Adaptive ship target detection in complex background

Xi CHEN; Bin HE; Yong-ji LONG; Xiang-yu SONG; Guo-ling BI

doi:10.37188/CJLCD.2021-0219

您当前的位置：

首页 >

文章列表页 >

Adaptive ship target detection in complex background

Image Processing | 更新时间：2022-03-25

- Adaptive ship target detection in complex background
- Chinese Journal of Liquid Crystals and Displays Vol. 37, Issue 3, Pages: 405-414(2022)
- 作者机构：
  
  1.中国科学院长春光学精密机械与物理研究所，吉林长春 130033
  2.中国科学院大学，北京 100049
- 作者简介：
- 基金信息：
- DOI：10.37188/CJLCD.2021-0219
  CLC： TP391.4
- Received：16 August 2021，
  
  Revised：19 October 2021，
  
  Published：2022-03
- 稿件说明：
移动端阅览
Xi CHEN, Bin HE, Yong-ji LONG, et al. Adaptive ship target detection in complex background[J]. Chinese journal of liquid crystals and displays, 2022, 37(3): 405-414.
DOI：

Xi CHEN, Bin HE, Yong-ji LONG, et al. Adaptive ship target detection in complex background[J]. Chinese journal of liquid crystals and displays, 2022, 37(3): 405-414. DOI： 10.37188/CJLCD.2021-0219.

摘要

光学遥感图像海面舰船目标检测易受云雾、海岛、海杂波、阴影等多种复杂因素的干扰。同时，由于卫星遥感图像的幅宽较大，若需要满足实时检测和硬件移植的需求，还要考虑算法的计算量和可移植性。鉴于实际工程的需要，本文提出了一种基于视觉显著性适用于复杂背景下的自适应舰船目标快速定位与检测方法。本算法首先基于图像梯度自适应获取全局最优尺度，通过谱残差显著性模型获得全局显著性区域。对于显著区域局部存在全局阈值分割效果不佳的区域(称为复杂区域)，本文通过设计轮廓等形状特征来筛选出局部复杂区域，并对其进一步计算显著图，之后将处理结果与原显著图进行融合，获取最终的疑似区域提取结果。最后使用支持向量机对候选区域进行进一步判别。结果表明，本文算法可以有效检测出复杂背景下不同尺寸和方向的舰船目标区域，算法检测正确率为91.4%，召回率为91.2%，优于大多数同类算法，接近深度学习算法精度。同时在算法体量上，本文算法的计算量和参数量远远低于大多数深度学习框架，更适合硬件移植，同时算法的迁移性更强，易于修改和维护。

Abstract

The optical remote sensing image sea surface ship target detection is susceptible to cloud

island

sea clutter

shadow and other complex factors interference. At the same time

due to the large width of satellite remote sensing images

if the real-time detection and hardware transplantation needs to be met

the amount of computation and portability of the algorithm should be considered. In order to meet the needs of practical engineering

this paper proposes an adaptive fast ship target location and detection method based on visual saliency under complex background. Firstly

the algorithm adaptively obtains the global optimal scale based on image gradient

and obtains the global significance region through the spectral residual significance model. For the regions with poor segmentation effect due to global threshold in significant regions (Complex regions)

the local complex regions are screened out by designing contour and other shape features

and the saliency map is further calculated. Then

the processing results are fused with the original significance map to obtain the final extraction results of suspected regions. Finally

the candidate regions are further distinguished using support vector machine. The results show that the proposed algorithm can effectively detect ship target areas with different sizes and directions under complex background

and the detection accuracy of the algorithm is 91.4% and the recall rate is 91.2%

which is better than most of the similar algorithms and close to the accuracy of the deep learning algorithm. At the same time

in terms of algorithm volume

the calculation amount and the number of parameters of the algorithm in this paper are far lower than those of most deep learning frameworks

which is more suitable for hardware transplantation. Meanwhile

the algorithm has stronger mobility and is easy to modify and maintain.

关键词

Keywords

references

徐芳 , 刘晶红 , 孙辉 , 等 . 光学遥感图像海面船舶目标检测技术进展 . 光学精密工程 , 2021 . 29 ( 4 ): 916 - 931 . DOI: 10.37188/OPE.2020.0419 http://doi.org/10.37188/OPE.2020.0419 .

