Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

DeepSolarEye: Power Loss Prediction and Weakly Supervised Soiling Localization via Fully Convolutional Networks for Solar Panels

Domain:

environment and energy

Record type:

paperdataset
Creator:
MehAzaCheRay
Host:avatar
The impact of soiling on solar panels is an important and well-studied problem in renewable energy sector. In this paper, we present the first convolutional neural network (CNN) based approach for solar panel soiling and defect analysis. Our approach takes an RGB image of solar panel and environmental factors as inputs to predict power loss, soiling localization, and soiling type. In computer vision, localization is a complex task which typically requires manually labeled training data such as bounding boxes or segmentation masks. Our proposed approach consists of specialized four stages which completely avoids localization ground truth and only needs panel images with power loss labels for training. The region of impact area obtained from the predicted localization masks are classified into soiling types using the webly supervised learning. For improving localization capabilities of CNNs, we introduce a novel bi-directional input-aware fusion (BiDIAF) block that reinforces the input at different levels of CNN to learn input-specific feature maps. Our empirical study shows that BiDIAF improves the power loss prediction accuracy by about 3% and localization accuracy by about 4%. Our end-to-end model yields further improvement of about 24% on localization when learned in a weakly supervised manner. Our approach is generalizable and showed promising results on web crawled solar panel images. Our system has a frame rate of 22 fps (including all steps) on a NVIDIA TitanX GPU. Additionally, we collected first of it's kind dataset for solar panel image analysis consisting 45,000+ images. Accepted for publication at WACV 2018

Visit

arxiv.org

Tasks

computer visionimage classification

Tags

Computer Vision and Pattern Recognition

Similar

Fully Convolutional Networks for Diabetic Foot Ulcer SegmentationWeakly Supervised Whole Cardiac Segmentation via Attentional CNNFully convolutional networks for the classification of aerial VHR imageryWeakly-Supervised Learning-Based Feature Localization in Confocal Laser Endomicroscopy Glioma ImagesOptimizing Weather Forecasting Accuracy via Radial Basis Function Networks, Convolutional Neural Networks and Convolutional Neural NetworksiEldesouky/Predicting-Power-Output-of-Solar-Panels-in-Egypt-

Fully Convolutional Networks for Diabetic Foot Ulcer Segmentation

Diabetic Foot Ulcer (DFU) is a major complication of Diabetes, which if not managed properly can lea

Weakly Supervised Whole Cardiac Segmentation via Attentional CNN

Part 2: Machine Learning International audience Whole-heart segmentation aims to deli

Fully convolutional networks for the classification of aerial VHR imagery

International audience Remote sensing images provide the capability to obtain informa

Weakly-Supervised Learning-Based Feature Localization in Confocal Laser Endomicroscopy Glioma Images

Confocal Laser Endomicroscope (CLE) is a novel handheld fluorescence imaging device that has shown p

Optimizing Weather Forecasting Accuracy via Radial Basis Function Networks, Convolutional Neural Networks and Convolutional Neural Networks

Weather forecasting is crucial for various sectors, including agriculture, disaster management, and

iEldesouky/Predicting-Power-Output-of-Solar-Panels-in-Egypt-

Predicting Power Output of Solar Panels in Egypt # ☀️ Solar Power Prediction for Aswan, Egypt