Solar container field segmentation plan

Can deep learning be used in solar photovoltaic system image segmentation?

Author to whom correspondence should be addressed. In the realm of solar photovoltaic system image segmentation, existing deep learning networks focus almost exclusively on single image sources both in terms of sensors used and image resolution. This often prevents the wide deployment of such networks.

Can deep solar PV refiner improve PV segmentation from satellite imagery?

To overcome the challenges, this study proposes Deep Solar PV Refiner, a detail-oriented deep learning network, to enhance PV segmentation from satellite imagery.

Can a size-aware deep-learning network segment small-scale solar PV systems?

Wang et al. developed a size-aware deep-learning-based network for segmenting small-scale rooftop solar PV systems from high-resolution images. The size-aware network has performed well when it comes to the transfer of the application of the network to different datasets of similar pixel resolution.

How to enhance PV segmentation from satellite imagery with deep learning?

Zhu et al. introduce a method to enhance PV segmentation from satellite imagery with a detail-oriented deep learning network using a Deeplabv3+ based Network. The network combines a Split-Attention Network and a Dual-Attention module with Atrous Spatial Pyramid Pooling (ASSP).

Does different image data affect PV segmentation performance?

Since, to the best of our knowledge, there is no research conducted that presents a model of PV segmentation that uses a variety of different image data with different resolutions and sensors for training at the same time, the effect of diverse image data on performance will be examined in more detail in this paper.

Is PV segmentation a significant improvement?

This means that there is a notable improvement in PV segmentation when PV areas are significantly small and imbalanced to negative ones. For instance, small PV areas that are easily influenced by rooftops with similar textures are successfully identified and extracted from images by the model having PRM (Fig. 7).