|
|
|
|
|
|
Multispectral Lightweight Ship Target Detection Algorithm for
Sentinel-2 Satellite |
CHEN Li1, 2, 3, WANG Shi-yong 1, 3, GAO Si-li1, 3, TAN Chang1, 2, 3, LI Lin-han1, 2, 3 |
1. Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai 200083, China
2. University of Chinese Academy of Sciences, Beijing 100049, China
3. Key Laboratory of Infrared System Detection and Imaging Technology, Chinese Academy of Sciences, Shanghai 200083, China
|
|
|
Abstract Recently, deep convolutional neural networks have made remarkable progress in visible light ship detection. However, most improve detection performance by improving large network structures, which require strong computer performance. In addition, the visible image is difficult to detect ships in the cloud, fog, sea clutter, night and other complex scenes. In order to solve these problems, this paper proposes a lightweight ship detection algorithm, which integrates the spectral information of Red, Green, Blue and NIR bands from coarse to fine. This paper uses the improved water detection algorithm to extract the ship candidate area from the existing methods that extract the water area by using the water detection algorithm according to the spectral characteristics. To obtain a more accurate candidate area, in this paper, the ships, the thick clouds, cloud, calm sea, five kinds of cluttered sea four bands of pixels in the scene have carried on the statistical analysis. Near-infrared is greater than the threshold as the auxiliary judgment, and in its center for candidate area the size of 32×32 slices, and to the maximum inhibition of slice, thus obtained the coarse detection results of the ship. Then constructs a lightweight LSGFNet network for fine identification of ship candidate regions. In the structural design of the network, the spectral features extracted by 1×1 convolution and the geometric features extracted by 3×3 are fused. In order to prevent the “information not flowing” during the fusion of spectral features and geometric features, the channel disruption mechanism in ShuffleNet is introduced in the LSGFNet network, and the model structure is reduced. Compared with the typical lightweight network, it has a better effect and a smaller model. Finally, 1 120 sets of data with 512×512 and 6014 sets of data with 32×32 were constructed for rough detection and fine network training using sentinel-2 multi-spectral 10-meter resolution data. Among them, the recall rate of rough extraction of candidate regions was 98.99%, and the fine identification network precision was 96.04%. The overall average precision is 92.98%. Experimental results show that the proposed algorithm has high detection efficiency in the complex background of suppressing clouds, sea clutter and other disturbances, the training time is short, and the computer performance demand is low.
|
Received: 2021-08-19
Accepted: 2021-11-23
|
|
|
[1] Li J, Tian J, Gao P, et al. Ship Detection and Fine-Grained Recognition in Large-Format Remote Sensing Images Based on Convolutional Neural Network. IGARSS 2020-2020 IEEE International Geoscience and Remote Sensing Symposium, 2020. 2859.
[2] Li Z, You Y, Liu F. IEEE Access, 2020, 8: 194485.
[3] Wang P, Liu J, Zhang Y, et al. Journal of Marine Science and Engineering,2021,9(9): 932.
[4] Kanjir U. Acta Astronautica, 2019, 155: 45.
[5] Xie X Y, Li B,Wei X X. Remote Sensing, 2020, 12(5): 792.
[6] WANG Wen-sheng, HUANG Min, LI Tian-jian(王文胜, 黄 民, 李天剑). Acta Optica Sinica(光学学报), 2020, 40(17): 191.
[7] SU Long-fei, LI Zhen-xuan, GAO Fei(苏龙飞, 李振轩, 高 飞). Remote Sensing of Land and Resources(国土资源遥感), 2021, 33(1): 9.
[8] ZHOU Peng, XIE Yuan-li, JIANG Guang-xin(周 鹏, 谢元礼, 蒋广鑫). Remote Sensing Information(遥感信息), 2020, 35(5): 9.
[9] Gong W B, Shi Z S, Wu Z H. International Journal of Remote Sensing, 2021, 42(7): 2622.
[10] Chen L Q, Shi W X, Deng D X. Remote Sensing, 2021, 13(4): 660.
[11] Jin L, Liu G D. Symmetry, 2021, 13(3): 495.
[12] He K, Zhang X, Ren S, et al. Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
[13] Sandler M, Howard A, Zhu M, et al. MobileNetV2: Inverted Residuals and Linear Bottlenecks. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2018.
