浏览全部资源
扫码关注微信
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 100039
Received:31 March 2022,
Revised:21 April 2022,
Published:25 February 2023
移动端阅览
肖术明,张叶,常旭岭等.面向航天光学遥感场景压缩感知测量值的舰船检测[J].光学精密工程,2023,31(04):517-532.
XIAO Shuming,ZHANG Ye,CHANG Xuling,et al.Ship detection oriented to compressive sensing measurements of space optical remote sensing scenes[J].Optics and Precision Engineering,2023,31(04):517-532.
肖术明,张叶,常旭岭等.面向航天光学遥感场景压缩感知测量值的舰船检测[J].光学精密工程,2023,31(04):517-532. DOI: 10.37188/OPE.20233104.0517.
XIAO Shuming,ZHANG Ye,CHANG Xuling,et al.Ship detection oriented to compressive sensing measurements of space optical remote sensing scenes[J].Optics and Precision Engineering,2023,31(04):517-532. DOI: 10.37188/OPE.20233104.0517.
基于压缩感知的航天光学遥感成像系统可以在采样阶段通过硬件同时完成采样和压缩。在面临舰船检测任务时,系统需要重建原始场景,CS的场景重建过程计算量大、内存要求高且耗时。本文提出了直接对成像系统测量值进行舰船检测的算法——基于压缩感知和改进YOLO的测量值舰船检测算法。为了模拟成像系统的分块压缩采样过程,利用步长和卷积核尺寸相等的卷积测量层对场景进行卷积运算,将高维图像信号投影到低维空间得到全图CS测量值。得到场景的测量值后,测量值舰船检测网络从测量值中提取舰船的位置信息。在主干网络中导入SENet模块,利用改进后的主干网络来提取测量值的舰船特征信息;利用特征金字塔网络强化特征提取的同时融合浅层、中层和高层的特征信息,进而完成舰船的位置信息预测。其中,CS-IM-YOLO将卷积测量层和CS测量值舰船检测网络连接起来端对端训练,大大简化了算法的预处理过程。通过数据集HRSC2016评测算法性能,实验结果表明:CS-IM-YOLO对于SORS场景CS测量值舰船检测的检测精度为91.60%,召回率为87.59%,F1值为0.90,和AP值为94.13%。这充分表明该算法可以对SORS场景的CS测量值进行高质量的舰船检测。
The compressive sensing (CS)-based space optical remote-sensing (SORS) imaging system can simultaneously perform sampling and compression by using hardware at the sensing stage. The system must reconstruct the original scene during the ship detection task. The scene reconstruction process of CS is computationally expensive, memory intensive, and time-consuming. This paper proposes an algorithm named compressive sensing and improved you only look once (CS-IM-YOLO) for direct ship detection based on measurements obtained by the imaging system. To simulate the block compression sampling process of the imaging system, the convolution measurement layer with the same stride and convolution kernel size is used to perform the convolution operation on the scene, and the high-dimensional image signal is projected into the low-dimensional space to obtain the full-image CS measurements. After obtaining the measurements of the scene, the proposed ship detection network extracts the coordinates of the ship from the measurements. The squeeze-and-excitation Network (SENet) module is imported into the backbone network, and the improved backbone network is used to extract the ship feature information using the measurements. The feature pyramid network is used to enhance feature extraction while fusing the feature information of the shallow, middle, and deep layers, and then to complete predicting the ship's coordinates. CS-IM-YOLO especially connects the convolutional measurement layer and the CS based ship detection network for end-to-end training; this considerably simplifies the preprocessing process. We present an evaluation of the performance of the algorithm by using the HRSC2016 dataset. The experimental results show that the precision of CS-IM-YOLO for detection of ships via CS measurements in SORS scenes is 91.60%, the recall is 87.59%, the F1 value is 0.90, and the AP value is 94.13%. This demonstrates that the algorithm can perform accurate ship detection using the CS measurements of SORS scenes.
