. Results show that multi-source data contribute to the classification accuracy achieved by the ER method, whereas play a negative role to that derived by maximum likelihood classifier (MLC). In comparison to the results derived based on TM imagery alone, the overall accuracy rate of the ER method increases by 7.66% and that of the MLC method decreases by 8.35% when all data sources (TM plus altitude and slope) are accessible. The ER method is regarded as a better approach for multi-source image classification. In addition, the method produces not only an accurate classification result, but also the uncertainty which presents the inherent difficulty in classification decisions. The uncertainty associated to the ER classification image is evaluated and proved to be useful for improved classification accuracy.

Monitoring of Land Use–Land Cover Change and Potential Causal Factors of Climate Change in Jhelum District, Punjab, Pakistan, through GIS and Multi-Temporal Satellite Data

“…Climate variation showed the most substantial influence on the adaptation of LULC categories in numerous regions of the land [41,65,66]. Similarly, alternation in climatic impacts on the biosphere of the land has a close link with hydrological and energy chains, explaining the effect on the vegetation index (VI) where it increases to its highest quantity [67].…”

“…RS data are a helpful tool in the mapping of LULC [41,42]. For LULC mapping, the temporal Landsat sensor data of the Landsat-7 Enhanced Thematic Mapper (ETM), Landsat-5 Thematic Mapper (TM) with ETM+ [43], and Landsat-8 Operational Land Imager (OLI) have been extensively used to discover the variation in the NDVI, NDBI, and LULC [33].…”

An automatic water detection approach based on Dempster-Shafer theory for multi-spectral images

“…For instance, an evidential model is proposed to deal with the statistical segmentation of multi-sensor images, taking into account contextual information via Markovian fields [11]. An incorporation of Landsat TM imagery, altitude and slope data through evidential reasoning improved classification accuracy thanks to uncertainty introduced in the classification system [12]. A multidimensional evidential reasoning (MDER) approach was proposed to estimate change detection from the fusion of heterogeneous remote sensing images [13].…”

A novel unsupervised Levy flight particle swarm optimization (ULPSO) method for multispectral remote-sensing image classification

“…Currently, it is widely accepted that remote sensing is the mainstream means to produce land cover data because of its many advantages over fieldwork including cost-effectiveness, instantaneous measurement, synoptic view, and high multi-temporal coverage (Li et al 2016b). In fact, classifying remote sensing image to available land cover data is regarded as one of the core tasks of the remote sensing community (Li et al 2011;Wilkinson 2005).…”