仿真图像作为模板的遥感影像小目标检测方法

doi:10.3778/j.issn.1002-8331.2103-0568

摘要/Abstract

摘要： 随着传感器技术和航空遥感技术的不断进步，遥感影像的质量和数量也得到了极大的提高，而遥感影像中的目标检测是理解和分析遥感影像所面临的一个基本问题。针对神经网络在遥感影像小目标检测任务中难以提取足够多的有效特征、遥感小目标易受云雾遮挡等问题，提出了一种基于仿真图像模板匹配的方法，通过特征融合的方式成功地将该方法应用于遥感影像小目标检测任务。成像仿真技术生成的仿真图像包含了更多的遥感小目标特征，如几何形状、材质等。在与深度学习结合之后，更多的特征可以提升神经网络检测遥感影像小目标的准确率。实验结果表明将基于仿真图像的模板匹配方法应用于深度学习之后，对于遥感影像小目标检测取得了较好的效果，尤其是针对受到云雾等天气干扰的小目标。

关键词: 遥感影像, 目标检测, 仿真图像, 模板, 深度学习

Abstract: With the continuous progress of sensor technology and aerial remote sensing technology, the quality and quantity of remote sensing images have been greatly improved. Target detection in remote sensing images is a basic problem in understanding and analyzing remote sensing images. Aiming at the problems that neural network is difficult to extract enough effective features in remote sensing image small target detection task, and remote sensing small target is easily blocked by cloud and fog, a method based on simulation image template matching is proposed, which is successfully applied to remote sensing image small target detection task by feature fusion. The simulation image generated by imaging simulation technology contains more features of remote sensing small target, such as geometry, material and so on. In the process of combining with deep learning, more features can improve the accuracy of neural network for small target detection in remote sensing image. The results show that the template matching method based on the simulation image is applied to the deep learning, and it achieves good detection results for small targets in remote sensing images, especially for small targets disturbed by the weather such as clouds and fog.

Key words: remote sensing image, object detection, simulation image, template, deep learning

曹亚明, 肖奇, 杨震. 仿真图像作为模板的遥感影像小目标检测方法[J]. 计算机工程与应用, 2022, 58(17): 111-119.

CAO Yaming, XIAO Qi, YANG Zhen. Remote Sensing Image Small Target Detection Method Using Simulation Image as Template[J]. Computer Engineering and Applications, 2022, 58(17): 111-119.

参考文献

[1] AKSOY S，AKCAY G，CINBIS G，et al.Automatic mapping of linearwoody vegetation features in agricultural landscapes[C]//IEEE International Geoscience & Remote Sensing Symposium，2009.
[2] LI D，WANG M，DONG Z，et al.Earth observation brain（EOB）：intelligent earth observation system[J].Geo-spatial Information Science，2017，20（2）：134-140.
[3] MCKEOWN D M，DENLINGER J L.Cooperative methods for road tracking in aerial imagery[C]//Proceedings of the 1988 DARPA IUS Workshop，1988：327-341.
[4] BARZOHAR M，COOPER D B.Automatic finding of main roads in aerial images by using geometric-stochastic models and estimation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，1996，18（7）：707-721.
[5] D’OLEIRE-OLTMANNS S，MARZOLFF I，TIEDE D，et al.Detection of gully-affected areas by applying object-based image analysis（OBIA） in the region of Taroudannt，Morocco[J].Remote Sensing，2014，6（9）：8287-8309.
[6] SAKLA W，KONJEVOD G，MUNDHENK T N.Deep multi-modal vehicle detection in aerial ISR imagery[C]//IEEE Winter Conference on Applications of Computer Vision（WACV），2017：916-923.
[7] NIE K，SOMMER L，SCHUMANN A，et al.Semantic labeling based vehicle detection in aerial imagery[C]//IEEE Winter Conference on Applications of Computer Vision（WACV），2018：626-634.
[8] ZHU X X，TUIA D，MOU L，et al.Deep learning in remote sensing：a comprehensive review and list of resources[J].IEEE Geoscience and Remote Sensing Magazine，2017，5（4）：8-36.
[9] 王志斌.仿真图像应用于深度学习的可行性方法研究[D].西安：西安电子科技大学，2020.
WANG Z B.Research on the feasibility of applying simu-lated image to deep learning[D].Xi’an：Xi’an University of Electronic Science and Technology，2020.
[10] RAZAKARIVONY S，JURIE F.Vehicle detection in aerial imagery：a small target detection benchmark[J].Journal of Visual Communication and Image Representation，2016，34：187-203.
[11] PENATTI O A B，NOGUEIRA K，DOS SANTOS J A.Do deep features generalize from everyday objects to remote sensing and aerial scenes domains?[C]//IEEE Conference on Computer Vision and Pattern Recognition（CVPR），2015：44-51.
[12] NANJUN H，PAOLETTI M E，MARIO H J，et al.Feature extraction with multiscale covariance maps for hyperspectral image classification[J].IEEE Transactions on Geoscience and Remote Sensing，2019：1-15.
[13] COURTRAI L，PHAM M T，LEFèVRE S.Small object detection in remote sensing images based on super-resolution with auxiliary generative adversarial networks[J].Remote Sensing，2020，12（19）：3152.
[14] MUNDHENK T N，KONJEVOD G，SAKLA W A，et al.A large contextual dataset for classification，detection and counting of cars with deep learning[C]//European Conference on Computer Vision.Cham：Springer，2016：785-800.
[15] 李晨阳，李立钢，杨震，等.基于三维场景的红外成像仿真框架及实现[J].计算机仿真，2020，37（7）：248-252.
LI C Y，LI L G，YANG Z，et al.Framework and implementation of infrared image simulation based on 3D scene[J].Computer Simulation，2020，37（7）：248-252.
[16] REDMON J，FARHADI A.Yolov3：an incremental improvement[J].arXiv：1804.02767，2018.
[17] JOCHER G，STOKEN A，BOROVEC J，et al.Yolov5：v3.1-bug fixes and performance improvements（Version v3.1）[Z].Zenodo，2020.
[18] JU M，LUO J，ZHANG P，et al.A simple and efficient network for small target detection[J].IEEE Access，2019，7：85771-85781.
[19] ZHANG Y，ROSSOW W B，LACIS A A，et al.Calculation of radiative fluxes from the surface to top of atmosphere based on ISCCP and other global data sets：refinements of the radiative transfer model and the input data[J].Journal of Geophysical Research：Atmospheres，2004，109：803.
[20] LUO H，CHEN C，FANG L，et al.MS-RRFSegNet：multiscale regional relation feature segmentation network for semantic segmentation of urban scene point clouds[J].IEEE Transactions on Geoscience and Remote Sensing，2020，58（12）：8301-8315.
[21] LV H，WANG Y，SHEN Y.An empirical and radiative transfer model based algorithm to remove thin clouds in visible bands[J].Remote Sensing of Environment，2016，179：183-195.
[22] LI Q，LU W，YANG J.A hybrid thresholding algorithm for cloud detection on ground-based color images[J].Journal of Atmospheric and Oceanic Technology，2011，28（10）：1286-1296.