[14] Ma N, Zhang X, Zheng H T, et al. ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design. European Conference on Computer Vision, 2018.
|
[1] |
LI Hu1, ZHONG Yun1, 2, FENG Ya-ting1, LIN Zhen1, ZHU Shi-jiang1, 2*. Multi-Vegetation Index Soil Moisture Inversion Model Based on UAV
Remote Sensing[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 207-214. |
[2] |
ZHU Wen-jing1, 2,FENG Zhan-kang1, 2,DAI Shi-yuan1, 2,ZHANG Ping-ping3,JI Wen4,WANG Ai-chen1, 2,WEI Xin-hua1, 2*. Multi-Feature Fusion Detection of Wheat Lodging Information Based on UAV Multispectral Images[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 197-206. |
[3] |
ZHANG Nan-nan1, 3, CHEN Xi-ya1,CHANG Xin-fang1, XING Jian1, GUO Jia-bo1, CUI Shuang-long1*, LIU Yi-tong2*, LIU Zhi-jun1. Distributed Design of Optical System for Multi-Spectral Temperature
Pyrometer[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(01): 230-233. |
[4] |
GAO Wei-ling, ZHANG Kai-hua*, XU Yan-fen, LIU Yu-fang*. Data Processing Method for Multi-Spectral Radiometric Thermometry Based on the Improved HPSOGA[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(12): 3659-3665. |
[5] |
ZHANG Ning-chao1, YE Xin1, LI Duo1, XIE Meng-qi1, WANG Peng1, LIU Fu-sheng2, CHAO Hong-xiao3*. Application of Combinatorial Optimization in Shock Temperature
Inversion[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(12): 3666-3673. |
[6] |
SHEN Si-cong, ZHANG Jing-xue, CHEN Ming-hui, LI Zhi-wei, SUN Sheng-nan, YAN Xue-bing*. Estimation of Above-Ground Biomass and Chlorophyll Content of
Different Alfalfa Varieties Based on UAV Multi-Spectrum[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(12): 3847-3852. |
[7] |
HAO Zi-yuan1, YANG Wei1*, LI Hao1, YU Hao1, LI Min-zan1, 2. Study on Prediction Models for Leaf Area Index of Multiple Crops Based on Multi-Source Information and Deep Learning[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(12): 3862-3870. |
[8] |
WANG Zhen-tao1, DAI Jing-min1*, YANG Sen2. Research on Multi-Spectral Thermal Imager Explosion Flame True
Temperature Field Measurment[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(12): 3885-3890. |
[9] |
LIANG Jin-xing1, 2, 3, XIN Lei1, CHENG Jing-yao1, ZHOU Jing1, LUO Hang1, 3*. Adaptive Weighted Spectral Reconstruction Method Against
Exposure Variation[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(11): 3330-3338. |
[10] |
WANG Wen-song1, PEI Chen-xi2, YANG Bin1*, WANG Zhi-xin2, QIANG Ke-jie2, WANG Ying1. Flame Temperature and Emissivity Distribution Measurement MethodBased on Multispectral Imaging Technology[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(11): 3644-3652. |
[11] |
TAO Jing-zhe1, 3, SONG De-rui1, 3, SONG Chuan-ming2, WANG Xiang-hai1, 2*. Multi-Band Remote Sensing Image Sharpening: A Survey[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(10): 2999-3008. |
[12] |
CAO Qian, MA Xiang-cai, BAI Chun-yan, SU Na, CUI Qing-bin. Research on Multispectral Dimension Reduction Method Based on Weight Function Composed of Spectral Color Difference[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(09): 2679-2686. |
[13] |
ZHU Zi-min, XING Jian*. Research on Inversion Algorithm of Multispectral Radiation Temperature Measurement Based on Bisection Iterative Recursion[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(09): 2674-2678. |
[14] |
LIU Zhao1, 2, LI Hua-peng1, CHEN Hui1, 2, ZHANG Shu-qing1*. Maize Yield Forecasting and Associated Optimum Lead Time Research Based on Temporal Remote Sensing Data and Different Model[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(08): 2627-2637. |
[15] |
XING Jian, LIU Zhi-jun, HAN Bing, HAO Xiang-wei*. Multi-Spectral True Temperature Inversion Algorithm Based on
Generalized Inverse Matrix-Coordinate Rotation Method[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(06): 1936-1940. |
|
|
|
|