计算机科学

计算机科学 ›› 2025, Vol. 52 ›› Issue (6A): 240700035-10.doi: 10.11896/jsjkx.240700035

• 图像处理&多媒体技术 • 上一篇    下一篇

用于新能源光伏电站选址的水体分割轮廓后处理算法

武星明1, 党旗1, 江波2, 张悦超1, 周继威1, 王晓龙3   

  1. 1 龙源(北京)新能源工程技术有限公司 北京 100034
    2 中国电子科技集团公司第三十二研究所 上海 201808
    3 杭州电子科技大学计算机学院 杭州 310018
  • 出版日期:2025-06-16 发布日期:2025-06-12
  • 通讯作者: 江波(b26jiang@126.com)
  • 作者简介:(3171189283@qq.com)
  • 基金资助:
    国家重点研发计划(2023YFC3006700)

Water Segmentation Contour Post-processing Algorithm for New Energy Photovoltaic PowerStation Location

WU Xingming1, DANG Qi1, JIANG Bo2, ZHANG Yuechao1, ZHOU Jiwei1, WANG Xiaolong3   

  1. 1 Longyuan( Beijing ) New Energy Engineering Technology Co.,Ltd.,Beijing 100034,China
    2 The 32nd Research Institute of China Electronics Technology Group Corporation,Shanghai 201808,China
    3 School of Computer Science,Hangzhou Dianzi University,Hangzhou 310018,China
  • Online:2025-06-16 Published:2025-06-12
  • About author:WU Xingming,born in 1992,senior engineer.His main research interests include network information security and artificial intelligence algorithm.
    JIANG Bo,born in 1968,Ph.D,professor,doctoral supervisor.His main research interests include software defined system architecture technology and industry digital solutions research intelligent information processing,and data modeling and analysis.
  • Supported by:
    National Key R&D Program of China(2023YFC3006700).

PDF (PC)

37

摘要： 在新能源光伏电站选址过程中,利用无人机采集图像进行水域分布的分析是一个不可或缺的步骤。通常采用水体分割算法对水域图像中的水体进行分割。然而,基于模型结构的改进或单个场景训练数据集的增加,对于语义分割神经网络来说只适用于对应数据集场景的性能提升,难以保证开放场景下水体边界分割的准确度。为了解决这个问题,提出两种用于水体分割神经网络的轮廓后处理算法。与最先进的技术相比,连续轮廓后处理算法可以根据轮廓特征有效去除水体分割算法产生的异常小轮廓,同时针对复杂图像产生断续水体边界线的情况,断续轮廓处理算法通过点集重排实现水体边界线补全,两种后处理算法均能提升分割精度。以PIDNet,EGE-UNet,BiSeNetv2和Fast-SCNN为实验模型,结果表明,在水体边界线检测任务中,实验模型经连续轮廓处理后的像素准确率(PA)和平均交并比(mIoU)都有所提高,平均增量分别为2.88%和2.71%;经断续轮廓处理后,平均F1指标提高2.62%。

关键词: 新能源光伏电站选址, 水体边界分割, 连续轮廓处理算法, 断续轮廓处理算法

Abstract: In the process of site selection of new energy photovoltaic power stations,it is an indispensable step to analyze the distribution of water areas using unmanned aerial vehicle(UAV) images.The water body in water image is usually segmented by water body segmentation algorithm.However,the improvement of the model structure or the increase of the single scene training dataset is only suitable for the performance improvement of the corresponding data set scene for the semantic segmentation neural network,and it is difficult to ensure the accuracy of the water boundary segmentation in the open scene.To solve this problem,two contour post-processing algorithms for water segmentation neural networks are proposed.Compared with the most advanced technology,the continuous contour post-processing algorithm can effectively remove the abnormal small contour generated by the water body segmentation algorithm according to the contour features.At the same time,for the case of intermittent water body boundary generated by complex images,the intermittent contour processing algorithm realizes the water body boundary completion through point set rearrangement.Both post-processing algorithms can improve the segmentation accuracy.PIDNet,EGE-UNet,BiSeNetv2 and Fast-SCNN are used as experimental models.The results show that the pixel accuracy(PA) and average intersection ratio(mIoU) of the experimental model after continuous contour processing are improved in the water boundary line detection task,with an average increment of 2.85 % and 2.71 %,respectively.The average F1 index increased by 2.62 % after discontinuous contour processing.

