基于多模态感知的水下目标检测应用构想
作者:
作者单位:

1.清江创新中心,湖北 武汉 430200 ;2.中国船舶集团有限公司第七一〇研究所,湖北 宜昌 443003 ;3.海军工程大学 基础部,湖北 武汉 430033

作者简介:

陈悦(1997-),女,硕士,助理工程师,主要从事深度学习、计算机视觉方向研究。

中图分类号:

TP391.4


Research on Application of Underwater Object Detection Based on Multimodal Perception
Author:
Affiliation:

1.Qingjiang Innovation Center,Wuhan 430200 ,China ;2.No.710 R&D Institute,CSSC,Yichang 443003 ,China ;3.Department of Basic Courses,Naval University of Engineering,Wuhan 430033 ,China

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [62]
  • |
  • 相似文献 [20]
  • | | |
  • 文章评论
    摘要:

    水下目标检测在海洋生物研究、考古探索、军事防御等多领域广泛应用,随着人工智能快速发展,水下目标检测也朝着无人化、智能化发展。深度学习采用神经网络挖掘信息特征,在速度和精度上均表现出优异的性能,成为了计算机视觉技术的主流算法,然而水下环境复杂,将其应用于水下图像目标检测仍存在较大的挑战。水下目标各模态信息互补,特征丰富,有利于目标检测识别,因此结合应用场景调研现有技术,然后设计基于深度学习的多模态水下目标检测系统,同时对比分析了现有关键技术的优缺点,最后对多模态目标检测系统未来发展进行总结与展望,具有重要意义。

    Abstract:

    Underwater object detection has been widely applied in various fields,such as marine biology research,archaeological exploration,and military defense. With the rapid development of artificial intelligence, underwater object detection has also become unmanned and intelligent. Deep learning uses neural networks to mine information features,demonstrating excellent performance in both speed and accuracy,and has become the mainstream algorithm in computer vision technology. However,in complex underwater environments,there are still significant challenges in applying it to underwater image object detection. The complementary information and rich features of various modalities of underwater targets are beneficial for target detection and recognition. Therefore,this article combines application scenarios to investigate existing technologies,and then designs a multimodal underwater target detection system based on deep learning. At the same time,the advantages and disadvantages of existing core technologies are compared and analyzed. Finally,a summary and outlook on the future development of multimodal object detection systems are carried out,which is of great significance.

