一种基于决策融合策略的全天空地基云图云量估计方法

方明; 张利箭

doi:10.19912/j.0254-0096.tynxb.2022-1024

PDF(4694 KB)

太阳能学报 ›› 2023, Vol. 44 ›› Issue (10) : 245-254. DOI: 10.19912/j.0254-0096.tynxb.2022-1024

一种基于决策融合策略的全天空地基云图云量估计方法

方明, 张利箭²

作者信息 +

CLOUD COVER ESTIMATION METHOD OF ALL-SKY GROUND-BASED CLOUD IMAGE BASED ON DECISION FUSION STRATEGY

Fang Ming, Zhang Lijian²

Author information +

文章历史 +

摘要

云量对光伏发电有至关重要的影响。全天空地基云图云量估计的重点在于对全天空图像进行畸变矫正,以及设计准确率高的地基云分割方法。针对这两个问题,提出一种基于决策融合策略的云量估计模型。首先,通过基于多维球切面透视投影模型的鱼眼畸变矫正算法,获取多方位的局部复原图像;其次,采用最近邻复原中心的决策融合方法对多维复原图像分割后的数据进行修正,最终获取云量估计值。实验表明：该方法更好地复原了云和天空的比例关系,提高了云量估计的准确性。

Abstract

Cloud coverage has a crucial impact on photovoltaic power generation. The key point of cloud cover estimation is to correct the distortion of the all-sky image and to design the segmentation method of ground-based cloud with high accuracy. Aiming at these two problems, this paper proposes a cloud cover estimation model based on decision fusion strategy. Firstly, the fisheye distortion correction algorithm based on the perspective projection model of multi-dimensional spherical section is used to obtain multi-directional local restoration images. Secondly, the decision fusion method of the nearest neighbor restoration center is used to modify the data after multi-dimensional restoration image segmentation, and finally, the estimated cloud cover is obtained. Experimental results show that this method can restore the proportion relationship between cloud and sky better and improve the accuracy of cloud cover estimation.

导出引用

方明, 张利箭. 一种基于决策融合策略的全天空地基云图云量估计方法[J]. 太阳能学报. 2023, 44(10): 245-254 https://doi.org/10.19912/j.0254-0096.tynxb.2022-1024

Fang Ming, Zhang Lijian. CLOUD COVER ESTIMATION METHOD OF ALL-SKY GROUND-BASED CLOUD IMAGE BASED ON DECISION FUSION STRATEGY[J]. Acta Energiae Solaris Sinica. 2023, 44(10): 245-254 https://doi.org/10.19912/j.0254-0096.tynxb.2022-1024