Key words: Site selection of new energy photovoltaic power station, Water boundary segmentation, Continuous contour processing algorithm, Intermittent contour processing algorithm

中图分类号: 

  • TP391.41
[1]LI D,WU B S,CHEN B W,et al.Review of water body inforamationextraction hasedl on satellite remoke sensing[J].Jourmal of Tsinghua University(Scicnce and Technology),2020,60(2):147-161.
[2]SU L F,LI Z X,GAO F,et al.A review of remoe scnsing image water extraction[J].Remote Sensing for Land and Resources,2021,33(1):9-19.
[3]WANG H,QIN F.Summary of the research on water body extractiomnand application from remotc sensing image[J].Science of Surveying and Mapping,2018,43(5):23-32.
[4]HUANG W K,TENG F,WANG Z D,et al.Image Segmentation Based on Deep Learning:A Survey[J].Computer Science,2023,49(4):233-239.
[5]LO S W,WU J H,LIN F P,et al.Visual Sensing for Urban Flood Monitoring[J].Sensors,2015,15:20006-20029.
[6]CHEN G,BAI K,LIN Z,et al Method on water level ruler rea-ding recognition based on image processing [J].Signal lmage and Video Processing,2021,15:33-41.
[7]WILSON T,WILLIAMS S B.Adaptive Path Planning forDepth-constrained Bathymetric Mapping with an Autonomous Surface Vessel[J].Field Robot,2018,35:345-358.
[8]HUANG Y S,XU Z P,CHEN Y M,et al.Design of automatic berthing control system of USV[J].China Meas Test,2020,46(10):111-117.
[9]WANG L,WU Q,LIU J L,et al.State-of-the-art research on motion control of maritime autonomous surface ships[J].Mar Sci Eng,2019,7(12):438.
[10]BOUKOBERINE M N,ZHOU Z,BENBOUZID M.Power Supply Architectures for Drones-A Review[C]//Proceedings of the IECON 2019-45th Annual Conference of the IEEE Industrial Electronics Society.2019:5826-5831.
[11]FENG Q L,NIU B,REN Y,et al.A10-m national scale map of ground mounted photovoltaic power stations in China of 2020[J].Scientific Data,2024,11:198.
[12]CHEN Y,ZHOU J,GE Y,et al.Uncovering the rapid expansion of photovoltaic power plants in China from 2010 to 2022 using satellite data and deep learning[J].Remote Sensing Environment,2024,305:114100.
[13]XIA Z,LI Y,GUO S,et al.Satellites reveal spatial heterogeneity in dryland photovoltaic plants’ effects on vegetation dynamics[J].Earth’s Future,2024,12:e2024EF004427.
[14]MURPHY R R,STEIMLE E,GRIFFIN C,et al.Cooperative use of unmanned sea surface and micro aerial vehicles at hurricane Wilma[J].Field Robot.,2008,25(3):164-780.
[15]PEREZ-GONZALEZ P,JARAMILLO-DUQUE L,CANO-QUINTERO J B.Automatic Boundary Extraction for Photovoltaic Plants Using the Deep Learning U-Net Model[J]. Applied Sciences,2021,11(14):6524.
[16]MA C,LIU Z.Water-surface photovoltaics:Performance,utilization,and interactions with water eco-environment[J].Renewable and Sustainable Energy Reviews,2022,167.
[17]TERCAN E,DERELI M A,SARACOGLU B O.Location alternatives generation and elimination of floatovoltaics with virtual power plant designs[J].Renewable Energy,2022,193(C):1150-1163.
[18]VASILOPOULOS E,VOSINAKIS G,KROMMYDA M,et al.A comparative study of autonomous object detection algorithms in the maritime environment using a UAV platform[J].Computation,2022,10(3):42.
[19]WANG S R,SHEN F,LI R H,et al.Research on water surface flare removal and information reconstruction method of UAV hyperspectral image[J].Journal of East China Normal University(Natural Science Edition),2024(1):36-49.
[20]FU Q F,LU M,ZHANG Z Y,et al.Research on water level monitoring method based on semantic segmentation[J].Advances in Laser and Optoelectronics,2022,59(4):12.
[21]XU J C,BHATTACHARYYA S P.A pid controller architecture inspired enhancement to the pso algorithm[C]//Future of Information and Communication Conference.2022:587-603.
[22]CHENG S H,ZHAO K P,ZHANG S J,et al.Water level detection based on U-net[J].Acta Metrologica Sinica,2019,40(3):361- 366.
[23]MAGGIOR E,TARABALKA Y,CHAROIAT G,et al.can semantic labeling methods generalize to any city? the inria aerial image labeling benchmark[C]//IEEEInternational Geoscience and Remote Sensing Symposium.2017:3226-3229.
[24]WU T,VALLET B,PIERROT-DESEILLIGNY M,et al.A new stereo dense matching benchmark dataset for deep learning[J].Copernicus GmbH,2021(B2):405-412.
[25]SHI T T,GUO Z,LI X Y X.Improvement of deep learningMethod for water body segmentation of remote sensing images based on attention modules[J].Earth Science Informatics,2023,16(3):2865-2876.
