English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

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

Photovoltaic Panel Defect Detection Based on Ghost Convolution with BottleneckCSP and Tiny Target Prediction Head Incorporating YOLOv5