期刊
LANDSCAPE ECOLOGY
卷 34, 期 11, 页码 2487-2492出版社
SPRINGER
DOI: 10.1007/s10980-019-00916-6
关键词
Image processing; Error propagation; Imbalanced classes; Map accuracy; Comprehensive assessment
资金
- USDA National Institute of Food and Agriculture McIntire Stennis Project [IND011523MS]
- National Natural Science Foundation of China [41471137]
- National Key R&D Program of China [2016YFC0502902]
- Natural Science Foundation of Fujian Province [2017J01468]
Context Image classification is routine in a variety of disciplines, and analysts rely on accuracy metrics to evaluate the resulting maps. The most frequently used accuracy metric in Earth resource remote sensing is overall accuracy. However, the inherent properties of this accuracy metric make it inappropriate as the single metric for map assessment, particularly when a map contains imbalanced categories. Objectives We discuss four noteworthy problems with overall accuracy. Under circumstances frequently encountered, overall accuracy is misleading or misinterpreted. Methods Literature review, hypothetical examples, and mathematic equations are used to prove overall accuracy is a poor general indicator of map quality. Conclusions Any research that involves classification techniques or a map product that is evaluated only with overall accuracy may be unreliable. It is necessary for map providers to publish the error matrix and its development procedure so that map users can computer whatever metrics as they wish.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据