多特征融合的红外舰船目标检测方法

张仲瑜; 焦淑红

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

多特征融合的红外舰船目标检测方法

张仲瑜, 焦淑红

文章导航 > 红外与激光工程 > 2015 > 44(S1): 29-34

张仲瑜, 焦淑红. 多特征融合的红外舰船目标检测方法[J]. 红外与激光工程, 2015, 44(S1): 29-34.

引用本文:

张仲瑜, 焦淑红. 多特征融合的红外舰船目标检测方法[J]. 红外与激光工程, 2015, 44(S1): 29-34.

Zhang Zhongyu, Jiao Shuhong. Infrared ship target detection method based on multiple feature fusion[J]. Infrared and Laser Engineering, 2015, 44(S1): 29-34.

Citation:

Zhang Zhongyu, Jiao Shuhong. Infrared ship target detection method based on multiple feature fusion[J]. Infrared and Laser Engineering, 2015, 44(S1): 29-34.

多特征融合的红外舰船目标检测方法

1.
哈尔滨工程大学信息与通信学院,黑龙江哈尔滨 150001

详细信息

作者简介:
张仲瑜(1991－),女,硕士生,主要从事图像处理与分析、模式识别方面的研究。Email:331614702@qq.com

中图分类号: TP391.9

Infrared ship target detection method based on multiple feature fusion

1.
Information and Communication Engineering,Harbin Engineering University,Harbin 150001,China

摘要: 针对海天背景下红外舰船目标的分割提出了一种基于多特征融合的分割算法。该算法对红外图像进行水平边缘信息和竖直边缘信息的提取。首先,将不同尺度下的结果进行求平均值算,将结果图作为第一个特征。其次,针对不同大小舰船目标的问题,运用改进的对红外图像进行多级滤波,从而达到背景抑制、突出目标的效果,其结果可作为第二个特征。最后,求红外图像的局部灰度最大值后,将其特征图像作为第三个特征,然后对各个特征图进行归一化处理并进行融合。在融合过程中,对各个特征图该赋予的权重进行研究,选取恰当的融合系数得到融合后的图像,对其采用自适应阈值进行目标最终分割,之后做一个形态学整形,去除孤立面积和补充空洞,完善分割结果。仿真结果表明,与传统的分割方法相比,该算法分割效果明显,能够达到分割要求。
- 红外舰船目标分割 /
- 多特征融合 /
- 多级滤波 /
- 局部灰度最大值 /
- 仿真
Abstract: Under the ocean background, a segmentation method was proposed based on the fusion of multiple features for infrared ship segmentation. This method is used to extract horizontal edge information and vertical edge information from infrared image. First of all, the mean of the data collected on different scales was got, and the result image was seen as the first feature. Furthermore, for the problem of ship targets with different sizes, the improved multistage filters was employed for infrared image, so as to prohibit background and highlight target. The multistage filtered image was identified as the second feature. Finally, the local maximum gray value of infrared image was identified the third feature. Then these three features would be normalized and integrated. During the process of infusion, firstly, each featue image was given weight; then, an appropriate infusion coefficient for fused image was selected. The fused image was segmented by adaptive threshold, followed by a morphological plastic in order to remove isolated areas, supplement holes and improve the segmentation results. The simulation results show that, compared with traditional segmentation strategies, the proposed segmentation method based on multiple features fusion is more likely to meet the demands of segmentation.
- infrared ship targets segmentation /
- multiple feature fusion /
- multistage filtering /
- a maximum local gray level /
- simulation

[1]
[2]	Ni Lin. Research on algorithms for image segmentation Based on otsu theory[D]. Chongqing: College of Mathematics and Statistics of Chongqing University, 2013. (in Chinese)
[3]
[4]	Liu Yunhe. Research on IR small target detection and tracking based on attention mechanism[D]. Harbin: Harbin Engineering University, 2009. (in Chinese)
[5]
[6]
[7]	Cheng Shenglian. IR small moving target real-time tracking based on multi-level filter[D]. Wuhan: Huazhong University of Science Technology, 2006. (in Chinese)
[8]	Liu Shijun. Under the background of air and infrared ship target recognition methods[D]. Chengdu: University of Electronic Science and Technology of China, 2012.
[9]	Liu Zhaoying, Zhou Fugen, Chen Xiaowu, et al. SunIterative infrared ship target segmentation based on multiple features[J]. Pattern Recognition, 2014, 47(9): 5-10.