曹佃生 , 石振华 , 林冠宇 . 机载海洋改进型Dyson高光谱成像仪的研制 [J]. 光学 精密工程 , 2017 , 25 ( 6 ): 1403 - 1409 . doi: 10.3788/OPE.20172506.1403 http://dx.doi.org/10.3788/OPE.20172506.1403
CAO D SH , SHI ZH H , LIN G Y . Development of airborne ocean modified Dyson hyperspectral imager [J]. Opt. Precision Eng. , 2017 , 25 ( 6 ): 1403 - 1409 . (in Chinese) . doi: 10.3788/OPE.20172506.1403 http://dx.doi.org/10.3788/OPE.20172506.1403
赵云峰 , 李夜金 , 张寅 , 等 . 海洋背景下运动目标的天基红外探测场景生成系统 [J]. 光学 精密工程 , 2017 , 25 ( 4 ): 487 - 493 . doi: 10.3788/ope.20172504.1019 http://dx.doi.org/10.3788/ope.20172504.1019
ZHAO Y F , LI Y J , ZHANG Y , et al . A space-based infrared detection scene generation system for moving objects with sea background [J]. Opt. Precision Eng. , 2017 , 25 ( 4 ): 487 - 493 . (in Chinese) . doi: 10.3788/ope.20172504.1019 http://dx.doi.org/10.3788/ope.20172504.1019
姜鑫 , 陈武雄 , 聂海涛 , 等 . 航空遥感影像的实时舰船目标检测 [J]. 光学 精密工程 , 2020 , 28 ( 10 ): 2360 - 2369 . doi: 10.37188/ope.20202810.2360 http://dx.doi.org/10.37188/ope.20202810.2360
JIANG X , CHEN W X , NIE H T , et al . Real-time ship target detection based on aerial remote sensing images [J]. Opt. Precision Eng. , 2020 , 28 ( 10 ): 2360 - 2369 . (in Chinese) . doi: 10.37188/ope.20202810.2360 http://dx.doi.org/10.37188/ope.20202810.2360
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 [J]. 光学 精密工程 , 2018 , 26 ( 3 ): 723 - 732 . doi: 10.3788/ope.20182603.0723 http://dx.doi.org/10.3788/ope.20182603.0723
WANG H L , ZHU M , LIN CH B , et al . Ship detection of complex sea background in optical remote sensing images [J]. Opt. Precision Eng. , 2018 , 26 ( 3 ): 723 - 732 . (in Chinese) . doi: 10.3788/ope.20182603.0723 http://dx.doi.org/10.3788/ope.20182603.0723
JAYAWEERA S K . Signal Processing for Cognitive Radios [M]. Hoboken : John Wiley & Sons Inc , 2015 . doi: 10.1002/9781118824818 http://dx.doi.org/10.1002/9781118824818
DONOHO D L . Compressed sensing [J]. IEEE Transactions on Information Theory , 2006 , 52 ( 4 ): 1289 - 1306 . doi: 10.1109/tit.2006.871582 http://dx.doi.org/10.1109/tit.2006.871582
CANDES E J , ROMBERG J , TAO T . Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information [J]. IEEE Transactions on Information Theory , 2006 , 52 ( 2 ): 489 - 509 . doi: 10.1109/tit.2005.862083 http://dx.doi.org/10.1109/tit.2005.862083
RICHARD BARANIUK . A lecture on compressive sensing [J]. IEEE Signal Processing Magazine , 2007 , 24 ( 4 ): 1 - 9 . doi: 10.1109/msp.2007.4286571 http://dx.doi.org/10.1109/msp.2007.4286571
刘吉英 , 朱炬波 , 严奉霞 , 等 . 基于压缩感知理论的稀疏遥感成像系统设计 [J]. 系统工程与电子技术 , 2010 , 32 ( 8 ): 1618 - 1623 . doi: 10.3969/j.issn.1001-506X.2010.08.14 http://dx.doi.org/10.3969/j.issn.1001-506X.2010.08.14
LIU J J , ZHU J B , YAN F X , et al . Design of remote sensing imaging system based on compressive sensing [J]. Systems Engineering and Electronics , 2010 , 32 ( 8 ): 1618 - 1623 . (in Chinese) . doi: 10.3969/j.issn.1001-506X.2010.08.14 http://dx.doi.org/10.3969/j.issn.1001-506X.2010.08.14
ZHANG X D , XIE J N , LI C L , et al . MEMS-based super-resolution remote sensing system using compressive sensing [J]. Optics Communications , 2018 , 426 : 410 - 417 . doi: 10.1016/j.optcom.2018.05.046 http://dx.doi.org/10.1016/j.optcom.2018.05.046
LIU J , ZHU J , YAN F , et al . Theoretical frameworks of remote sensing systems based on compressive sensing [J]. Mathematics , Environmental Science, 2010 .