    参考文献
    [1] 张起.新形势下的反水雷需求与对策[J].水雷战与舰船防护,2015,23(2):1-5.
    [2] 周穗华,张晓兵,蒋培,等.水雷总体技术[M].北京:兵器工业出版社,2015,1-22.
    [3] 赵治平,官红,艾艳辉,等.无人化时代反水雷装备体系构想[J].数字海洋与水下攻防,2018,1(1):1-6.
    [4] 傅金祝.美国海军反水雷能力和无人反水雷平台装备分析[J].现代舰船,2012(6):44-47.
    [5] 张鹏,何心怡,林杨.反水雷与 UxV[J].舰船科学技术,2009,31(1):29-33.
    [6] DJAPIC V,NAD D.Using collaborative autonomous vehicles in mine countermeasures[C]//OCEANS 2010-MTS/IEEE Seattle.Sydney:IEEE,2010.
    [7] 刘平,杨洋,王青.国外反水雷舰艇装备现状及发展趋势[J].船舶工程,2004,26(6):1-3.
    [8] 王进,王慧.反水雷无人艇的发展趋势分析[J].数字海洋与水下攻防,2021,4(2):113-116.
    [9] 王久法,吴乔,高频,等.国外无人反水雷特点及关键技术分析[J].数字海洋与水下攻防,2020,3(5):382-386.
    [10] 张晓鹏,周利生.掩埋小目标声探测技术研究[J].声学技术,2012,31(1):30-35.
    [11] COURMONTAGNE P.A new approach for mine detection in SAS imagery[C]//OCEANS 2008-MTS/IEEE Kobe Technology.Kobe:IEEE,2008.
    [12] BALTRU T,AHUJA C,MORENCY L P.Multimodal machine learning:a survey and taxonomy[J].Transactions of Pattern Analysis and Machine Intelligence,2018,41(2):423-443.
    [13] 刘建伟,丁熙浩,罗雄麟,等.多模态深度学习综述 [J].计算机应用研究,2020,37(6):1601-1614.
    [14] ZHOU T X,RUAN S,CANU S.A review:deep learning for medical image segmentation using multi-modality fusion[J].Array,2019,3-4:100004.
    [15] ZHOU T X,RUAN S,VERA P.A tri-attentionfusion guided multi-modal segmentation network[J].Pattern Recognition,2022,124:108417.
    [16] VORA S,LANG A H,HELOU B,et al.PointPainting:sequential fusion for 3D object detection[J].Computer Vision and Pattern Recognition,2020,2019(1):10150.
    [17] PANG S,MORRIS D,RADHA H.Fast-CLOCs:fast camera-LiDAR object candidates fusion for 3D object detection[EB/OL].[2022-03-08].https://openaccess.thecvf.com/content/WACV2022/papers/Pang_Fast-CL OCs_Fast_Camera-LiDAR_Object_Candidates_Fusion _for_3D_Object_Detection_WACV_2022_paper.pdf.
    [18] KIM W,SON B,KIM I.ViLT:vision-and-language transformer without convolution or region supervision [EB/OL].[2021-07-10].https://arxiv.org/abs/2102.03334.
    [19] RADFORD A,KIM J W,HALLACY C,et al.Learning transferable visual models from natural language supervision[C]//38th International Conference on Machine Learning.San Francisco:IEEE,2021.
    [20] YE M,LAN X Y,LI J W,et al.Hierarchical discriminative learning for visible thermal person re-identification[C]//32nd AAAI Conference on Artificial Intelligence.New Orleans:AAAI,2018.
    [21] LU Y,WU Y,LIU B,et al.Cross-modality person re-identification with shared-specific feature transfer[EB/OL].[2020-03-12].https://arxiv.org/abs/2002.12489.
    [22] JANSEN B J,GOODRUM A,SPINK A.Searching for multimedia:analysis of audio,video and image Web queries[J].World Wide Web:Internet and Web Information Systems,2000,3(4):249-254.
    [23] MA L,ZHUO C,XU L,et al.Multimodal deep learning for solar radio burst classification[J].Patter Recognition,2017,6(1):573-582.
    [24] 常昕,陈晓冬,张佳琛,等.基于激光雷达和相机信息融合的目标检测及跟踪[J].光电工程,2019,46(7):91-l01.
    [25] VORA S,LANG A H,HELOU B,et al.PointPainting:sequential fusion for 3D object detection[EB/OL].[2020-05-06].https://arxiv.org/abs/1911.10150
    [26] 程腾,孙磊,侯登超,等.基于特征融合的多层次多模态目标检测[J].汽车工程,2021,43(11):1602-1610.
    [27] DUAN W T,ZHANG L,COLMAN J,et al.Multi-modal brain segmentation using hyper-fused convolutional neural network[C]//4th International Workshop on Machine learning in Clinical Neuroimaging.Strasbourg:Springer,2021.
    [28] 杨舜翔.基于多模态医学影像的疾病早筛方法研究 [D].济南:山东大学,2021.
