Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟯𝟳𝟯 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗛𝘆𝗽𝗲𝗿𝗶𝗼𝗻𝗦𝗼𝗹𝗮𝗿𝗡𝗲𝘁: 𝗦𝗼𝗹𝗮𝗿 𝗣𝗮𝗻𝗲𝗹 𝗗𝗲𝘁𝗲𝗰𝘁𝗶𝗼𝗻 𝗳𝗿𝗼𝗺 𝗔𝗲𝗿𝗶𝗮𝗹 𝗜𝗺𝗮𝗴𝗲𝘀 𝗯𝘆 𝗨𝗖 𝗕𝗲𝗿𝗸𝗲𝗹𝗲𝘆. Follow me for a similar post: Ashish Patel  ------------------------------------------------------------------- 𝗜𝗻𝘁𝗲𝗿𝗲𝘀𝘁𝗶𝗻𝗴 𝗙𝗮𝗰𝘁𝘀 : 🔸 Paper: HyperionSolarNet: Solar Panel Detection from Aerial Images 🔸 This paper is published arxiv2021. 🔸 As awareness of the impacts and risks of climate change continue to increase, efforts are being made to reduce greenhouse gas emissions. Within the energy industry, strategies are being deployed to lower carbon emissions by reducing fossil fuel energy sources and integrating renewable energy. Although solar panel production continues to increase, the integration of renewable energy is losing momentum and carbon emission reduction goals are falling short due to wavering and unsupportive policy frameworks. This paper is provide end to end framework for creating world map of solar panels. ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 With the effects of global climate change impacting the world, collective efforts are needed to reduce greenhouse gas emissions.  🔸 The energy sector is the single largest contributor to climate change and many efforts are focused on reducing dependence on carbon-emitting power plants and moving to renewable energy sources, such as solar power.  🔸 A comprehensive database of the location of solar panels is important to assist analysts and policymakers in defining strategies for further expansion of solar energy.  🔸 In this paper we focus on creating a world map of solar panels. We identify locations and total surface area of solar panels within a given geographic area.  🔸 We use deep learning methods for automated detection of solar panel locations and their surface area using aerial imagery.  🔸 The framework, which consists of a two-branch model using an image classifier in tandem with a semantic segmentation model, is trained on our created dataset of satellite images.  🔸 Our work provides an efficient and scalable method for detecting solar panels, achieving an accuracy of 0.96 for classification and an IoU score of 0.82 for segmentation performance. #computervision #artificialintelligence #innovation