DU J , XIE X M , WANG C Y , et al . Color image reconstruction with perceptual compressive sensing [C]. 2018 24th International Conference on Pattern Recognition (ICPR). 2024,2018 , Beijing, China. IEEE , 2018 : 1512 - 1517 . doi: 10.1109/icpr.2018.8546222 http://dx.doi.org/10.1109/icpr.2018.8546222
LOHIT S , KULKARNI K , KERVICHE R , et al . Convolutional neural networks for noniterative reconstruction of compressively sensed images [J]. IEEE Transactions on Computational Imaging , 2018 , 4 ( 3 ): 326 - 340 . doi: 10.1109/tci.2018.2846413 http://dx.doi.org/10.1109/tci.2018.2846413
YAO H T , DAI F , ZHANG S L , et al . DR 2 -Net: deep Residual Reconstruction Network for image compressive sensing [J]. Neurocomputing , 2019 , 359 ( C ): 483 - 493 . doi: 10.1016/j.neucom.2019.05.006 http://dx.doi.org/10.1016/j.neucom.2019.05.006
GUO H Y , YANG X , WANG N N , et al . A rotational libra R-CNN method for ship detection [J]. IEEE Transactions on Geoscience and Remote Sensing , 2020 , 58 ( 8 ): 5772 - 5781 . doi: 10.1109/tgrs.2020.2969979 http://dx.doi.org/10.1109/tgrs.2020.2969979
WANG Z Q , ZHOU Y , WANG F T , et al . SDGH-net: ship detection in optical remote sensing images based on Gaussian heatmap regression [J]. Remote Sensing , 2021 , 13 ( 3 ): 499 . doi: 10.3390/rs13030499 http://dx.doi.org/10.3390/rs13030499
WANG Q , SHEN F Y , CHENG L F , et al . Ship detection based on fused features and rebuilt YOLOv3 networks in optical remote-sensing images [J]. International Journal of Remote Sensing , 2021 , 42 ( 2 ): 520 - 536 . doi: 10.1080/01431161.2020.1811422 http://dx.doi.org/10.1080/01431161.2020.1811422
WANG Y Y , WANG C , ZHANG H , et al . Automatic ship detection based on RetinaNet using multi-resolution Gaofen-3 imagery [J]. Remote Sensing , 2019 , 11 ( 5 ). doi: 10.3390/rs11050531 http://dx.doi.org/10.3390/rs11050531
魏玮 , 杨茹 , 朱叶 . 改进CenterNet的遥感图像目标检测 [J]. 计算机工程与应用 , 2021 , 57 ( 6 ): 191 - 199 .
WEI W , YANG R , ZHU Y . Target detection of improved CenterNet to remote sensing images [J]. Computer Engineering and Applications , 2021 , 57 ( 6 ): 191 - 199 . (in Chinese)
胡炎 , 单子力 , 高峰 . 基于Faster-RCNN和多分辨率SAR的海上舰船目标检测 [J]. 无线电工程 , 2018 , 48 ( 2 ): 96 - 100 . doi: 10.3969/j.issn.1003-3106.2018.02.04 http://dx.doi.org/10.3969/j.issn.1003-3106.2018.02.04
HU Y , SHAN Z L , GAO F . Ship detection based on faster-RCNN and multiresolution SAR [J]. Radio Engineering , 2018 , 48 ( 2 ): 96 - 100 . (in Chinese) . doi: 10.3969/j.issn.1003-3106.2018.02.04 http://dx.doi.org/10.3969/j.issn.1003-3106.2018.02.04
陈科峻 , 张叶 . 基于YOLO-v3模型压缩的卫星图像船只实时检测 [J]. 液晶与显示 , 2020 , 35 ( 11 ): 1168 - 1176 . doi: 10.37188/yjyxs20203511.1168 http://dx.doi.org/10.37188/yjyxs20203511.1168
CHEN K J , ZHANG Y . Real-time ship detection in satellite images based on YOLO-v3model compression [J]. Chinese Journal of Liquid Crystals and Displays , 2020 , 35 ( 11 ): 1168 - 1176 . (in Chinese) . doi: 10.37188/yjyxs20203511.1168 http://dx.doi.org/10.37188/yjyxs20203511.1168
