HyperionSolarNet: Solar Panel Detection from Aerial Images

Poonam, Parhar,; Sawasaki, Ryan; Todeschini, Alberto; Reed, Colorado; Vahabi, Henri; Nusaputra, Nathan; Vergara, Felipe

doi:10.48550/arxiv.2201.02107

Cited by 5 publications

(5 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Mean Relative Error (MRE) is 3% in residential areas and 2.1% in non-residential areas, which reflects good size estimation performance. Parhar et al [14] used the image classifier EfficientNet-B7 to identify images containing PV panels and then employed the semantic segmentation model U-Net to identify the pixels belonging to the panels. Furthermore, they built a website that allows users to see the visualization results of the classification and segmentation models, as well as the location and size of the PV panel regions.…”

Section: Current Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A Method for Extracting Photovoltaic Panels from High-Resolution Optical Remote Sensing Images Guided by Prior Knowledge

Liu,

Huo,

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

The extraction of photovoltaic (PV) panels from remote sensing images is of great significance for estimating the power generation of solar photovoltaic systems and informing government decisions. The implementation of existing methods often struggles with complex background interference and confusion between the background and the PV panels. As a result, the completeness and edge clarity of PV panel extraction results are compromised. Moreover, most previous studies have overlooked the unique color characteristics of PV panels. To alleviate these deficiencies and limitations, a method for extracting photovoltaic panels from high-resolution optical remote sensing images guided by prior knowledge (PKGPVN) is proposed. Firstly, aiming to address the problems related to missed extractions and background misjudgments, a Photovoltaic Index (PVI) based on visible images in the three-band is constructed to serve as prior knowledge to differentiate between PV panels and non-PV panels. Secondly, in order to strengthen information interaction between shallow features and deep features and enhance the accuracy and integrity of results, a Residual Convolution Hybrid Attention Module (RCHAM) is introduced into the skip-connection of the encoding–decoding structure. Finally, for the purpose of reducing the phenomenon of blurred edges, a multilevel Feature Loss (FL) function is designed to monitor the prediction results at different scales. Comparative experiments are conducted with seven methods, including U-Net, on publicly available datasets. The experimental results show that our PKGPVN achieves superior performance in terms of evaluation metrics such as IoU (above 82%), Precision (above 91%), Recall (above 89%), and F1-score (above 90%) on the AIR-PV dataset. Additionally, the ablation experiments illustrate the effectiveness of our key parts. The proposed method reduces the phenomena of missed extractions and background misjudgments effectively while producing highly accurate results with clear boundaries.

show abstract

Section: Current Methodsmentioning

confidence: 99%

“…Remote sensing images have complex backgrounds, and PV panels can easily be confused with other targets such as dark buildings [19], greenhouses, glass, roads, etc. [14]. • After continuous downsampling operations, the resolution of the feature map gradually decreases.…”

Section: Limitations and Proposed Solutionsmentioning

confidence: 99%

A Method for Extracting Photovoltaic Panels from High-Resolution Optical Remote Sensing Images Guided by Prior Knowledge

Liu,

Huo,

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…An innovative deep learning technique called EfficientNet-B7 was employed for PV panel detection in [27], showing better accuracy and efficiency compared to classic CNN approaches. EfficientNet-B7 was used as a backbone encoder to train a U-Net model for segmenting solar panels.…”

Section: Related Workmentioning

confidence: 99%

Detecting Photovoltaic Panels in Aerial Images by Means of Characterising Colours

Marletta,

Midolo,

Tramontana

2023

Technologies

View full text Add to dashboard Cite

The detection of photovoltaic panels from images is an important field, as it leverages the possibility of forecasting and planning green energy production by assessing the level of energy autonomy for communities. Many existing approaches for detecting photovoltaic panels are based on machine learning; however, they require large annotated datasets and extensive training, and the results are not always accurate or explainable. This paper proposes an automatic approach that can detect photovoltaic panels conforming to a properly formed significant range of colours extracted according to the given conditions of light exposure in the analysed images. The significant range of colours was automatically formed from an annotated dataset of images, and consisted of the most frequent panel colours differing from the colours of surrounding parts. Such colours were then used to detect panels in other images by analysing panel colours and reckoning the pixel density and comparable levels of light. The results produced by our approach were more precise than others in the previous literature, as our tool accurately reveals the contours of panels notwithstanding their shape or the colours of surrounding objects and the environment.

show abstract

“…Image segmentation is the task of assigning a predefined land-use class label (e.g., “Access Road”), to each pixel found in an image. Image segmentation has been widely applied to land-use quantification and land-cover classification, yet has primarily been used in energy studies focused on solar energy development. − We combined image segmentation with GIS analysis in a workflow that includes image preparation, image segmentation, and postprocessing for accurate mapping of wind energy infrastructure. Results are presented in terms of LUE (W/m 2 ) but also land transformation (m 2 /MWh) for broad applicability that includes both energy system planning and LCA.…”

Section: Introductionmentioning

confidence: 99%

Land Resources for Wind Energy Development Requires Regionalized Characterizations

Dai,

Jose Valanarasu,

Zhao

et al. 2024

Environ. Sci. Technol.

View full text Add to dashboard Cite

Estimates of the land area occupied by wind energy differ by orders of magnitude due to data scarcity and inconsistent methodology. We developed a method that combines machine learning-based imagery analysis and geographic information systems and examined the land area of 318 wind farms (15,871 turbines) in the U.S. portion of the Western Interconnection. We found that prior land use and human modification in the project area are critical for land-use efficiency and land transformation of wind projects. Projects developed in areas with little human modification have a land-use efficiency of 63.8 ± 8.9 W/m 2 (mean ±95% confidence interval) and a land transformation of 0.24 ± 0.07 m 2 /MWh, while values for projects in areas with high human modification are 447 ± 49.4 W/m 2 and 0.05 ± 0.01 m 2 /MWh, respectively. We show that land resources for wind can be quantified consistently with our replicable method, a method that obviates >99% of the workload using machine learning. To quantify the peripheral impact of a turbine, buffered geometry can be used as a proxy for measuring land resources and metrics when a large enough impact radius is assumed (e.g., >4 times the rotor diameter). Our analysis provides a necessary first step toward regionalized impact assessment and improved comparisons of energy alternatives.

show abstract

HyperionSolarNet: Solar Panel Detection from Aerial Images

Cited by 5 publications

References 7 publications

A Method for Extracting Photovoltaic Panels from High-Resolution Optical Remote Sensing Images Guided by Prior Knowledge

A Method for Extracting Photovoltaic Panels from High-Resolution Optical Remote Sensing Images Guided by Prior Knowledge

Detecting Photovoltaic Panels in Aerial Images by Means of Characterising Colours

Land Resources for Wind Energy Development Requires Regionalized Characterizations

Contact Info

Product

Resources

About