机载LiDAR测深(Airborne LiDAR Bathymetry, ALB)海底底质分类能够为海洋资源开发利用、海洋环境保护、海洋工程建设等领域提供基础数据,对海洋活动与海洋科学研究具有重要意义。针对ALB海底底质分类存在的特征冗余问题,本文提出了一种顾及波形和地形特征优选的底质分类算法。在提取波形和地形特征的基础上,构建Relief-F特征优选模型,通过计算各特征在底质分类中的贡献率,实现多元特征优选；然后,利用随机森林、支持向量机(Support Vector Machine, SVM)、BP神经网络三种分类器进行监督分类,提取珊瑚礁、砾石、砂、植被、海岸带五类底质。为验证所提分类方法的有效性,利用西沙甘泉岛实测ALB数据进行实验,结果表明：利用Relief-F算法进行特征优选后,随机森林、SVM与BP神经网络的分类精度分别提高了1.1%、1.1%和2.7%；其中,随机森林底质分类具有更高的分类精度,其总体分类精度和Kappa系数分别达到了95.36%和0.94。本文研究成果能够为海洋工程等领域对海底底质分类需求提供有效的技术支撑。

Airborne LiDAR bathymetry seabed sediment classification can provide basic data for the development and utilization of marine resources, marine environmental protection, marine engineering construction and other fields, which has great significance to marine activities and marine scientific research. To solve the feature redundancy problem in ALB seabed sediment classification, this paper proposes a sediment classification algorithm considering optimal waveform and topographic features. Based on the extracted waveform and topographic features, Relief-F feature optimization model is constructed. And multivariate features optimization is realized by calculating the contribution rate of each feature in the sediment classification. Then, random forest, support vector machine, and BP neural network classifiers are used to classify coral reefs, gravel, sand, vegetation, and coastal zones five types sediments. The proposed method was verified using the ALB data captured around Ganquan Island in the Xisha Archipelago. The experiment results showed that after using the Relief-F algorithm for feature optimization the classification accuracy of random forest, SVM and BP neural network was improved by 1.1%, 1.1% and 2.7%, respectively. The random forest sediment classification has higher classification accuracy, and theoverall accuracy and Kappa coefficient reach 95.36% and 0.94, respectively. The research results in this paper can provide effective technical support for the seabed sediment classification in the fields of marine engineering and other fields.