FU D , GUIMARAES G . Using compression to speed up image classification in artificial neural networks [EB/OL]. [ 2016-12-10 ]. https://www.danfu.org/files/CompressionImageClassification.pdf https://www.danfu.org/files/CompressionImageClassification.pdf
TORFASON R , MENTZER F , AGUSTSSON E , et al . Towards image understanding from deep compression without decoding [EB/OL]. 2018 : arXiv : 1803 . 06131 . https://arxiv.org/abs/1803.06131 https://arxiv.org/abs/1803.06131
DEGUERRE B , CHATELAIN C , GASSO G . Fast object detection in compressed JPEG Images [C]. 2019 IEEE Intelligent Transportation Systems Conference (ITSC). New York : ACM , 2019 : 333 - 338 . doi: 10.1109/itsc.2019.8916937 http://dx.doi.org/10.1109/itsc.2019.8916937
SHI W Z , JIANG F , LIU S H , et al . Image compressed sensing using convolutional neural network [J]. IEEE Transactions on Image Processing , 2020 , 29 : 375 - 388 . doi: 10.1109/tip.2019.2928136 http://dx.doi.org/10.1109/tip.2019.2928136
ZHAO Z , XIE X , WANG C , et al . ROI-CSNet: Compressive sensing network for ROI-aware image recovery [J]. Signal Processing: Image Communication , 2019 , 78 : 113 - 124 . doi: 10.1016/j.image.2019.06.006 http://dx.doi.org/10.1016/j.image.2019.06.006
KULKARNI K , LOHIT S , TURAGA P , et al . ReconNet: non-iterative reconstruction of images from compressively sensed measurements [C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2730,2016 , Las Vegas, NV, USA. IEEE , 2016 : 449 - 458 . doi: 10.1109/cvpr.2016.55 http://dx.doi.org/10.1109/cvpr.2016.55
YAO H T , DAI F , ZHANG S L , et al . DR 2 -Net: deep Residual Reconstruction Network for image compressive sensing [J]. Neurocomputing , 2019 , 359 ( C ): 483 - 493 . doi: 10.1016/j.neucom.2019.05.006 http://dx.doi.org/10.1016/j.neucom.2019.05.006
REDMON J , FARHADI A . YOLOv 3: an incremental improvement [EB/OL]. 2018 : arXiv : 1804 . 02767 . https://arxiv.org/abs/1804.02767 https://arxiv.org/abs/1804.02767 . doi: 10.1109/cvpr.2017.690 http://dx.doi.org/10.1109/cvpr.2017.690
LIN T Y , GOYAL P , GIRSHICK R , et al . Focal Loss for Dense Object Detection [J]. IEEE Transactions on Pattern Analysis & Machine Intelligence , 2017 , 99 : 2999 - 3007 . doi: 10.1109/iccv.2017.324 http://dx.doi.org/10.1109/iccv.2017.324
DUAN K , BAI S , XIE L , et al . CenterNet: Object Detection with Keypoint Triplets [EB/OL]. [ 2019-04-17 ]. https://arxiv.org/pdf/1904.08189v1.pdf https://arxiv.org/pdf/1904.08189v1.pdf . doi: 10.1109/iccv.2019.00667 http://dx.doi.org/10.1109/iccv.2019.00667
WANG Q , SHEN F Y , CHENG L F , et al . Ship detection based on fused features and rebuilt YOLOv3 networks in optical remote-sensing images [J]. International Journal of Remote Sensing , 2021 , 42 ( 2 ): 520 - 536 . doi: 10.1080/01431161.2020.1811422 http://dx.doi.org/10.1080/01431161.2020.1811422
LIU Z K , WANG H Z , WENG L B , et al . Ship rotated bounding box space for ship extraction from high-resolution optical satellite images with complex backgrounds [J]. IEEE Geoscience and Remote Sensing Letters , 2016 , 13 ( 8 ): 1074 - 1078 . doi: 10.1109/lgrs.2016.2565705 http://dx.doi.org/10.1109/lgrs.2016.2565705
0
Views
732
下载量
2
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution