Intelligent Progress Recognition for PV Project Inspection via UAV: an Improved YOLO v8 Approach

YANG Yu; ZHANG Junbo; HE Tianle; CAO Zhengnong; SUN Qi

doi:10.3724/j.gyjzG26012002

Volume 56 Issue 5

May 2026

Turn off MathJax

Article Contents

Article Navigation > INDUSTRIAL CONSTRUCTION > 2026 > 56(5): 248-257

YANG Yu, ZHANG Junbo, HE Tianle, CAO Zhengnong, SUN Qi. Intelligent Progress Recognition for PV Project Inspection via UAV: an Improved YOLO v8 Approach[J]. INDUSTRIAL CONSTRUCTION, 2026, 56(5): 248-257. doi: 10.3724/j.gyjzG26012002

Citation:

YANG Yu, ZHANG Junbo, HE Tianle, CAO Zhengnong, SUN Qi. Intelligent Progress Recognition for PV Project Inspection via UAV: an Improved YOLO v8 Approach[J]. INDUSTRIAL CONSTRUCTION, 2026, 56(5): 248-257. doi: 10.3724/j.gyjzG26012002

Citation:

PDF( 2969 KB)

Intelligent Progress Recognition for PV Project Inspection via UAV: an Improved YOLO v8 Approach

doi: 10.3724/j.gyjzG26012002

YANG Yu^1,2,
ZHANG Junbo^1,2,
HE Tianle^{1,2
,
,},
CAO Zhengnong^1,2,
SUN Qi^1,2

1. Power China Huadong Engineering Co., Ltd., Hangzhou 311122, China;
2. Zhejiang Huadong Engineering Consulting Co., Ltd., Hangzhou 310014, China

Received Date: 2026-01-20
Available Online: 2026-06-06
Publish Date: 2026-05-20

Abstract

Abstract

To enhance the intelligent supervision of photovoltaic （PV） project progress and address the issue of low recognition accuracy caused by component occlusion in complex scenarios， this study proposed an automated recognition approach for key PV components that integrates UAV images with an improved object detection algorithm. In response to common challenges such as small-scale targets and occlusion interference in UAV images， this study developed an optimized non-maximum suppression mechanism and a dynamic screening strategy based on target size and category features. Experimental results showed that the improved model achieved stable convergence of the loss function during training. Its key performance indicators， including detection precision， recall， mAP50， and mAP50-95， reached 94.8%， 93.2%， 94.8%， and 96.5%， respectively. In the practical application of the Anduo PV project in Nagqu， Tibet， the average recognition accuracy for core components such as pile foundations， PV supports， and PV modules exceeded 95%， significantly outperforming traditional manual inspection methods. These findings demonstrated that the proposed approach effectively reduces target omission under occlusion through dynamic detection optimization， providing a feasible technical solution for intelligent progress monitoring in complex PV construction environments and possessing considerable practical engineering value.
- PV projects,
- YOLO v8,
- UAV image,
- target detection,
- progress recognition

FullText(HTML)

References(23)

References

[1]	MORANDUZZO T，MELGANI F. Detecting cars in UAV images with a catalog-based approach［J］. IEEE Transactions on Geoscience and Remote Sensing，2014，52（10）：6356- 6367.
[2]	SHEN Q，JIANG L，XIONG H. Person tracking and frontal face capture with UAV［C］// 2018 IEEE 18th International Conference on Communication Technology（ICCT）. IEEE. Chongqing：2018：1412- 1416.
[3]	XIE X，YANG W，CAO G，et al. Real-time vehicle detection from UAV imagery［C］// 2018 IEEE Fourth International Conference on Multimedia Big Data（BigMM）. IEEE. Xi’an：2018：1- 5.
[4]	DENG S，LI S，XIE K，et al. A global-local self-adaptive network for drone-view object detection［J］. IEEE Transactions on Image Processing，2020，30：1556- 1569.
[5]	REN S，HE K，GIRSHICK R，et al. Faster R-CNN：towards real-time object detection with region proposal networks［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence，2016，39（6）：1137- 1149.
[6]	ROSS T Y，DOLLÁR G. Focal loss for dense object detection［C］// proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu，Hawaii，USA：2017：2980- 2988.
[7]	REDMON J. You only look once：unified，real-time object detection［C］// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas，NV，USA：2016.
[8]	VAN ETTEN A. You only look twice：rapid multi-scale object detection in satellite imagery［PP/OL］.（2018-05-24）［2026-01-20］. https://arxiv.org/abs/1805.09512. arXiv：1805.09512.
[9]	REDMON J. Yolo v3：an incremental improvement［PP/OL］.（2018-04-08）［2026-01-20］. https://arxiv.org/abs/1804.02767. arXiv：1804.02767.
[10]	陈伟，江志成，田子建，等. 基于 YOLO v8 的煤矿井下人员不安全动作检测算法［J］. 煤炭科学技术，2024，52（增刊2）：267- 283.
[11]	赵金环. 基于卫星遥感与YOLT车辆检测的NO₂浓度时空分析算法研究［D］. 郑州：河南大学，2021.
[12]	江松，李研博，何旭乾，等. 基于无人机影像深度学习的滑坡灾害智能识别［J］. 中国安全科学学报，2024，34（7）：229- 238.
[13]	陈金林，吴一全，苑玉彬. 无人机视角下目标检测的YOLO系列算法研究进展［J/OL］．北京航空航天大学学报，2024［2026-01-20］. https://doi.org/10.13700/j.bh.1001-5965.2024.0420.
[14]	张润梅，肖钰霏，贾振楠，等. 改进YOLOv7的无人机视角下复杂环境目标检测算法［J］. 光电工程，2024，51（5）：92- 103.
[15]	胡惠娟，秦一锋，徐鹤，等. 面向无人机航拍图像的YOLOv8目标检测改进算法［J］. 计算机科学，2025，52（4）：202- 211.
[16]	梁燕，何孝武，邵凯，等. 改进YOLO v8的无人机航拍图像目标检测算法［J］. 计算机工程与应用，2025，61（1）：121- 130.
[17]	程换新，乔庆元，骆晓玲，等. 基于改进YOLOv8的无人机航拍图像目标检测算法［J］. 无线电工程，2024，54（4）：871- 881.
[18]	奚能业. 光伏电站无人机巡检路径优化［D］. 杭州：浙江大学，2022.
[19]	向罗巧. 光伏电站缺陷组件定位若干关键技术研究和系统设计［D］. 杭州：杭州电子科技大学，2023.
[20]	于祥跃. 基于红外图像处理的无人机光伏组件故障检测［D］. 长春：吉林大学，2023.
[21]	WANG A，CHEN H，LIU L，et al. Yolov10：real-time end-to-end object detection［J］. Advances in Neural Information Processing Systems，2024，37：107984- 108011.
[22]	ZHENG Z，WANG P，LIU W，et al. Distance-IoU loss:Faster and better learning for bounding box regression［C］// Proceedings of the AAAI Conference on Artificial Intelligence. New York，USA：2020：12993- 13000.
[23]	LI X，WANG W，WU L，et al. Generalized focal loss:learning qualified and distributed bounding boxes for dense object detection［J］. Advances in Neural Information Processing Systems，2020，33：21002- 21012.