基于光强—光谱—偏振信息融合的水下目标检测

doi:10.3969/j.issn.1000-436x.2013.03.025

摘要/Abstract

摘要：

由于图像建模及参数估计的困难和复杂性，水下目标检测算法的性能受到了严重影响。受水下生物视觉信息处理机制的启发，针对特殊的水下光学环境提出一种新的基于光强—光谱—偏振的仿生信息融合目标检测方法，能够根据所获得的水下光学先验知识进行适应性特征融合。算法摆脱繁琐的图像预处理过程，以较低的运算复杂度为代价实现可靠的目标检测结果。

关键词: 水下图像处理, 水下目标检测, 信息融合, 机器学习

Abstract:

Difficulties and high computational costs in the model establishmen and parameter estimation seriously de-graded the efficiency of the underwater object detection system, making them too cumbersome to the practical work. A noval light intensity, spectrum and polarization feature fusion method was proposed. This method directly introduces the prior underwater knowledge into the system for feature fusion, getting rid of the harassment of the image preprocessing. Experiments prove that this method by comparison can achieve more reliable results at the lower computational cost.

Key words: underwater image processing, underwater object detection, information fusion, machine learning

陈哲,王慧斌,沈洁,徐立中. 基于光强—光谱—偏振信息融合的水下目标检测[J]. 通信学报, 2013, 34(3): 192-198.

Zhe CHEN,Hui-bin WANG,Jie SHEN,Li-zhong XU. Light intensity, spectrum and polarization information fusion based underwater object detection[J]. Journal on Communications, 2013, 34(3): 192-198.

图/表 11

图1

图2

图3

图4

图5

图6

表1

图7

表2

图8

表3

参考文献 13

[1]	GIANL F . Visual inspection of sea bottom structures by an autonom-ous underwater vehicle[J]. IEEE Transactions on Systems, Man and Cybernetics, Part B, 2001,31: 691-705.
[2]	HUY , WANGL , LIANGJ , et al. Cooperative box-pushing with mul-tiple autonomous robotic fish in underwater environment[J]. Control Theory ＆ Applications, 2011,5(17): 2015-2022.
[3]	FANDOSR , ZOUBIRA M . Optimal feature set for automatic detec-tion and classification of underwater objects in SAS images[J]. IEEE Journal of Selected Topics in Signal Processing, 2011,5(3): 454-468.
[4]	SCHETTINIR , CORCHSS . Underwater image processing: state of the art of restoration and image enhancement methods[J]. EURASIP Journal on Advances in Signal Processing, 2010,2010: 1-14.
[5]	WANGX , YANX J , LVG F , et al. Balloon-borne spectrum-polariza-tion imaging for river surface velocimetry under extreme co itions[J]. Infrared Physics ＆ Technology, 2013,277(3): 182-194.
[6]	TANG P , LIY H . An adaptive HEC scheme with variable packet size for wireless real-time reliable multicast[J]. Chinese Journal of Elec-tronics, 2012,21: 299-303.
[7]	WANGG , ZHENGB , SUNF F . Estimation-based approach for un-derwater image restoration[J]. Optics Letter, 2011,36: 2384-2386.
[8]	LIUZ , YUY , ZHANGK , et al. Underwater image transmission and blurred image restoration[J]. Optical Engineering, 2001,40: 1125-1131.
[9]	LANGYM S , MOVSHONJ A . Computational Models of Visual Processing[M]. Cambridge: MIT Press, 1991.
[10]	SCHIFFH , DOREB , BOIDOM . Morphology of adaptation and morphogenesis in stomatopod eyes[J]. Ital J Zool, 2007,74: 123-134.
[11]	ITTIL , KOCHC , NIEBURE . A model of saliency-based visual atten-tion for rapid scene analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998,20(11): 1254-1259.
[12]	HOJJATOLESLAMIS A , KITTLERJ . Region growing: a new ap-proach[J]. IEEE Transactions on Image Process, 1998,7: 1079-1084.
[13]	ELDERJ H , ZUCKERS W . Local scale control for edge detection and blur estimation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998,20(7): 699-716.

光学先验知识	C_good	C_false
+	0.911 4	0.007 2
-	0.877 0	0.091 9

算法	C_good	C_false	运算时间/s
水下先验知识	0.911 4	0.007 2	1.32
图像恢复	0.915 8	0.196 8	2.87

算法	C_good	C_false	运算时间/s
经验知识	0.894 2	0.026 2	2.52
图像恢复	0.870 2	0.066 9	7.43

[1]	戴千一, 张斌, 郭松, 徐开勇. 基于多分类器集成的区块链网络层异常流量检测方法[J]. 通信学报, 2023, 44(3): 66-80.
[2]	何高峰, 魏千峰, 肖咸财, 朱海婷, 徐丙凤. 支持数据隐私保护的恶意加密流量检测确认方法[J]. 通信学报, 2022, 43(2): 156-170.
[3]	冯智斌, 徐煜华, 杜智勇, 刘鑫, 李文, 韩昊, 张晓博. 对抗智能干扰的主动防御技术[J]. 通信学报, 2022, 43(10): 42-54.
[4]	陆彦辉, 柳寒, 李航, 朱光旭. 基于多鉴别器生成对抗网络的时间序列生成模型[J]. 通信学报, 2022, 43(10): 167-176.
[5]	梅锴, 赵海涛, 刘潇然, 刘军, 熊俊, 任保全, 魏急波. 高效的基于数据与模型的信道估计算法[J]. 通信学报, 2022, 43(1): 59-70.
[6]	彭长根, 高婷, 刘惠篮, 丁红发. 面向机器学习模型的基于PCA的成员推理攻击[J]. 通信学报, 2022, 43(1): 149-160.
[7]	邹福泰, 谭越, 王林, 蒋永康. 基于生成对抗网络的僵尸网络检测[J]. 通信学报, 2021, 42(7): 95-106.
[8]	刘留, 张建华, 樊圆圆, 于力, 张嘉驰. 机器学习在信道建模中的应用综述[J]. 通信学报, 2021, 42(2): 134-153.
[9]	伏玉笋,杨根科. 人工智能在移动通信中的应用：挑战与实践[J]. 通信学报, 2020, 41(9): 190-201.
[10]	陈铁明,金成强,吕明琪,朱添田. 基于样本增强的网络恶意流量智能检测方法[J]. 通信学报, 2020, 41(6): 128-138.
[11]	韩春雨,张永铮,张玉. Fast-flucos：基于DNS流量的Fast-flux恶意域名检测方法[J]. 通信学报, 2020, 41(5): 37-47.
[12]	周鑫,何晓新,郑昌文. 基于图像深度学习的无线电信号识别[J]. 通信学报, 2019, 40(7): 114-125.
[13]	何友,姚力波,江政杰. 基于空间信息网络的海洋目标监视分析与展望[J]. 通信学报, 2019, 40(4): 1-9.
[14]	杜学绘,林杨东,孙奕. 基于混合特征的恶意PDF文档检测[J]. 通信学报, 2019, 40(2): 118-128.
[15]	孙鸿宇,何远,王基策,董颖,朱立鹏,王鹤,张玉清. 人工智能技术在安全漏洞领域的应用[J]. 通信学报, 2018, 39(8): 1-17.