[1]	王鹏翔, 张兆基, 杨怀. 结合多特征融合和极限学习机的红外图像目标分类方法 . 红外与激光工程, 2022, 51(6): 20210597-1-20210597-6. doi: 10.3788/IRLA20210597
[2]	刘雯雯, 苏伟, 罗文豪, 李健坷, 刘人怀. 中红外固体激光器的振动可靠性 . 红外与激光工程, 2021, 50(4): 20200242-1-20200242-6. doi: 10.3788/IRLA20200242
[3]	王伟平, 于佳睿, 胡小燕, 赵少宇. 中波红外集成偏振光栅结构参数对偏振性能影响仿真分析 . 红外与激光工程, 2021, 50(11): 20210132-1-20210132-8. doi: 10.3788/IRLA20210132
[4]	高有道, 李福东, 沈正祥, 丁琳, 胡斌, 徐绍伟. 低温红外镜头设计仿真方法及试验验证 . 红外与激光工程, 2021, 50(5): 20200397-1-20200397-6. doi: 10.3788/IRLA20200397
[5]	陈宏宇, 罗海波, 惠斌, 常铮. 采用多特征融合的子块自动提取方法 . 红外与激光工程, 2021, 50(8): 20200407-1-20200407-9. doi: 10.3788/IRLA20200407
[6]	尚超, 王锦春, 张晓兵. 红外焦平面阵列读出电路非均匀性研究 . 红外与激光工程, 2020, 49(8): 20190581-1-20190581-8. doi: 10.3788/IRLA20190581
[7]	陆福星, 陈忻, 陈桂林, 饶鹏. 背景自适应的多特征融合的弱小目标检测 . 红外与激光工程, 2019, 48(3): 326002-0326002(7). doi: 10.3788/IRLA201948.0326002
[8]	刘尊洋, 叶庆, 李修和, 邵立, 孙晓泉. 红外预警卫星直视地表波段选择及探测能力 . 红外与激光工程, 2018, 47(2): 204003-0204003(6). doi: 10.3788/IRLA201847.0204003
[9]	余骁, 闵敏, 张兴赢, 孟晓阳, 邓小波. 典型滤波器对星载高光谱分辨率激光雷达532 nm通道回波信号的影响 . 红外与激光工程, 2018, 47(12): 1230008-1230008(10). doi: 10.3788/IRLA201847.1230008
[10]	卢新然, 宋路, 万秋华. 红外光源参数对光电编码器信号的影响 . 红外与激光工程, 2017, 46(9): 917007-0917007(6). doi: 10.3788/IRLA201746.0917007
[11]	施蕊, 徐畅, 徐锐, 石诺, 杨扬, 钱丽勋, 王欣, 李卓. 基于MEMS的红外动态图像生成技术 . 红外与激光工程, 2016, 45(2): 204002-0204002(5). doi: 10.3788/IRLA201645.0204002
[12]	毛羽丰, 李运泽, 王晶, 姜利祥, 魏传峰. 基于红外热成像的热流分布测量技术 . 红外与激光工程, 2016, 45(8): 804001-0804001(6). doi: 10.3788/IRLA201645.0804001
[13]	殷世民, 王具民, 梁永波, 朱健铭, 韩国成, 陈洪波, 陈真诚. 红外干涉光谱仪非均匀性在线校正与仿真 . 红外与激光工程, 2016, 45(6): 604002-0604002(8). doi: 10.3788/IRLA201645.0604002
[14]	王炜强, 贾晓洪, 韩宇萌, 张晓阳, 付奎生. 定向干扰激光的红外成像建模与仿真 . 红外与激光工程, 2016, 45(6): 606005-0606005(6). doi: 10.3788/IRLA201645.0606005
[15]	张瑞, 王志斌, 王耀利, 李克武. 可实现零光程差的红外静态斜楔干涉具研究 . 红外与激光工程, 2015, 44(7): 2093-2096.
[16]	王良训, 周辉, 李子乐, 刘国根, 王虹, 王雅培. 面向星载激光测高仪的陆地目标响应函数仿真 . 红外与激光工程, 2015, 44(11): 3424-3430.
[17]	童奇, 王超哲, 童中翔, 李建勋, 贾林通, 柴世杰. 红外干扰机对四元正交探测器的干扰效能 . 红外与激光工程, 2014, 43(8): 2496-2504.
[18]	朱敏, 陈宇, 杨春玲. 红外诱饵弹干扰特性有限元建模 . 红外与激光工程, 2013, 42(8): 1979-1986.
[19]	曹春芹, 向静波, 张晓阳, 王炜强. 红外成像导弹气动加热仿真建模方法 . 红外与激光工程, 2013, 42(8): 1951-1955.
[20]	成志铎, 李明博, 李健, 常晓权, 刘君. 目标与背景的红外辐射特性仿真方法 . 红外与激光工程, 2013, 42(9): 2336-2340.