[26]YAO L H,KANOULAS D,JI Z,et al.ShorelineNet:An Efficient Deep Learning Approach for Shoreline Semantic Segmentation for Unmanned Surface Vehicles[C]//Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems.2021:5403-5409.
[27]YANG Z,LI Y,WANG B,et al.A Lightweight Sea Surface Object Detection Network for Unmanned Surface Vehicles[J].Journal of Marine Science and Engineering,2022,10(7):965.
[28]BOVCON B,KRISTAN M.A water-obstacle separation and re-finement network for unmanned surface vehicles[C]//IEEE International Conference on Robotics and Automation(ICRA).2020:9470-9476.
[29]WEN Q,LI L,XIONG L,et al.A review of water body extraction research based on deep learning in remote sensing images[J].Remote Sensing for Natural Resources,2024(3).
[30]ZHAO H S,SHI J P,QI X J,et al.Pyramid Scene Parsing Network[J].arXiv:1612.01105,2016.
[31]LONG J,SHELHARMER E,DARRELL T.Fully ConvolutionalNetworks for Semantic Segmentation[J].arXiv:1411.4038,2014.
[32]CHEN L C,ZHU Y,PAPANDREOU G,et al.Encoder-decoder with atrous separable convolution for semantic image segmentation[C]//Proceedings of the European Conference on Computer Vision(ECCV).2018:801-818.
[33]XU J C,XIONG Z X,BHATTACHARYYA S P.PIDNet:A Real-time Semantic Segmentation Network Inspired by PID Controllers[J].arXiv:2206.02066,2023.
[34]PENG J C,LIU Y,TANG S Y,et al.Pp-liteseg:A superior real-time semantic segmentation model[J].arXiv:2204.02681,2022.
[35]RONNCBCRGER O,FISCHER P,BROX T.U-Net:Convolutional networks for biomedical image segmentation[C]//Medical Image Computing and Computer Assisted Intervention So-ciety.2015:234-241.
[36]ZHOU Z,RAHMAN SIDDIQUEE M M,TAJBAKHSH N,et al.Unet++:A nested u-net architecture for medical image segmentation[C]//Medical Image Computing and Computer Assisted Intervention Society.2018:3-11.
[37]SHI T T,GUO Z H,YAN X.Water body segmentation in remote sensing images based on multi-scale fusion attention mo-dule improved UNet[J].Chinese Journal of Liquid Crystals and Displays,2023,38(8):397-408.
[38]CHAI Z H,LUO J F,WEI X L.Rethinking bisenet for real-time semantic segmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:9716-9725.
[39]IOFFE S,SZEGEDY C.Batch normalization:Accelerating deep network training by reducing internal covariate shift[C]//International Conference on Machine Learning.2015:448-456.
[40]GLORITl X,BORDES A,BENGIO Y.Deep sparse rectifier neural networks[C]//International Conference on Artificial Intelligence and Statistics.2011:315-323.
[41]POUDEL R P K,LIWICKI S,CIPOLLA R.Fast-SCNN:Fast Semantic Segmentation Network[J].arXiv:1902.04502,2019.
[42]ZEILER M D,FERGUS R.Visualizing and understanding con-volutional networks[C]//European Conference on Computer Vision.2014:818-833.
[43]CANNY J.A Computational approach to edge detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1986,8(6):679-698.
[44]WU X Y,CHEN Z M,LI J J.Semi-supervised Deep Learning Network Based Water Body Segmentation Method[J].Journal of Zhengzhou University(Natural Science Edition),2023,55(6):29-34.
[45]CAO W Z,WANG T G,XU B,et al.Research on water level detection of ship lock based on semantic segmentation[J].Chinese Journal of Scientific Instrument,2023,44(2):238-247.
[46]朱战霞,李倩龙,张志昊,等.一种面向空间轻量化平台的卫星组件轮廓提取方法及系统:CN 202310251728.0[P].2023-07-14.
[47]CARBONNEAU P E,DUGDALE S J,BRECKON T P,et al.Adopting deep learning methods for airborne RGB fluvial scene classification[J].Remote Sensing of Environment,2022,251.
[48]XIA M,QIAN J,ZHANG X,J.et al.River segmentation based on separable attention residual network[J].Journal of Applied Remote Sensing,2019,14(3):1.
[49]SARP S,KUZLU M,CETIN M,et al.Detecting floodwater on roadways from image data using Mask-R-CNN[C]//Procee-dings Int.Conf.Innovations Intell.Syst.Appl..2020:1-6.
[50]RUAN J C,XIE M Y,GAO J S,et al.EGE-UNet:an Efficient Group Enhanced UNet for skin lesion segmentation[J].arXiv:2307.08473,2023.
[51]ZHANG H,CISSE M,DAUPHIN Y N,et al.mixup:BeyondEmpirical Risk Minimization[J].arXiv:1710.09412,2017.
[52]CORDTS M,OMRAN M,RAMOS S.The cityscapes dataset for semantic urban scene understanding[C]//2016 IEEE Confe-rence on Computer Vision and Pattern Recognition.2016:3213-3223.
[53]LIU Y X,ZHANG B,WANG B.Semi-supervised semantic segmentation based on Generative Adversarial Networks for remote sensing images[J].Journal of Infrared and Millimeter Waves,2020,39(4):473-482.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发