A multi-stage model based on YOLOv3 for defect detection in PV panels based on IR and visible imaging by unmanned aerial vehicle

Tommaso, Antonio Di; Betti, Alessandro; Fontanelli, Giacomo; Michelozzi, Benedetto

doi:10.1016/j.renene.2022.04.046

Cited by 54 publications

(26 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This proves that our cross-fusion improves the localisation accuracy, which contributes to the detection of small defects that are critical to reflector surface inspection. Compared to the YOLO series [10,20,21,22] that have been widely used in defect detection on drone imagery [5,12], and to the recent efficient TOOD [23], our model clearly performs better, in particular surpassing the popular YOLOv5 [21] by a large margin of 3.4 % in the AP. These results confirm the effectiveness of our cross-fusion design.…”

Section: Results For Fast's Surface Defect Detectionmentioning

confidence: 83%

“…Vlaminck et al [11] proposed a two-stage approach to the automatic detection of anomalies in large photovoltaic sites using drone-based imaging. Similarly, Tommaso et al [12] presented a UAV-based inspection system for improved photovoltaic diagnostics based on a multistage architecture built on top of YOLOv3 [10]. Previous works involving defect detection using aerial imagery were primarily designed to detect large defects and were not reliable for detecting very small defects.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automated optical inspection of FAST’s reflector surface using drones and computer vision

Li¹,

Jiang²,

Song³

et al. 2023

gxjzz

View full text Add to dashboard Cite

The Five-hundred-meter Aperture Spherical radio Telescope (FAST) is the world's largest single-dish radio telescope. Its large reflecting surface achieves unprecedented sensitivity but is prone to damage, such as dents and holes, caused by naturally-occurring falling objects. Hence, the timely and accurate detection of surface defects is crucial for FAST's stable operation. Conventional manual inspection involves human inspectors climbing up and examining the large surface visually, a time-consuming and potentially unreliable process. To accelerate the inspection process and increase its accuracy, this work makes the first step towards automating the inspection of FAST by integrating deep-learning techniques with drone technology. First, a drone flies over the surface along a predetermined route. Since surface defects significantly vary in scale and show high inter-class similarity, directly applying existing deep detectors to detect defects on the drone imagery is highly prone to missing and misidentifying defects. As a remedy, we introduce cross-fusion, a dedicated plug-in operation for deep detectors that enables the adaptive fusion of multi-level features in a point-wise selective fashion, depending on local defect patterns. Consequently, strong semantics and fine-grained details are dynamically fused at different positions to support the accurate detection of defects of various scales and types. Our AI-powered drone-based automated inspection is time-efficient, reliable, and has good accessibility, which guarantees the long-term and stable operation of FAST.

show abstract

Section: Results For Fast's Surface Defect Detectionmentioning

confidence: 83%

Section: Introductionmentioning

confidence: 99%

Automated optical inspection of FAST’s reflector surface using drones and computer vision

Li¹,

Jiang²,

Song³

et al. 2023

gxjzz

View full text Add to dashboard Cite

show abstract

“…In addition, the validation set was held-out until the last test. Comparing the methods proposed in this paper with the five techniques discussed in the literature, which are the YOLOv3-based method from Tommaso et al [33], the Faster-RCNN-based method from Girshick et al [54], the SVM-based method from Mantel et al [32], the Mask-RCNN-based method from Almazroue et al [55], and the SSD-based method from Ren et al [56], the results showed that our performance on the Multi-Defect dataset was much better than the other models. The specific mAP performance is listed in Table 3.…”

Section: Comparison With Other Methods On the Multi-defect Datasetmentioning

confidence: 99%

“…YOLO and Region-CNN (R-CNN) algorithms, represented by deep learning techniques, are another class of methods that rely mainly on learning a large number of samples to obtain a deep dataset feature representation with better generalization ability and robustness [9,32]. Inspired by the previous research, we use YOLOv5 as the primary network framework, which is fast while maintaining good accuracy [33,34].…”

Section: Introductionmentioning

confidence: 99%

GBH-YOLOv5: Ghost Convolution with BottleneckCSP and Tiny Target Prediction Head Incorporating YOLOv5 for PV Panel Defect Detection

Wang

Zhang

2023

Electronics

View full text Add to dashboard Cite

Photovoltaic (PV) panel surface-defect detection technology is crucial for the PV industry to perform smart maintenance. Using computer vision technology to detect PV panel surface defects can ensure better accuracy while reducing the workload of traditional worker field inspections. However, multiple tiny defects on the PV panel surface and the high similarity between different defects make it challenging to accurately identify and detect such defects. This paper proposes an approach named Ghost convolution with BottleneckCSP and a tiny target prediction head incorporating YOLOv5 (GBH-YOLOv5) for PV panel defect detection. To ensure better accuracy on multiscale targets, the BottleneckCSP module is introduced to add a prediction head for tiny target detection to alleviate tiny defect misses, using Ghost convolution to improve the model inference speed and reduce the number of parameters. First, the original image is compressed and cropped to enlarge the defect size physically. Then, the processed images are input into GBH-YOLOv5, and the depth features are extracted through network processing based on Ghost convolution, the application of the BottleneckCSP module, and the prediction head of tiny targets. Finally, the extracted features are classified by a Feature Pyramid Network (FPN) and a Path Aggregation Network (PAN) structure. Meanwhile, we compare our method with state-of-the-art methods to verify the effectiveness of the proposed method. The proposed PV panel surface-defect detection network improves the mAP performance by at least 27.8%.

show abstract

“…Previous works involving defect detection using aerial imagery were primarily designed to detect large defects and were not reliable for detecting very small defects 3 – 8 . In contrast, this work aims to inspect the large surface of FAST from on high.…”

mentioning

confidence: 99%

AI-powered drone-based automated inspection of FAST

Wang

2023

Light Sci Appl

View full text Add to dashboard Cite

show abstract

A multi-stage model based on YOLOv3 for defect detection in PV panels based on IR and visible imaging by unmanned aerial vehicle

Cited by 54 publications

References 22 publications

Automated optical inspection of FAST’s reflector surface using drones and computer vision

Automated optical inspection of FAST’s reflector surface using drones and computer vision

GBH-YOLOv5: Ghost Convolution with BottleneckCSP and Tiny Target Prediction Head Incorporating YOLOv5 for PV Panel Defect Detection

AI-powered drone-based automated inspection of FAST

Contact Info

Product

Resources

About