点击查看大图

计量

文章访问数: 474
HTML全文浏览量: 69
PDF下载量: 193
被引次数: 0

多特征融合的红外舰船目标检测方法

1. 哈尔滨工程大学信息与通信学院,黑龙江哈尔滨 150001

作者简介:
张仲瑜(1991－),女,硕士生,主要从事图像处理与分析、模式识别方面的研究。Email:331614702@qq.com

收稿日期: 2015-10-05
修回日期: 2015-11-10
刊出日期: 2016-01-25

中图分类号: TP391.9

关键词:

摘要: 针对海天背景下红外舰船目标的分割提出了一种基于多特征融合的分割算法。该算法对红外图像进行水平边缘信息和竖直边缘信息的提取。首先,将不同尺度下的结果进行求平均值算,将结果图作为第一个特征。其次,针对不同大小舰船目标的问题,运用改进的对红外图像进行多级滤波,从而达到背景抑制、突出目标的效果,其结果可作为第二个特征。最后,求红外图像的局部灰度最大值后,将其特征图像作为第三个特征,然后对各个特征图进行归一化处理并进行融合。在融合过程中,对各个特征图该赋予的权重进行研究,选取恰当的融合系数得到融合后的图像,对其采用自适应阈值进行目标最终分割,之后做一个形态学整形,去除孤立面积和补充空洞,完善分割结果。仿真结果表明,与传统的分割方法相比,该算法分割效果明显,能够达到分割要求。

English Abstract

Infrared ship target detection method based on multiple feature fusion

1. Information and Communication Engineering,Harbin Engineering University,Harbin 150001,China

Received Date: 2015-10-05
Rev Recd Date: 2015-11-10
Publish Date: 2016-01-25

Keywords:

Abstract: Under the ocean background, a segmentation method was proposed based on the fusion of multiple features for infrared ship segmentation. This method is used to extract horizontal edge information and vertical edge information from infrared image. First of all, the mean of the data collected on different scales was got, and the result image was seen as the first feature. Furthermore, for the problem of ship targets with different sizes, the improved multistage filters was employed for infrared image, so as to prohibit background and highlight target. The multistage filtered image was identified as the second feature. Finally, the local maximum gray value of infrared image was identified the third feature. Then these three features would be normalized and integrated. During the process of infusion, firstly, each featue image was given weight; then, an appropriate infusion coefficient for fused image was selected. The fused image was segmented by adaptive threshold, followed by a morphological plastic in order to remove isolated areas, supplement holes and improve the segmentation results. The simulation results show that, compared with traditional segmentation strategies, the proposed segmentation method based on multiple features fusion is more likely to meet the demands of segmentation.