中图分类号： TP391 TN911.73

参考文献

[1] ZHUO W, CAO Z G, XIAO Y.Cloud classification of ground-based images using texture-structure features[J]. Journal of atmospheric and oceanic technology, 2014, 31(1): 79-92.
[2] 高晓清, 蒋俊霞, 汪宁渤, 等. 基于TSI地基云图的云量反演方法研究[J]. 太阳能学报, 2018, 39(1): 95-100.
GAO X Q, JIANG J X, WANG N B, et al.Study on the retrieval method of cloud coverage based on TSI imagers[J]. Acta energiae solaris sinica, 2018, 39(1): 95-100.
[3] 蒋俊霞, 高晓清, 吕清泉, 等. 基于地基云图的云跟踪与太阳辐照度超短期预报方法研究[J]. 太阳能学报, 2020, 41(5): 351-358.
JIANG J X, GAO X Q, LYU Q Q, et al.Study on cloud tracking and solar irradiance ultra-short-term forecasting based on TSI images[J]. Acta energiae solaris sinica, 2020, 41(5): 351-358.
[4] CAZORLA A, OLMO F J, ALADOS-ARBOLEDAS L.Development of a sky imager for cloud cover assessment[J]. Journal of the Optical Society of America A, 2008, 25(1): 29-39.
[5] SHIELDS J E, JOHNSON R W, KARR M E, et al.Daylight visible/NIR whole-sky imagers for cloud and radiance monitoring in support of UV research programs[J]. Proceedings of SPIE, 2003, 5156: 155-166.
[6] 杨达, 王孝通, 徐冠雷, 等. 一种基于图像分割和图像拼接技术的全天空云量估计方法[J]. 新型工业化, 2014, 4(8): 15-21.
YANG D, WANG X T, XU G L, et al.A method of whole-sky cloud coverage estimation base on image segmentation and mosaic[J]. The journal of new industrialization, 2014, 4(8): 15-21.
[7] 朱想, 周海, 丁杰, 等. 全天空云图图像复原算法[J]. 计算机辅助设计与图形学学报, 2014, 26(6): 896-902.
ZHU X, ZHOU H, DING J, et al.All-sky cloud map image restoration algorithm research[J]. Journal of computer-aided design & computer graphics, 2014, 26(6): 896-902.
[8] 陶法, 胡树贞, 张雪芬. 地基可见光/红外全天空成像仪数据融合[J]. 气象, 2018, 44(4): 518-525.
TAO F, HU S Z, ZHANG X F.Data fusion for base ground visible/infrared whole sky imager[J]. Meteorological monthly, 2018, 44(4): 518-525.
[9] 朱均超, 葛磊, 韩芳芳, 等. 基于分离参数标定的鱼眼镜头成像模型研究[J]. 传感技术学报, 2013, 26(7): 975-980.
ZHU J C, GE L, HAN F F, et al.Research on fisheye lens imaging model based on the separated parameters calibration[J]. Chinese journal of sensors and actuators, 2013, 26(7): 975-980.
[10] SCHNEIDER D, SCHWALBE E, MAAS H G.Validation of geometric models for fisheye lenses[J]. ISPRS journal of photogrammetry and remote sensing, 2009, 64(3): 259-266.
[11] LU L J, LIU M, SHI Y.Correction method of image distortion of fisheye lens[J]. Infrared and laser engineering, 2019, 48(9): 926002.
[12] SONG R H, ZHOU G Q, WANG Q Y, et al.Fisheye image correction based on three-dimensional control field[J]. IOP conference series: earth and environmental science, 2021, 783(1): 012073.
[13] 杨前华, 李尤, 赵力. 基于改进球面投影模型的鱼眼图像校正算法的研究[J]. 电子器件, 2019, 42(2): 449-452.
YANG Q H, LI Y, ZHAO L.Research on correction algorithm of fish eye image based on improved spherical projection model[J]. Chinese journal of electron devices, 2019, 42(2): 449-452.
[14] 刘亿静, 苗长云, 杨彦利. 基于经纬映射的径向畸变快速校正算法的研究[J]. 激光杂志, 2015, 36(1): 1-4.
LIU Y J, MIAO C Y, YANG Y L.Rapid radial distortion correction algorithm based on latitude and longitude of image mapping[J]. Laser journal, 2015, 36(1): 1-4.
[15] 魏利胜, 周圣文, 张平改, 等. 基于双经度模型的鱼眼图像畸变矫正方法[J]. 仪器仪表学报, 2015, 36(2): 377-385.
WEI L S, ZHOU S W, ZHANG P G, et al.Double longitude model based correction method for fish-eye image distortion[J]. Chinese journal of scientific instrument, 2015, 36(2): 377-385.
[16] 沈慧想, 夏旻, 施必成, 等. 对称式密集连接网络的地基云图分割方法[J]. 计算机工程与应用, 2019, 55(17): 207-213.
SHEN H X, XIA M, SHI B C, et al.Ground-based cloud image segmentation method based on symmetric convolutional neural network with dense connection[J]. Computer engineering and applications, 2019, 55(17): 207-213.
[17] DEV S, NAUTIYAL A, LEE Y H, et al.CloudSegNet: a deep network for nychthemeron cloud image segmentation[J]. IEEE geoscience and remote sensing letters, 2019, 16(12): 1814-1818.
[18] SHI C J, ZHOU Y T, QIU B.CloudU-Netv2: a cloud segmentation method for ground-based cloud images based on deep learning[J]. Neural processing letters, 2021, 53(4): 2715-2728.
[19] 叶亮. 地基云图像的云状识别技术研究[D]. 武汉: 华中科技大学, 2019.
YE L.Research on cloud type recognition in ground-based cloud images[D]. Wuhan: Huazhong University of Science and Technology, 2019.
[20] 周辉, 罗飞, 李慧娟, 等. 基于柱面模型的鱼眼影像校正方法的研究[J]. 计算机应用, 2008, 28(10): 2664-2666.
ZHOU H, LUO F, LI H J, et al.Study on fisheye image correction based on cylinder model[J]. Journal of computer applications, 2008, 28(10): 2664-2666.
[21] SALENTINIG A, GAMBA P.Data-and decision-level fusion for classification[M]//Comprehensive remote sensing. Amsterdam: Elsevier, 2018: 134-155.
[22] YANG H, DU Q, MA B.Decision fusion on supervised and unsupervised classifiers for hyperspectral imagery[J]. IEEE geoscience and remote sensing letters, 2010, 7(4): 875-879.
[23] 王志舟. 鱼眼成像全景漫游系统的研究[D]. 天津: 天津大学, 2016.
WANG Z Z.Research of panoramic roaming system based on fisheye images[D]. Tianjin: Tianjin University, 2016.
[24] LI X, PI Y D, JIA Y L, et al.Fisheye image rectification using spherical and digital distortion models[C]//Tenth International Symposium on Multispectral Image Processing and Pattern Recognition. Xiangyang, China, 2017.
[25] 郑伟. 基于信息融合方法的MRI脑肿瘤图像分割[D]. 成都: 电子科技大学, 2021.
ZHENG W.MRI brain tumor image segmentation based on information fusion method[D]. Chengdu: University of Electronic Science and Technology of China, 2021.
[26] QIN X B, ZHANG Z C, HUANG C Y, et al.U²-Net: going deeper with nested U-structure for salient object detection[J]. Pattern recognition, 2020, 106: 107404.
[27] DUAN J W, MAO S Q, JIN J W, et al.A novel GA-based optimized approach for regional multimodal medical image fusion with super pixel segmentation[J]. IEEE access, 2021, 9: 96353-96366.