Cloud fluctuations cause variations in the concentrated energy flux density of tower solar power systems, and these variations produce thermal stress and fatigue in the receiver. To reduce the influence of clouds, accurate cloud identification is required. A cloud instance segmentation model based on YOLOv8 was proposed. The C2f module in the Neck was replaced with a multi-scale dilated attention (MSDA) module to achieve model lightweighting. Standard convolution layers were substituted with arbitrary kernel convolution (AKConv) to improve the extraction of cloud features. The spatial pyramid pooling fast (SPPF) module was upgraded to the SPPFCSPC structure to enable richer multi-scale spatial information extraction from sky images.The accuracy of the improved MAS-YOLO model’s target detection indicators is 75.8%. The recall of the target detection indicators is 65.5%, and the mean accuracy of the target detection indicators is 75.1%. The accuracy of the segmentation indicators is 79.9%, the recall of the segmentation indicators is 62.9%, and the mean accuracy of the segmentation indicators is 74.7%. The computational complexity is 54.6 GFLOPs. On the SWIMSEG dataset, MAS-YOLO was compared with other models. The results show that its recognition performance is better than that of the other models, and heat-map comparisons indicate that it extracts cloud features more effectively. This model provides methodological support for optimizing the performance of tower solar energy systems.
WAN Zhen-jie, SU Ji-kang, GENG Xin, WU Yan-min.
Cloud Instance Segmentation Algorithm Based on MAS-YOLOv8n[J].
Science Technology and Engineering, 2026, 26(8): 3386-3396 DOI:10.12404/j.issn.1671-1815.2501903
BaiJieyu, DongCun, WangZheng, et al. Ultra-short-term prediction of photovoltaic power generation considering cloud cover[J]. High Voltage Engineering, 2023, 49(1): 159-168.
[4]
范燚杰. 塔式电站集热岛中的定日镜与云检测研究[D]. 南京: 南京师范大学, 2020.
[5]
FanYijie. Research on the heliostat and cloud detection in the urban heat island of tower power stations[D]. Nanjing: Nanjing Normal University, 2020.
[6]
GerhardtC, WeidnerF, BrollW. SkyCloud: neural network-based sky and cloud segmentation from natural images[C]// 2023 8th International Conference on Image, Vision and Computing (ICIVC). New York: IEEE, 2023: 343-351.
[7]
NiuY, SongJ, ZouL, et al. Cloud detection method using ground-based sky images based on clear sky library and superpixel local threshold[J]. Renewable Energy, 2024, 226: 120452.
[8]
HuF, HouB, ZhuW, et al. CloudY-Net: a deep convolutional neural network architecture for joint segmentation and classification of ground-based cloud images[J]. Atmosphere, 2023, 14(9): 1405.
WangBoyue, LiYingxiang, ZhongJiandan. Segmentation network for day and night ground-based cloud images based on improved Res-UNet[J]. Journal of Computer Applications, 2024, 44(4): 1310-1316.
WangMin, LiSheng, ZhuangZhihao, et al. Ground-based cloud graph segmentation method based on deep learning semantic segmentation network[J]. Science Technology and Engineering, 2023, 23(31): 13204-13216.
[17]
FengD, Haase-SchützC, RosenbaumL, et al. Deep multi-modal object detection and semantic segmentation for autonomous driving: Datasets, methods, and challenges[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 22(3): 1341-1360.
[18]
BaranwalN, SinghK N, SinghA K. YOLO-based ROI selection for joint encryption and compression of medical images with reconstruction through super-resolution network[J]. Future Generation Computer Systems, 2024, 150: 1-9.
[19]
ZhengH, ChenX, ChengH, et al. MD-YOLO: surface defect detector for industrial complex environments[J]. Optics and Lasers in Engineering, 2024, 178: 108170.
[20]
WeiP, YanX, YanW, et al. Precise extraction of targeted apple tree canopy with YOLO-Fi model for advanced UAV spraying plans[J]. Computers and Electronics in Agriculture, 2024, 226: 109425.
[21]
XuD, WuY. FE-YOLO: a feature enhancement network for remote sensing target detection[J]. Remote Sensing, 2021, 13(7): 1311.
[22]
SelvamP, KoilrajJ A S. A deep learning framework for grocery product detection and recognition[J]. Food Analytical Methods, 2022, 15(12): 3498-3522.
[23]
WangC Y, BochkovskiyA, LiaoH Y M. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2023: 7464-7475.
[24]
GeZ, LiuS, WangF, et al. Yolox: Exceeding yolo series in 2021[J]. arXiv Preprint, arXiv: 2107.08430, 2021.
[25]
JiaoJ, TangY M, LinK Y, et al. Dilateformer: Multi-scale dilated transformer for visual recognition[J]. IEEE Transactions on Multimedia, 2023, 25: 8906-8919.
[26]
ZhangX, SongY, SongT, et al. AKConv: convolutional kernel with arbitrary sampled shapes and arbitrary number of parameters[J]. arXiv Preprint, arXiv: 2311.11587, 2023.
[27]
DosovitskiyA. An image is worth 16x16 words: Transformers for image recognition at scale[J]. arXiv Preprint, arXiv: 2010.11929, 2020.
[28]
DevS, LeeY H, WinklerS. Color-based segmentation of sky/cloud images from ground-based cameras[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016, 10(1): 231-242.
[29]
WangC Y, BochkovskiyA, LiaoH Y M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2023: 7464-7475.
[30]
WangC Y, YehI H, Mark LiaoH Y. Yolov9: Learning what you want to learn using programmable gradient information[C]// European Conference on Computer Vision. Cham: Springer, 2025: 1-21.
[31]
KhanamR, HussainM. YOLOv11: an overview of the key architectural enhancements[J]. arXiv Preprint, arXiv: 2410. 17725, 2024.
PDF
(13815KB)
