| 陈敬军,傅寅锋.被动声纳目标识别系统设计研究[J].声学技术,2012,(2):147~151 |
| 被动声纳目标识别系统设计研究 |
| The research on the design of passive sonar target recognition system |
| 投稿时间：2011-10-15 修订日期：2012-01-20 |
| DOI： |
| 中文关键词: 目标识别 特征提取 性能评估 声纳 信号处理 |
| 英文关键词: target recognition feature extraction performance evaluation sonar signal processing |
| 基金项目: |
|
| 摘要点击次数: 1326 |
| 全文下载次数: 1304 |
| 中文摘要: |
| 目标识别是声纳的主要功能之一,其性能包括识别正确率、泛化能力和识别距离。由于数据样本的保密特性,声纳目标识别系统设计有其自身特色。在设计过程中,应首先降低对数据样本的依赖,把目标辐射噪声的机理分析、组成、运动规律等知识巧妙地运用到系统设计中;其次还应尽可能提高泛化率,以提高声纳目标识别系统对未见过的样本的正确识别能力。讨论了声纳目标识别流程、声纳目标识别系统的设计方法;在声纳目标识别系统的性能评估中,给出了目标识别距离的估算方法。 |
| 英文摘要: |
| Automatic recognition of underwater targets is one of the key techniques in modern passive sonar systems,the correct recognition rate,generalization and recognition range can be used to evaluate the performance system.Due to the security of target data,the design of classifier for passive sonar target recognition has its own special features.The use of prior knowledge and the improvements of generalization are important points for passive sonar recognition.The classification processes and the design of a classification system are discussed;also the method of how to evaluate range recognition for passive sonar is given. |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |
