GitHub
The goal of this project is to develop a tool to locate solar panels in high resolution satellite images, which could passively and automatically monitor the size and location of distributed residential solar
The goal of this project is to develop a tool to locate solar panels in high resolution satellite images, which could passively and automatically monitor the size and location of distributed residential solar
Aiming at the problem of low detection accuracy of existing deep learning-based photovoltaic panel defect detection methods, an improved Mask R-CNN photovoltaic panel defect
The existing approaches that are relevant to our work can be grouped into 3 categories: Existing approaches for solar panel detection in satellite images or similar tasks, Mask- CNN Architectures,
In this guide, you''ll learn how to use Mask R-CNN, a powerful instance segmentation model, to build solar panel detection system using TensorFlow''s Object Detection API.
The retractable photovoltaic wings are the headline feature here, and for good reason. When parked, they deploy from beneath the seat and unfold into a circular solar array that Mask claims captures up
In this work, Mask R-CNN algorithm is used to identify solar photovoltaic (PV) panels in aerial images and create a mask that can be used to remove the background from the images. This allows
MASK Architects recently unveiled an electric motorcycle concept called the Solaris. It''s a slick-looking two-wheeler, but what really caught our attention is a set of retractable wings covered...
This proposed method can accurately segment the PV panels and then identify different sizes of hot-spot defects on the PV panels.
This paper proposes a multimodal PV defect segmentation framework based on a modified Mask R-CNN architecture that fuses RGB, IR, and EL modalities at the feature level.
This paper suggests an improved Mask R-CNN-based intelligent detection method for PV panel faults. The FPN in the Mask R-CNN model is improved to BiFPN to better reflect the original image
PDF version includes complete article with source references. Suitable for printing and offline reading.