F XU , J H LIU , H SUN , 等 . Research progress on vessel detection using optical remote sensing image . Optics and Precision Engineering , 2021 . 29 ( 4 ): 916 - 931 . DOI: 10.37188/OPE.2020.0419 http://doi.org/10.37188/OPE.2020.0419 .

王彦情 , 马雷 , 田原 . 光学遥感图像舰船目标检测与识别综述 . 自动化学报 , 2011 . 37 ( 9 ): 1029 - 1039 . DOI: 10.3724/SP.J.1004.2011.01029 http://doi.org/10.3724/SP.J.1004.2011.01029 .

Y Q WANG , L MA , Y TIAN . State-of-the-art of ship detection and recognition in optical remotely sensed imagery . Acta Automatica Sinica , 2011 . 37 ( 9 ): 1029 - 1039 . DOI: 10.3724/SP.J.1004.2011.01029 http://doi.org/10.3724/SP.J.1004.2011.01029 .

王慧利 , 朱明 , 蔺春波 , 等 . 光学遥感图像中复杂海背景下的舰船检测 . 光学精密工程 , 2018 . 26 ( 3 ): 723 - 732 . DOI: 10.3788/OPE.20182603.0723 http://doi.org/10.3788/OPE.20182603.0723 .

H L WANG , UM ZH , C B LIN , 等 . Ship detection of complex sea background in optical remote sensing images . Optics and Precision Engineering , 2018 . 26 ( 3 ): 723 - 732 . DOI: 10.3788/OPE.20182603.0723 http://doi.org/10.3788/OPE.20182603.0723 .

赵浩光 , 王平 , 董超 , 等 . 结合多尺度视觉显著性的舰船目标检测 . 光学精密工程 , 2020 . 28 ( 6 ): 1395 - 1403 . DOI: 10.3788/OPE.20202806.1395 http://doi.org/10.3788/OPE.20202806.1395 .

H G ZHAO , P WANG , C DONG , 等 . Ship detection based on the multi-scale visual saliency model . Optics and Precision Engineering , 2020 . 28 ( 6 ): 1395 - 1403 . DOI: 10.3788/OPE.20202806.1395 http://doi.org/10.3788/OPE.20202806.1395 .

姜鑫 , 陈武雄 , 聂海涛 , 等 . 航空遥感影像的实时舰船目标检测 . 光学精密工程 , 2020 . 28 ( 10 ): 2360 - 2369 . DOI: 10.37188/OPE.20202810.2360 http://doi.org/10.37188/OPE.20202810.2360 .

X JIANG , W X CHEN , H T NIE , 等 . Real-time ship target detection based on aerial remote sensing images . Optics and Precision Engineering , 2020 . 28 ( 10 ): 2360 - 2369 . DOI: 10.37188/OPE.20202810.2360 http://doi.org/10.37188/OPE.20202810.2360 .

聂婷. 大幅宽光学遥感图像目标检测技术研究[D]. 长春: 中国科学院大学(中国科学院长春光学精密机械与物理研究所), 2019.

NIE T. Target detection technique for large-field optical remote sensing image[D]. Changchun: University of Chinese Academy of Sciences (Changchun Institute of Optics, Fine Mechanics and Physics), 2019. (in Chinese)

李庆峰 , 何斌 , 王文胜 , 等 . 基于谱残差和梯度纹理融合特征的舰船检测 . 液晶与显示 , 2019 . 34 ( 8 ): 803 - 815 . DOI: 10.3788/YJYXS20193408.0803 http://doi.org/10.3788/YJYXS20193408.0803 .

Q F LI , B HE , W S WANG , 等 . Ship detection based on spectral residual and gradient texture fusion features . Chinese Journal of Liquid Crystals and Displays , 2019 . 34 ( 8 ): 803 - 815 . DOI: 10.3788/YJYXS20193408.0803 http://doi.org/10.3788/YJYXS20193408.0803 .

X G LENG , K F JI , X W XING , 等 . Area ratio invariant feature group for ship detection in SAR imagery . IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 2018 . 11 ( 7 ): 2376 - 2388 . DOI: 10.1109/JSTARS.2018.2820078 http://doi.org/10.1109/JSTARS.2018.2820078 .

刘冬梅 , 常发亮 . 结合Retinex校正和显著性的主动轮廓图像分割 . 光学精密工程 , 2019 . 27 ( 7 ): 1593 - 1600 . DOI: 10.3788/OPE.20192707.1593 http://doi.org/10.3788/OPE.20192707.1593 .

