Accurate assessment of electromechanical system status is essential for the safe and efficient management of airport energy stations, where pointer-meter readings serve as key operational indicators. To address pointer-meter detection under complex lighting and cluttered backgrounds, this study proposes YOLO-METER, a vision-based detection model tailored for airport energy stations. The model integrates a Triple Attention Mechanism (TAM) in the backbone to suppress background interference and employs a weighted bidirectional feature pyramid network (BiFPN) in the neck for efficient multi-scale feature fusion. Furthermore, an Improved Sparrow Search Algorithm (ISSA) is used to optimize 12 hyperparameters, substantially improving convergence and detection performance. An inspection-robot platform was built, and on-site images were collected to construct a dedicated pointer-meter detection dataset. Experimental results show that YOLO-METER achieves mAP@0.5 of 97.6%, Precision of 96.46%, and 224.8 FPS, outperforming multiple YOLO variants. These results indicate that YOLO-METER provides an effective and efficient solution for real-time pointer-meter detection, supporting autonomous inspection in airport energy stations.
ChoiHUmCYKangK, et al. (2021) Application of vision-based occupancy counting method using deep learning and performance analysis. Energy Build252: 111389.
5.
FanHLiY (2024) Image recognition and Reading of single pointer meter based on deep learning. IEEE Sens J24: 25163–25174.
6.
FengJLuoHMingR (2025) Pointer meters recognition method in the wild based on innovative deep learning techniques. Sci Rep15: 845.
7.
GuanHXiaoTLuoW, et al. (2022) Automatic fault diagnosis algorithm for hot water pipes based on infrared thermal images. Build Environ218: 109111.
8.
GuyonneauRMercierFBoucherV (2024) Robotic system for indoor illuminance map generation. J Build Eng86: 108800.
9.
HouLWangSSunX, et al. (2023) A pointer meter Reading recognition method based on YOLOX and semantic segmentation technology. Measurement218: 113241.
10.
HuDGanVJLWangT, et al. (2022) Multi-agent robotic system (MARS) for UAV-UGV path planning and automatic sensory data collection in cluttered environments. Build Environ221: 109349.
11.
JeonJJeongBBaekS, et al. (2022) Hybrid malware detection based on bi-LSTM and SPP-Net for Smart IoT. IEEE Trans Ind Inform18: 4830–4837.
12.
JiaXCaoBZhuY, et al. (2021) Field studies on thermal comfort of passengers in airport terminals and high-speed railway stations in summer. Build Environ206: 108319.
13.
LiSWangYFengC, et al. (2022) A thermal imaging flame-detection model for firefighting robot based on YOLOv4-F model. Fire5: 172.
14.
LiaoDZhangJTaoY, et al. (2024) ATBHC-YOLO: Aggregate transformer and bidirectional hybrid convolution for small object detection. Complex Intell Syst11: 38.
15.
LiuGHuYChenZ, et al. (2023a) Lightweight object detection algorithm for robots with improved YOLOv5. Eng Appl Artif Intell123: 106217.
16.
LiuWAnguelovDErhanD, et al. (2016) SSD: Single shot MultiBox detector. In: LeibeBMatasJSebeN, et al. (eds) Computer Vision – ECCV 2016. Cham: Springer International Publishing, 21–37.
17.
LiuYLiuJKeY (2020) A detection and recognition system of pointer meters in substations based on computer vision. Measurement152: 107333.
18.
LiuZYuJFengC, et al. (2023b) A hybrid forecasting method for cooling load in large public buildings based on improved long short term memory. J Build Eng76: 107238.
19.
LyuSZhouXLiZ, et al.YOLO-SCL: a lightweight detection model for citrus psyllid based on spatial channel interaction. Front Plant Sci14: 1276833. DOI: 10.3389/fpls.2023.1276833
20.
RenSHeKGirshickR, et al. (2017) Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell39: 1137–1149.
21.
SebastianRMLouisJ (2021) Understanding waste management at airports: A study on current practices and challenges based on literature review. Renew Sustain Energy Rev147: 111229.
22.
SongPLiPDaiL, et al. (2023) Boosting R-CNN: Reweighting R-CNN samples by RPN’s error for underwater object detection. Neurocomputing530: 150–164.
23.
TanMPangRLeQV. Efficientdet: Scalable and efficient object detection. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp.10778–10787.
24.
TangWYangQDaiZ, et al. (2024) Module defect detection and diagnosis for intelligent maintenance of solar photovoltaic plants: Techniques, systems and perspectives. Energy297: 131222.
25.
VigneronVDuarteLMaarefH. Z-pooling. In: 2021 18th International Multi-Conference on Systems, Signals & Devices (SSD), pp.29–34.
26.
WangAChenHLiuL, et al.YOLOv10: Real-time end-to-end object detection. Epub ahead of print 23 May 2024. DOI: 10.48550/arXiv.2405.14458.
27.
WangZIkeuraRZhangZ, et al. (2024) A general-purpose pointer meter Reading detection method based on adaptive feature fusion and data augmentation. Measurement233: 114773.
28.
WuDYingYZhouM, et al. (2024) YOLO-Claw: A fast and accurate method for chicken claw detection. Eng Appl Artif Intell136: 108919.
29.
WuXSahooDHoiSCH (2020) Recent advances in deep learning for object detection. Neurocomputing396: 39–64.
30.
WuXShiXJiangY, et al. (2021) A high-precision automatic pointer meter Reading system in low-light environment. Sensors21: 4891.
31.
XiY-A-MLiY-ZChenY-H, et al. (2024) Energy demand and carbon emission analyses of a solar-driven domestic regional environment mobile robot as household auxiliary heating and cooling method. Appl Energy371: 123743.
32.
XuLDongSWeiH, et al. (2023a) Defect signal intelligent recognition of weld radiographs based on YOLO V5-IMPROVEMENT. J Manuf Process99: 373–381.
33.
XuLYanWJiJ (2023b) The research of a novel WOG-YOLO algorithm for autonomous driving object detection. Sci Rep13: 3699.
34.
XuYGuoA (2024) Improving resource recycling based on deep learning. J Ambient Intell Smart Environ16: 527–540.
35.
YuJSuYFengC, et al. (2023) Global path planning for airport energy station inspection robots based on improved grey wolf optimization algorithm. J Intell Fuzzy Syst45: 4483–4500.
36.
ZhangJZhengZXieX, et al. (2022) ReYOLO: A traffic sign detector based on network reparameterization and features adaptive weighting. J Ambient Intell Smart Environ14: 317–334.
37.
ZhangKYuanBCuiJ, et al. (2024a) Lightweight tea bud detection method based on improved YOLOv5. Sci Rep14: 31168.
38.
ZhangLHuangZAShiC, et al. (2024b) MFPIDet: Improved YOLOV7 architecture based on multi-scale feature fusion for prohibited item detection in complex environment. Complex Intell Syst10: 8095–8108.
39.
ZhaoBZhangXZhanZ, et al. (2021) Deep multi-scale separable convolutional network with triple attention mechanism: A novel multi-task domain adaptation method for intelligent fault diagnosis. Expert Syst Appl182: 115087.
40.
ZhouTYeXLuH, et al. (2024) An adaptive and lightweight YOLOv5 detection model for lung tumor in PET/CT images. Sci Rep14: 30719.
41.
ZouZChenKShiZ, et al. (2023) Object detection in 20 years: A survey. Proc IEEE111: 257–276.
