Answers are grounded in this paper and cite their sources.
Comparative analysis reveals optimal classification methods for key marine targets in complex environments, indicating significant implications for marine resource management.
随着对复杂广域的海洋环境进行探索,有效识别海冰、浒苔、海面溢油等海洋目标对维护海洋权益具有重要意义。由于海冰等目标表现形式比较多样,理化特性和光学特性不同,以及海面光照变化、海水运动等原因,给基于海背景下的目标分类带来了很大挑战。对此,借助机载高光谱图像图谱合一的独特优势可获取目标的更多信息,利用光谱角匹配算法(spectral angle matching,SAM)、最大似然法(maximum likelihood classification,MLC)和支持向量机(support vector machine,SVM)3种经典分类算法对基于海背景下的海冰、浒苔和溢油目标进行分类,从定性和定量的角度比较发现,SAM算法对浒苔分类结果较差,Kappa系数为0.67, MLC算法对于海冰和溢油分类结果较差,分类区域边界较模糊; SVM算法分类效果较好,总体精度、平均准确度以及Kappa系数均在0.9以上,整体较为稳定。
No takes yet. Share an insight, caveat, or question.
LI et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: