无人艇视觉系统多类水面目标特征提取与识别

马忠丽; 文杰; 梁秀梅; 陈虹丽; 赵新华

doi:10.7652/xjtuxb201408011

您当前的位置：

首页 >

文章列表页 >

无人艇视觉系统多类水面目标特征提取与识别

更新时间：2025-07-09

- 无人艇视觉系统多类水面目标特征提取与识别
- Extraction and Recognition of Features from Multi-Types of Surface Targets for Visual Systems in Unmanned Surface Vehicle
- 西安交通大学学报 2014年48卷第8期页码：60-66
- 作者机构：
  
  哈尔滨工程大学自动化学院,黑龙江,哈尔滨,150001
- 作者简介：
- 基金信息：
  
  : 2013-12-24。作者简介: 马忠丽(1974—),女,副教授。基金项目: 国家自然科学基金资助项目(51109047)
- DOI：10.7652/xjtuxb201408011
  中图分类号： TP391.4
- 网络首发：2014-08-10，
  
  纸质出版：2014
- 稿件说明：
移动端阅览
马忠丽, 文杰, 梁秀梅, 等. 无人艇视觉系统多类水面目标特征提取与识别[J]. 西安交通大学学报, 2014,48(8):60-66.

Extraction and Recognition of Features from Multi-Types of Surface Targets for Visual Systems in Unmanned Surface Vehicle[J]. 2014, 48(8): 60-66.
马忠丽, 文杰, 梁秀梅, 等. 无人艇视觉系统多类水面目标特征提取与识别[J]. 西安交通大学学报, 2014,48(8):60-66. DOI： 10.7652/xjtuxb201408011.

Extraction and Recognition of Features from Multi-Types of Surface Targets for Visual Systems in Unmanned Surface Vehicle[J]. 2014, 48(8): 60-66. DOI： 10.7652/xjtuxb201408011.

摘要

针对海浪、海雾会造成无人艇视觉系统采集的视频图像模糊

影响目标特征提取和识别

且单一特征提取不能有效识别水面多类目标问题

在对无人艇采集的视频序列图像进行海雾去除和电子稳像预处理的基础上

提出一种多类水面目标组合特征提取和识别方法。首先分割清晰化后的图像

实现目标背景分离; 然后提取不同目标几何特征、不变矩特征和纹理特征; 最后采用基于组合特征和主分量分析降维的分级BP神经网络进行目标识别。通过实测、网络搜索和3D建模获得礁石、岛屿与船只3大类目标样本库

在MATLAB7.9下进行仿真研究

结果表明:多类水面目标组合特征提取和识别方法能有效实现无人艇视觉系统对海面3大类常见目标的分类识别

识别正确率达到85%以上。

Abstract

Sea waves and fog can cause video images captured by visual systems in a unmanned surface vehicle degradation and fuzzy

and influence targets feature extraction and recognition of targets. One single feature extraction is hard to identify multi-types of surface targets effectively. A method to extract and to identify features of multi-types surface targets for unmanned surface vehicle is proposed based on the fact that the video image sequence is preprocessed by removing sea fog and electronic image stabilization. At first

targets and background are separated by segmenting images. The geometrical feature

the moment invariant feature and texture feature in different targets are extracted. Then the grading BP neutral network with principal component analysis and dimension reduction is used to identify targets. A sample library of three types of targets such as reef

islands and ships are obtained through real measurements

network searching and 3D modeling. Simulations with MATLAB 7.9 show that the proposed method recognizes three types of common surface targets effectively

and the recognition accuracy is above 85%.

关键词

Keywords

references

汪成亮, 汪连伟. 基于特征的江面轮船识别算法[J]. 计算机应用研究, 2011, 28(6): 2352-2354.

WANG Chengliang, WANG Lianwei. Ship targets recognition algorithm based on features[J]. Application Research of Computers, 2011, 28(6): 2352-2354.

刘新科, 于吉红, 吕俊伟, 等. 基于仿射不变矩特征的舰船图像识别方法[J]. 海军航空工程学院学报, 2011, 26(6): 687-690.

LIU Xinke, YU Jihong, LV Junwei, et al. Ship image recognition method based on the affine invariant moments[J]. Journal of Naval Aeronautical Engineering Institute, 2011, 26(6): 687-690.

ZABIDI M M A, MUSTAPA J, MOKJI M M, et al. Embedded vision systems for ship recognition[C]∥Proceedings of TENCON 2009, IEEE Region 10 International Conference. Los Alamitos, CA, USA: IEEE Computer Society, 2009: 1-5.

ZHU Changren, ZHOU Hui, WANG Runsheng, et al. A novel hierarchical method of ship detection from spaceborne optical image based on shape and texture features[J]. IEEE Transactions on Geoscience and Remote Sensing, 2010, 48(9): 3446-3456.

VELLA F. Digital image stabilization by adaptive block motion vectors filtering[J]. IEEE Transactions on Consumer Electronics, 2002, 48(3): 796-801.

MA Z, WEN J, LIANG X. Video image clarity algorithm research of USV visual system under the sea fog[M]∥Advances in Swarm Intelligence. Heidelberg, Germany: Springer, 2013: 436-444.

马忠丽, 李慧凤, 文杰, 等. 高速水面艇视觉系统电子稳像算法[J]. 计算机应用研究, 2014, 31(2): 633-636.

MA Zhongli, LI Huifeng, WEN Jie, et al. Electronic image stabilization algorithm for high speed surface vehicle vision system[J]. Application Research of Computers, 2014, 31(2): 633-636.

马忠丽, 梁秀梅, 文杰. 无人水面艇目标图像自适应分割算法[J]. 哈尔滨工业大学学报, 2014, 46(5): 612-636.

MA Zhongli, LIANG Xiumei, WEN Jie. Image adaptive segmentation algorithm for unmanned surface vehicle targets[J]. Journal of Harbin Institute of Technology, 2014, 46(5): 612-636.

宋卫东. 解析几何[M]. 北京: 高等教育出版社, 2003: 96-101.

CHENG Y Z. Mean shift, mode seeking, and clustering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1995, 17(8): 790-799.

FLUSSER J, SUK T. Pattern recognition by affine moment invariants[J]. Pattern Recognition, 1993, 1(26): 167-174.[12] 钟建华, 齐乐华, 李妙玲, 等. 利用人工神经网络的偏光下热解炭织构类型识别[J]. 西安交通大学学报, 2010, 44(7): 46-49.

ZHONG Jianhua, QI Lehua, LI Miaoling, et al. Automatic classification of pyrocarbon texture under polarized light microscope based on artificial neural network[J]. Journal of Xi'an Jiaotong University, 2010, 44(7): 46-49.

苑丽红, 付丽, 杨勇, 等. 灰度共生矩阵提取纹理特征的实验结果分析[J]. 计算机应用, 2009, 29(4): 1018-1021.

YUAN Lihong, FU Li, YANG Yong, et al. Analysis of texture feature extracted by gray level co-occurrence matrix[J]. Journal of Computer Applications, 2009, 29(4): 1018-1021.

张国英, 王娜娜, 张润生, 等. 基于主成分分析的BP神经网络在岩性识别中的应用[J]. 北京石油化工学院学报, 2008, 16(3): 43-46.

ZHANG Guoying, WANG Nana, ZHANG Runsheng, et al. Application of principal component analysis and BP neural network in identifying lithology[J]. Journal of Beijing Institute of Petro-chemical Technology, 2008, 16(3): 43-46.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

采用残差神经网络的无人机遥控信号识别监测算法

面向高海拔空冷发电机防晕性能演化规律的电热耦合研究

冷库水平空气幕热湿阻隔性能数值模拟研究

结构-语义-残差协同的图像压缩框架：面向隐私保护与高保真重建

超临界二氧化碳向心透平轮背间隙内风阻损失及流动特性研究