典型文献
Semisupervised heterogeneous ensemble for ship target discri-mination in synthetic aperture radar images
文献摘要：
Ship detection using synthetic aperture radar (SAR) plays an important role in marine applications. The existing methods are capable of quickly obtaining many candidate targets, but numerous non-ship objects may be wrongly detected in complex backgrounds. These non-ship false alarms can be excluded by training discriminators, and the desired accuracy is obtained with enough verified samples. However, the reliable verification of targets in large-scene SAR images still inevitably requires manual interpretation, which is difficult and time consuming. To address this issue, a semisupervised heterogeneous ensemble ship target discrimination method based on a tri-training scheme is proposed to take advantage of the plentiful candidate targets. Specifically, various features commonly used in SAR image target discrimination are extracted, and several acknowledged classification models and their classic variants are investigated. Multiple discriminators are constructed by dividing these features into different groups and pairing them with each model. Then, the performance of all the discriminators is tested, and better discriminators are selected for implementing the semisupervised training process. These strategies enhance the diversity and reliability of the discriminators, and their heterogeneous ensemble makes more correct judgments on candidate targets, which facilitates further positive training. Experimental results demonstrate that the proposed method outperforms traditional tri-training.
文献关键词：
中图分类号：
作者姓名：
Yongxu Li;Xudong Lai;Mingwei Wang
作者机构：
School of Remote Sensing and Information Engineering,Wuhan University,Wuhan 430079,China;School of Computer Science,Hubei University of Technology,Wuhan 430068,China
文献出处：
引用格式：
[1]Yongxu Li;Xudong Lai;Mingwei Wang-.Semisupervised heterogeneous ensemble for ship target discri-mination in synthetic aperture radar images)[J].海洋学报（英文版）,2022(07):180-192
A类：
Semisupervised,wrongly,discriminators,semisupervised
B类：
heterogeneous,ensemble,ship,synthetic,aperture,radar,images,Ship,detection,using,SAR,plays,important,role,marine,applications,existing,methods,are,capable,quickly,obtaining,many,candidate,targets,but,numerous,objects,may,detected,complex,backgrounds,These,false,alarms,excluded,by,training,desired,accuracy,obtained,enough,verified,samples,However,reliable,verification,large,scene,still,inevitably,requires,manual,interpretation,which,difficult,consuming,To,address,this,issue,discrimination,tri,scheme,proposed,take,advantage,plentiful,Specifically,various,features,commonly,used,extracted,several,acknowledged,classification,models,their,classic,variants,investigated,Multiple,constructed,dividing,these,into,different,groups,pairing,them,each,Then,performance,tested,better,selected,implementing,process,strategies,enhance,diversity,reliability,makes,more,correct,judgments,facilitates,further,positive,Experimental,results,demonstrate,that,outperforms,traditional
AB值：
0.576216
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
