期刊名称：American Journal of Geographic Information System
印刷版ISSN：2163-1131
电子版ISSN：2163-114X
出版年度：2020
卷号：9
期号：1
页码：33-45
DOI：10.5923/j.ajgis.20200901.04
语种：English
出版社：Scientific & Academic Publishing Co.
摘要：Land cover is a complex parameter because it represents the relationship between socio-economic activities and regional environmental changes, which is why it is important to review and update it periodically. This paper seeks to navigate via a range of subtopics on Land Cover Mapping (LCM) using Remote Sensing (RS) technology for providing enough information that play a significant and prime role in planning, management and monitoring programmes at local, regional and national levels. The literature review structure is described as; give a review of information type and sources with highlights on the strengths and weaknesses of distinct RS information as well as distinct variables extracting from RS information that have been used for LCM. Similarly, the highpoint was done on the LCM techniques which comprise conventional and remote sensed techniques for accurate LCM. For detailed knowledge of the methods, phases, and algorithms of Image classification (IC) for LCM, a brief overview is provided and some issues that influence the efficiency and accuracy of the IC methods were also discussed. From this investigated literature, the most common RS data used for LCM are multispectral, hyperspectral, light detection and ranging (LiDAR), and radio detection and ranging (radar). The choice of appropriate RS data for LCM, however, relies on data accessibility and the particular goal to be obtained and type of classification algorithms. Non-parametric classification algorithms tend to be superior to parametric classification algorithms in LCM using RS data. Nevertheless, the issue which non-parametric algorithms are better than other LCM algorithms was not normally answered. As conclusion, LCM efficiency is influenced by numerous variables like landscape, sampling schedule, training selection techniques and training size, type of non-parametric algorithms, raw data, etc. Thus, these influenced variables need to be addressed before LCM using RS data.
关键词：Land cover mapping techniques; Image classification process; Remote sensing data
