摘要
随着全球变暖和全球贸易的增长,西北航道的经济效益日渐突出。但是西北航道内浮冰的存在对船舶的航行有一定的影响。鉴于此,利用遥感影像的灰度和灰度共生矩阵组成组合特征构建训练样本,利用支持向量机(Support Vector Machine,SVM)对样本进行训练,实现海冰、海水的分类,并借助蚁群算法进行可通行性分析。实验结果证明,相比较传统单一特征分类结果,本文提出的组合特征的方法能够在一定程度上提高分类正确率,有效区分遥感影像中的海水、海冰,为船舶航行的可行性提供依据。
With global warming and the growth of global trade,the economic benefit of the Northwest Passage have become increasingly significant.However,the existence of floating ice in the Northwest Passage has a certain influence on the navigation of ships.In view of this,this paper used the combination of gray-level and gray-level co-occurrence matrices of remote sensing images to construct training samples,uses support vector machine(SVM)to train the samples to achieve classification of sea ice and sea water,and analyzed the results with ant colony algorithm.The classification accuracy of experimental results were verified to a certain extent compared with the traditional single feature classification results.It was proven that the method could effectively distinguish sea water and sea ice in remote sensing images and provided the basis for the feasibility of ship navigation.
作者
潘荔君
PAN Lijun(China Railway First Survey and Design Institute Group Company Limited, Xi’an Shaanxi 710043, China)
出处
《北京测绘》
2021年第7期915-920,共6页
Beijing Surveying and Mapping