Developments in Landsat Land Cover Classification Methods: A Review

Abstract

Land cover classification of Landsat images is one of the most important applications developed from Earth observation satellites. The last four decades were marked by different developments in land cover classification methods of Landsat images. This paper reviews the developments in land cover classification methods for Landsat images from the 1970s to date and highlights key ways to optimize analysis of Landsat images in order to attain the desired results. This review suggests that the development of land cover classification methods grew alongside the launches of a new series of Landsat sensors and advancements in computer science. Most classification methods were initially developed in the 1970s and 1980s; however, many advancements in specific classifiers and algorithms have occurred in the last decade. The first methods of land cover classification to be applied to Landsat images were visual analyses in the early 1970s, followed by unsupervised and supervised pixel-based classification methods using maximum likelihood, K-means and Iterative Self-Organizing Data Analysis Technique (ISODAT) classifiers. After 1980, other methods such as sub-pixel, knowledge-based, contextual-based, object-based image analysis (OBIA) and hybrid approaches became common in land cover classification. Attaining the best classification results with Landsat images demands particular attention to the specifications of each classification method such as selecting the right training samples, choosing the appropriate segmentation scale for OBIA, pre-processing calibration, choosing the right classifier and using suitable Landsat images. All these classification methods applied on Landsat images have strengths and limitations. Most studies have reported the superior performance of OBIA on different landscapes such as agricultural areas, forests, urban settlements and wetlands; however, OBIA has challenges such as selecting the optimal segmentation scale, which can result in over or under segmentation, and the low spatial resolution of Landsat images. Other classification methods have the potential to produce accurate classification results when appropriate procedures are followed. More research is needed on the application of hybrid classifiers as they are considered more complex methods for land cover classification.

A Review of Free Optical Satellite Imagery for Watershed-Scale Landscape Analysis

“…Review articles have addressed vegetation mapping (Xie et al, 2008), land cover classification (Phiri & Morgenroth, 2017), forest inventories , and large area mapping techniques (Gómez et al, 2016; Hansen & Loveland, 2012 …”

“…Classification methods can be unsupervised, supervised, or object-oriented (Phiri & Morgenroth, 2017). Unsupervised classification techniques group pixels based on similar spectral values with limited user input.…”

“…Land cover classification was one of the earliest uses of satellite imagery (e.g., Anderson et al, 1976;Figure 5, F) and multiple classification techniques are available (Phiri & Morgenroth, 2017). e evolution of land cover over time is a topic of extensive research .…”

“…e availability of FOSI has enabled the development of free online visualization tools (see Appendix A), free open source remote sensing soware (see Appendix B), and free analysis-ready remote sensing products (see Appendix C). e abundance of FOSI has empowered natural resource managers, researchers, and others to increase, and ultimately improve, the monitoring and quantification of watershed-scale environmental change.Review articles have addressed vegetation mapping (Xie et al, 2008), land cover classification (Phiri & Morgenroth, 2017), forest inventories , and large area mapping techniques (Gómez et al, 2016; Hansen & Loveland, 2012 …”

Land Cover Change in Northern Botswana: The Influence of Climate, Fire, and Elephants on Semi-Arid Savanna Woodlands

“…In this study, we used a hybrid unsupervised ISO Cluster supervised maximum likelihood approach to classify land cover based on contextual knowledge [98]. Our use of PCA helped reduce spectral overlap and redundancy of image data, which has been shown to improve model discrimination between vegetation and bare ground in savannas [99].…”