    [29] CHEN Y,WAN L,LI Z H,et al.Neural feature search for RGB-infrared person re-identification[EB/OL].[2021-06-06].https://arxiv.org/abs/2104.02366.
    [30] 孙影影,贾振堂,朱昊宇,等.多模态深度学习综述 [J].计算机工程与应用,2020,56(21):1-10.
    [31] 郝紫霄,王琦.基于声呐图像的水下目标检测研究综述[J].水下无人系统学报,2023,31(2):339-348.
    [32] 曾文冠,鲁建华.基于卷积神经网络的声呐图像目标检测识别[C]//第17届船舶水下噪声学术讨论会论文集.衢州:《船舶力学》编辑部,2019.
    [33] RAO C,MUKHERJEE K,GUPTA S,et al.Underwater mine detection using symbolic pattern analysis of side scan sonar images[C]//2009 American Control Conference.St.Louis:IEEE,2009.
    [34] JEONG D M,SON K,LEE Y G,et al.Echo energy estimation in active sonar using fast independent component analysis [J].Neural Information Processing,2011,5863:381-388.
    [35] 杜召平,陈刚,王达,等.国外声呐技术发展综述[J].舰船科学技术,2019,41(1):145-151.
    [36] 梁开龙.水下地形测量[M].北京:测绘出版社,1995.
    [37] 康路遥,夏开奇.图像声呐技术现状及其在水下探测中的应用浅析[C]//第10届中国国际救捞论坛论文集.上海:中国航海学会救捞专业委员会,2018.
    [38] 张合,江小华.目标探测与识别技术[M].北京:北京理工大学出版社,2015.
    [39] 徐燕,周昌剑.磁技术在水下密封和探测中的应用[J].电子世界,2014(10):163-164.
    [40] 张明.水下磁性目标探测系统研制[D].杭州:杭州电子科技大学,2017.
    [41] 卞光浪,翟国君,黄谟涛,等.利用剖面测线磁场数据反演三度磁性体参数[J].武汉大学学报:信息科学版,2012,37(1):91-95.
    [42] 蒋敏志,林春生.船舶水下被动磁性定位研究[J].武汉理工大学学报:信息与管理工程版,2003,25(6):168-170,187.
    [43] 黄玉,郝燕玲.基于磁矩信息的水下地磁连续定位算法[J].上海交通大学学报,2012,46(3):390-393.
    [44] 朱彩霞,闫亚东,沈满德,等.基于水下反恐的微光成像系统[J].应用光学,2008,29(2):220-224.
    [45] 冯包根.国外水下激光成像技术现状[J].红外与激光技术,1995,24(2):11-16.
    [46] DUNTLEY S Q.Light in the sea[J].Journal of the Optical Society of America,1963,52(1):214-233.
    [47] 赵涛.国外激光告警技术的设备与发展[J].舰船电子工程,2009,29(2):27-29.
    [48] HULST H C.Light Scattering by Small Particles[M].New York:Wiley,1957.
    [49] 冯包根.美国海军“魔灯”机载激光探雷系统[J].水雷战与战舰防护,1998,17(5):30-32.
    [50] 刘雪明,胡正荣.同步扫描水下激光成像系统主要光学参数的理论分析[J].电子器件,1997,20(3):47-51.
    [51] 李哲,邓甲吴,周卫.水下激光探测技术及其进展[J].舰船电子工程,2008,28(12):13-16,53.
    [52] 孙剑峰,郜键,魏靖松,等.条纹管激光成像雷达水下探测成像研究进展[J].红外与激光工程,2010,39(5):811-814.
    [53] 蒋弘毅,王永娟,康锦煜.目标检测模型及其优化方法综述[J].自动化学报,2021,47(6):1232-1255.
    [54] REN S Q,HE K M,GIRSHICK R,et al.Faster R-CNN:towards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2017,39(6):1137-1149.
    [55] REDMON J,DIVVALA S,GIRSHICK R,et al.You only look once:unified,real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.New York:IEEE,2016.
    [56] REDMON J,FARHADI A.YOLO9000:better,faster,stronger[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.New York:IEEE,2017.
    [57] REDMON J,FARHADI A.YOLOv3:an Incremental Improvement[EB/OL].[2018-04-08].https://arxiv.org/pdf/1804.02767.
    [58] LIU W,ANGUELOV D,ERHAN D,et al.SSD:single shot multibox detector[EB/OL].[2016-12-29].https://arxiv.org/abs/1512.02325
    [59] LIN T Y,GOYAL P,GIRSHICK R,et al.Focal loss for dense object detection[EB/OL].[2018-02-07].https://arxiv.org/abs/1708.02002
    [60] LAW H,DENG J.CornerNet:detecting objects as paired keypoints[J].International Journal of Computer Vision,2020,128(3):642-656.
    [61] TIAN Z,SHEN C H,CHEN H,et al.FCOS:fully convolutional one-stage object detection[EB/OL].[2019-08-20].https://arxiv.org/abs/1904.01355.
    [62] ZAND M,ETEMAD A,GREENSPAN M.ObjectBox:from centers to boxes for anchor-free object detection[C]//17th European Conference on Computer Vision.Tel Aviv:Springer,2022.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

陈悦,罗逸豪,李锦.基于多模态感知的水下目标检测应用构想[J].数字海洋与水下攻防,2024,7(3):334-341

复制
分享
文章指标
  • 点击次数:104
  • 下载次数: 3739
  • HTML阅读次数: 516
  • 引用次数: 0
历史
  • 收稿日期:2024-03-11
  • 在线发布日期: 2024-07-02
文章二维码