Improving building rooftop segmentation accuracy through the optimization of UNet basic elements and image foreground-background balance

J Yang, B Matsushita, H Zhang - ISPRS Journal of Photogrammetry and …, 2023 - Elsevier
Building rooftop segmentation using deep learning techniques is a popular yet challenging
area of research in computer vision and remote sensing image processing. While recent …

Unlocking rooftop potential for sustainable cities: A systematic review

Y Chen, Y Liu, M Slootweg, M Hu, A Tukker… - Frontiers of Engineering …, 2024 - Springer
The utilization of rooftop space offers various benefits to cities and their residents, such as
urban heat island mitigation, energy saving, and water management. However, a …

Development assessment of regional rooftop photovoltaics based on remote sensing and deep learning

Q Qi, J Zhao, Z Tan, K Tao, X Zhang, Y Tian - Applied Energy, 2024 - Elsevier
Assessing the development of rooftop photovoltaic (PV) plays a positive role in promoting
the deployment of solar installations. In response to the problem that previous studies did …

Solar-Powered Solutions for the Water and Energy Shortage Problem: The Case Study of Nahr El Bared, Lebanon

Y Kassem, H Gokcekus, IA Ab Albakoush… - … , Technology & Applied …, 2023 - etasr.com
Solar power is an effective way to reduce the dependency on conventional fuels and
mitigate the water and energy shortage issue. The main aim of the current paper is to assess …

Investigating the resolution-performance trade-off of object detection models in support of the Sustainable Development Goals

CN Clark, A Bedada, B Huff, B Lita… - IEEE Journal of …, 2023 - ieeexplore.ieee.org
Satellite imagery provides impartial, inclusive, and timely geospatial data regarding global
issues, supplementing traditional ground-based methods. The volume, velocity, and variety …

Extending cam-based xai methods for remote sensing imagery segmentation

AK Gizzini, M Shukor, AJ Ghandour - arXiv preprint arXiv:2310.01837, 2023 - arxiv.org
Current AI-based methods do not provide comprehensible physical interpretations of the
utilized data, extracted features, and predictions/inference operations. As a result, deep …

Trainable Noise Model as an XAI evaluation method: application on Sobol for remote sensing image segmentation

H Shreim, AK Gizzini, AJ Ghandour - arXiv preprint arXiv:2310.01828, 2023 - arxiv.org
eXplainable Artificial Intelligence (XAI) has emerged as an essential requirement when
dealing with mission-critical applications, ensuring transparency and interpretability of the …

Why should imminent international funds for solar photovoltaics go to families and the private sector and not to the government to stop the electricity crisis in Lebanon?

C Merheb - Energy Policy, 2024 - Elsevier
In Lebanon, the failure to supply oil-based electricity was mostly due to flawed management,
increasing costs of bills of private generators, the rise of fuel prices, and the absence of …

Mapping of utility-scale solar panel areas from 2000 to 2022 in China using Google Earth Engine

X Lyu, X Li, H Wei, J Wu, D Dang… - IEEE Journal of …, 2024 - ieeexplore.ieee.org
Solar power generation is an effective way to reduce carbon emissions and has a wide
range of applications worldwide. China's newly installed photovoltaic capacity has ranked …

Zero-Shot Refinement of Buildings' Segmentation Models using SAM

A Mayladan, H Nasrallah, H Moughnieh… - arXiv preprint arXiv …, 2023 - arxiv.org
Foundation models have excelled in various tasks but are often evaluated on general
benchmarks. The adaptation of these models for specific domains, such as remote sensing …