| 注册
首页|期刊导航|中国光学(中英文)|用于水下声呐目标检测的弱特征共焦通道调控方法

用于水下声呐目标检测的弱特征共焦通道调控方法

何梦云 何自芬 张印辉 陈光晨 张枫

中国光学(中英文)2024,Vol.17Issue(6):1281-1296,16.
中国光学(中英文)2024,Vol.17Issue(6):1281-1296,16.DOI:10.37188/CO.2024-0031

用于水下声呐目标检测的弱特征共焦通道调控方法

Weak feature confocal channel regulation for underwater sonar target detection

何梦云 1何自芬 1张印辉 1陈光晨 1张枫1

作者信息

  • 1. 昆明理工大学机电工程学院,云南 昆明 650500
  • 折叠

摘要

Abstract

Visual detection of sonar images is a critical technology in complex water resource exploration and underwater foreign object target detection.Aiming at the problems of weak features and background informa-tion interference of small targets in sonar images,we propose a weak feature confocal channel modulation al-gorithm for underwater sonar target detection.First,in order to improve the model's ability to capture and characterize the information of weak targets,we design a weak target-specific activation strategy and intro-duce an a priori frame scale calibration mechanism to match the underlying semantic feature detection branch to improve the accuracy of small target detection;second,we apply the global information aggregation mod-ule to deeply excavate the global features of weak targets to avoid the redundant information from covering the small target's weak key features;finally,in order to solve the problem of traditional spatial pyramid pool-ing which is easy to ignore the channel information,the confocal channel regulation pooling module is pro-posed to retain effective channel domain small target information and overcome interference from complex background information.Experiment results show that the model in this paper achieves an average detection accuracy of 83.3%on nine types of weak targets in the underwater sonar dataset,which is 5.5%higher than the benchmark.Among these,the detection accuracy of iron buckets,human body models and cubes is signi-ficantly improved by 24%,8.6%,and 7.3%,respectively,effectively solving the problem of leakage and mis-detection of weak targets in complex underwater environment.

关键词

弱小目标检测/水下声呐图像/全局信息聚合/共焦通道调控池化

Key words

weak target detection/underwater sonar images/global information aggregation/confocal chan-nel modulation pooling

分类

信息技术与安全科学

引用本文复制引用

何梦云,何自芬,张印辉,陈光晨,张枫..用于水下声呐目标检测的弱特征共焦通道调控方法[J].中国光学(中英文),2024,17(6):1281-1296,16.

基金项目

国家自然科学基金资助项目(No.62171206,No.62061022)Supported by the National Natural Science Foundation of China(No.62171206,No.62061022) (No.62171206,No.62061022)

中国光学(中英文)

OA北大核心CSTPCD

2095-1531

访问量0
|
下载量0
段落导航相关论文