Hotspots Infrared detection of photovoltaic modules based on Hough line transformation and Faster-RCNN approach

In the last two decades, the installation and production of photovoltaic (PV) plants increased widely. As the PV system operation time grew, more and more defect occurred on the PV modules. One of the most significant open issues in the PV sector is to find appropriate inspection methods to detect PV modules' failures. In this paper, two approaches are proposed to detect the hotspots in the infrared image of PV modules. The classical digital image processing technology mainly uses Hough line transformation and canny operator to detect hotspots. The deep learning model is based on Faster-RCNN and transfer learning, which perform better with more compute resources.

[1]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Yaser M. Roshan,et al.  Comparative Study of Fine-Tuning of Pre-Trained Convolutional Neural Networks for Diabetic Retinopathy Screening , 2017, 2017 24th National and 2nd International Iranian Conference on Biomedical Engineering (ICBME).

[3]  Meng Xie,et al.  An improved Hough transform for line detection , 2010, 2010 International Conference on Computer Application and System Modeling (ICCASM 2010).

[4]  Tanupriya Choudhury,et al.  Suicide Forecast System Over Linear Regression, Decision Tree, Naïve Bayesian Networks and Precision Recall , 2018, 2018 8th International Conference on Cloud Computing, Data Science & Engineering (Confluence).

[5]  Erees Queen B. Macabebe,et al.  Image segmentation using K-means color quantization and density-based spatial clustering of applications with noise (DBSCAN) for hotspot detection in photovoltaic modules , 2016, 2016 IEEE Region 10 Conference (TENCON).

[6]  Smriti,et al.  Double Threshold-Based Energy Detection Spectrum Sensing Scheme by Considering the Sensing History in Confusion Region , 2018, 2018 5th International Conference on Signal Processing and Integrated Networks (SPIN).

[7]  Mohammadreza Aghaei,et al.  PV power plant inspection by image mosaicing techniques for IR real-time images , 2017, 2017 IEEE 44th Photovoltaic Specialist Conference (PVSC).

[8]  Xavier Martorell,et al.  Work-efficient parallel non-maximum suppression for embedded GPU architectures , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[9]  Yuying Guo,et al.  Using HOG Descriptors and UAV for Crop Pest Monitoring , 2018, 2018 Chinese Automation Congress (CAC).

[10]  Biao Hao,et al.  Research on Pedestrian Detection Based on Faster R-CNN and Hippocampal Neural Network , 2018, 2018 Tenth International Conference on Ubiquitous and Future Networks (ICUFN).

[11]  Ramjee Prasad,et al.  Automating the maintenance of photovoltaic power plants , 2017, 2017 Global Wireless Summit (GWS).

[12]  Dong Huiying,et al.  Transmission line extraction method based on Hough transform , 2015, The 27th Chinese Control and Decision Conference (2015 CCDC).

[13]  Leïla Azouz Saïdane,et al.  Monitoring road traffic with a UAV-based system , 2018, 2018 IEEE Wireless Communications and Networking Conference (WCNC).

[14]  M.K.H. Leung,et al.  Ellipse Detection with Hough Transform in One Dimensional Parametric Space , 2007, 2007 IEEE International Conference on Image Processing.

[15]  Jianchao Fan,et al.  Monitoring the thermal discharge of hongyanhe nuclear power plant with aerial remote sensing technology using a UAV platform , 2017, IGARSS.

[16]  Rui Song,et al.  Microarray camera image segmentation with Faster-RCNN , 2018, 2018 IEEE International Conference on Applied System Invention (ICASI).

[17]  Myung-Cheol Roh,et al.  Refining faster-RCNN for accurate object detection , 2017, 2017 Fifteenth IAPR International Conference on Machine Vision Applications (MVA).

[18]  Mohana,et al.  Real Time Object Detection and Tracking Using Deep Learning and OpenCV , 2018, 2018 International Conference on Inventive Research in Computing Applications (ICIRCA).

[19]  Xuan Liu,et al.  Classifying High Resolution Remote Sensing Images by Fine-Tuned VGG Deep Networks , 2018, IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium.