高光谱图像深度模糊核聚类的洋底锰结核识别  

Recognition of ocean floor manganese nodules by deep kernel fuzzy C-means clustering of hyperspectral images

作　　者：张启忠[1,2] 郑恩迪 王叶剑 高发荣 Zhang Qizhong;Zheng Endi;Wang Yejian;Gao Farong(Laboratory of Underwater Intelligent Equipment,Hangzhou Dianzi University,Hangzhou 310018,China;School of Automation,Hangzhou Dianzi University,Hangzhou 310018,China;Second Institute of Oceanography,Ministry of Natural Resources,Hangzhou 310012,China)

机构地区：[1]杭州电子科技大学水下智能装备实验室,杭州310018 [2]杭州电子科技大学自动化学院,杭州310018 [3]自然资源部第二海洋研究所,杭州310012

出　　处：《中国图象图形学报》2021年第8期1886-1895,共10页Journal of Image and Graphics

基　　金：自然资源部海底科学重点实验室开放基金项目(KLSG2002)。

摘　　要：目的海洋资源调查是海洋科学研究的重要组成部分,对于开发利用海洋资源、保护海洋环境有重要意义。将深海高光谱图像用于调查洋底锰结核资源,相比传统图像方法信息更为全面,识别更为准确。但是高光谱方法中用于有监督分类识别的分类器需要人工标定的标签,这在深海环境中是较为困难的。针对这一局限性,本文提出了一种融合深度网络与模糊核聚类的深度模糊核聚类(deep kernel fuzzy C-means,DKFCM)算法,实现对洋底锰结核高光谱图像的无监督聚类。方法DKFCM由随机深度卷积网络(Rdnet)及改进的模糊核聚类算法两大模块组成。Rdnet通过降维、随机图块卷积及非线性激活操作的循环,实现对高光谱图像浅层及深层特征的提取,融合这两类特征作为后续聚类识别的输入。改进的模糊核聚类算法先用欧氏距离计算初始聚类中心,再用模糊核聚类的方法以实现海洋资源的准确分类。结果实验结果表明,DKFCM无监督聚类能有效聚类洋底资源,对锰结核的聚类准确率达到76.59%,相比单用K-means聚类提高了20.99%,相比经Rdnet提取特征后再用K-means聚类提高了13.76%,对比实验表明DKFCM算法在无标签数据的情况下也能达到良好的准确率。结论本文所提的高光谱深度模糊核聚类方法,实现了深海锰结核的无监督聚类,可以用于海洋资源量的评估。Objective Marine resource survey is an important component of marine scientific research,which is of great significance to the development and utilization of marine resources and the protection of the marine environment.Polymetallic nodules,otherwise known as manganese nodules,are commonly distributed in the submarine plains of the water depth of 4~6 km.These nodules contain metallic elements,such as manganese,nickel,copper,and cobalt.Polymetallic nodules are regarded as an important oceanic mineral resource.The rich metallic elements of these nodules are relatively rare in terrestrial resources,but they are widely used.Influential countries and research institutions are currently conducting forward-looking investigations on the potential of deep-sea manganese nodules in view of its crucial strategic value.Traditional methods for investigating manganese nodules on the ocean floor are based on mechanical sampling,multi-beam acoustic remote sensing,and optical images.In recent years,the application of hyperspectral imaging technology in deep-sea resource surveys has gradually attracted the attention of researchers.Hyperspectral image refers to the integration of hundreds of continuous spectral bands and high-resolution image data.Each pixel corresponds to a continuous spectral curve,and objects of different materials obtain their unique"optical fingerprints".Using deep-sea hyperspectral images to investigate manganese nodule resources on the ocean floor has more comprehensive information and accurate identification than traditional image methods.This situation is precisely because many prospecting methods based on hyperspectral images have been proposed and applied to the investigation of ocean floor manganese nodules,such as the active hyperspectral imager mounted underwater,due to the superiority of these images in spectral characteristics compared with ordinary images.Platforms or remotely operated submersibles conduct surveys of seabed resources.At present,most processing methods for underwater hyperspectral im

关 键 词：高光谱图像 深度学习 卷积网络 特征提取 聚类 锰结核 

分 类 号：TP79[自动化与计算机技术—检测技术与自动化装置]