D M LIU , F L CHANG . Active contour model for image segmentation based on Retinex correction and saliency . Optics and Precision Engineering , 2019 . 27 ( 7 ): 1593 - 1600 . DOI: 10.3788/OPE.20192707.1593 http://doi.org/10.3788/OPE.20192707.1593 .

马俊杰 , 黄大庆 , 刘耀辉 , 等 . 基于改进ship-yolo的舰船目标定位 . 电子测量技术 , 2020 . 43 ( 5 ): 112 - 115 . https://www.cnki.com.cn/Article/CJFDTOTAL-DZCL202005025.htm https://www.cnki.com.cn/Article/CJFDTOTAL-DZCL202005025.htm , .

J J MA , D Q HUANG , Y H LIU , 等 . Ship target positioning based on improved ship-yolo . Electronic Measurement Technology , 2020 . 43 ( 5 ): 112 - 115 . https://www.cnki.com.cn/Article/CJFDTOTAL-DZCL202005025.htm https://www.cnki.com.cn/Article/CJFDTOTAL-DZCL202005025.htm , .

赵江洪 , 张晓光 , 杨璐 , 等 . 深度学习的遥感影像舰船目标检测 . 测绘科学 , 2020 . 45 ( 3 ): 110 - 116 . 110-116, 134 DOI: 10.16251/j.cnki.1009-2307.2020.03.017 http://doi.org/10.16251/j.cnki.1009-2307.2020.03.017 .

J H ZHAO , X G ZHANG , L YANG , 等 . Ship detection in remote sensing based on deep learning . Science of Surveying and Mapping , 2020 . 45 ( 3 ): 110 - 116 . 110-116, 134 DOI: 10.16251/j.cnki.1009-2307.2020.03.017 http://doi.org/10.16251/j.cnki.1009-2307.2020.03.017 .

HOU X D, ZHANG L Q. Saliency detection: a spectral residual approach[C]// IEEE Conference on Computer Vision and Pattern Recognition . Minneapolis: IEEE, 2007: 1-8.

L ITTI , C KOCH , E NIEBUR . A model of saliency-based visual attention for rapid scene analysis . IEEE Transactions on Pattern Analysis and Machine Intelligence , 1998 . 20 ( 11 ): 1254 - 1259 . DOI: 10.1109/34.730558 http://doi.org/10.1109/34.730558 .

E ERDEM , A ERDEM . Visual saliency estimation by nonlinearly integrating features using region covariances . Journal of Vision , 2013 . 13 ( 4 ): 11 DOI: 10.1167/13.4.11 http://doi.org/10.1167/13.4.11 .

刘娟妮 , 彭进业 , 李大湘 , 等 . 基于谱残差和多分辨率分析的显著目标检测 . 中国图象图形学报 , 2011 . 16 ( 2 ): 244 - 249 . DOI: 10.11834/jig.20110212 http://doi.org/10.11834/jig.20110212 .

J N LIU , J Y PENG , D X LI , 等 . Detecting salient objects based on spectral residual and multi-resolution . Journal of Image and Graphics , 2011 . 16 ( 2 ): 244 - 249 . DOI: 10.11834/jig.20110212 http://doi.org/10.11834/jig.20110212 .

REDMON J, FARHADI A. YOLOv3: an incremental improvement[J]. arXiv e-prints arXiv : 1804.02767, 2018.

WANG C Y, BOCHKOVSKIY A, LIAO H Y M. Scaled-YOLOv4: scaling cross stage partial network[J]. arXiv e-prints arXiv : 2011.08036, 2020.

Views

132

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Traffic sign recognition algorithm based on depthwise separable convolutions

Improved sliding average target detection algorithm based on statistical information

Development of AOI inspection of Mura defects on TFT-LCD surface

Application of dual-wavelength fiber guided light based on OpenCV in high-precision assembly and alignment

Related Author

CHEN Xi

HE Bin

LONG Yong-ji

SONG Xiang-yu

BI Guo-ling

Jin-sheng YANG

Yan-nan YANG

Tian-jiao LI

Related Institution

Changchun Institute of Optics， Fine Mechanics and Physics， Chinese Academy of Sciences

School of Microelectronics, Tianjin University

Changchun Institute of Optics Fine Mechanic and Physics, Chinese Academy of Science

University of Chinese Academy of Science

College of Engineering， Shantou University

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China 130033 Postal code：130033
Tel：0431-86176059 Email：yjxs@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