{"id":12483,"date":"2025-03-27T09:10:22","date_gmt":"2025-03-27T06:10:22","guid":{"rendered":"https:\/\/coie-nahrain.edu.iq\/en\/?p=12483"},"modified":"2025-04-13T12:50:46","modified_gmt":"2025-04-13T09:50:46","slug":"graduation-project-solar-panel-detection-within-aerial-images-using-yolov10-deep-learning-model","status":"publish","type":"post","link":"https:\/\/coie-nahrain.edu.iq\/en\/graduation-project-solar-panel-detection-within-aerial-images-using-yolov10-deep-learning-model\/","title":{"rendered":"Graduation Project: Solar panel detection within aerial images using YOLOV10 deep learning model"},"content":{"rendered":"

In today’s world, solar panel systems are widely recognized as one of the most environmentally friendly infrastructures, providing clean energy, moderate costs, and high efficiency. Despite these advantages, challenges remain, particularly regarding the random installation of solar panels on rooftops, which can reduce their efficiency and even lead to damage. Additionally, manual monitoring of these systems is costly, time-consuming, and requires a large workforce.<\/p>\n

Fortunately, recent advancements in artificial intelligence (AI), particularly deep learning (DL) models, offer a promising solution for detecting and monitoring the performance of solar panel systems. However, effectively applying these technologies requires the use of appropriate aerial image datasets.<\/p>\n

In his graduation project, Mohammed Mahdi Awad<\/strong>, from the Systems Engineering\u00a0department,<\/strong> and under the supervision of Asst. Lect. Israa Nadheer<\/strong>, introduced an innovative framework for solar panel detection. This framework leverages the cutting-edge DL detection model, You Only Look Once (YOLOV10), which was released in 2024. The model is trained on aerial images where solar panels are often located far from the camera and are surrounded by complex backgrounds, sometimes comprising less than 1% of the entire image.<\/p>\n

A key feature of Mohammed\u2019s project is the post-processing algorithm, which calculates the area percentage of the solar panel system and determines the orientation of each panel. This provides valuable statistical and organizational information that can help optimize the installation of solar panels in cities and villages.<\/p>\n

The project achieved impressive results, with precision, recall, and mAP50 scores of 89.5%, 75.6%, and 84.7%, respectively, on the test set. Moreover, the model was tested on a variety of external samples, demonstrating its ability to accurately detect, localize, and assess the solar panels\u2019 orientation and area in aerial images.<\/p>\n

Mohammed\u2019s work offers a significant advancement in the monitoring and optimization of solar panel systems. By integrating this model into sustainable infrastructure initiatives, cities and communities can improve the installation process and ensure the long-term efficiency of solar energy systems.<\/p>\n

\"\" \"\"<\/p>\n","protected":false},"excerpt":{"rendered":"

In today’s world, solar panel systems are widely recognized as one of the most environmentally friendly infrastructures, providing clean energy, moderate costs, and high efficiency. Despite these advantages, challenges remain, particularly regarding the random installation of solar panels on rooftops, which can reduce their efficiency and even lead to damage. Additionally, manual monitoring of these systems is costly, time-consuming, and requires a large workforce. Fortunately, recent advancements in artificial intelligence (AI), particularly deep learning (DL) models, offer a promising solution for detecting and monitoring the performance of solar panel systems. However, effectively applying these technologies requires the use of appropriate aerial image datasets. In his graduation project, Mohammed Mahdi Awad, from the Systems Engineering\u00a0department, and under the supervision of Asst. Lect. Israa Nadheer, introduced an innovative framework for solar panel detection. This framework leverages the cutting-edge DL detection model, You Only Look Once (YOLOV10), which was released in 2024. The model is trained on aerial images where solar panels are often located far from the camera and are surrounded by complex backgrounds, sometimes comprising less than 1% of the entire image. A key feature of Mohammed\u2019s project is the post-processing algorithm, which calculates the area percentage of the solar panel system and determines the orientation of each panel. This provides valuable statistical and organizational information that can help optimize the installation of solar panels in cities and villages. The project achieved impressive results, with precision, recall, and mAP50 scores of 89.5%, 75.6%, and 84.7%, respectively, on the test set. Moreover, the model was tested on a variety of external samples, demonstrating its ability to accurately detect, localize, and assess the solar panels\u2019 orientation and area in aerial images. Mohammed\u2019s work offers a significant advancement in the monitoring and optimization of solar panel systems. By integrating this model into sustainable infrastructure initiatives, cities and communities can improve the installation process and ensure the long-term efficiency of solar energy systems.<\/p>\n","protected":false},"author":4,"featured_media":12484,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[25],"tags":[],"class_list":["post-12483","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-research"],"views":43,"_links":{"self":[{"href":"https:\/\/coie-nahrain.edu.iq\/en\/wp-json\/wp\/v2\/posts\/12483","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/coie-nahrain.edu.iq\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/coie-nahrain.edu.iq\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/coie-nahrain.edu.iq\/en\/wp-json\/wp\/v2\/users\/4"}],"replies":[{"embeddable":true,"href":"https:\/\/coie-nahrain.edu.iq\/en\/wp-json\/wp\/v2\/comments?post=12483"}],"version-history":[{"count":4,"href":"https:\/\/coie-nahrain.edu.iq\/en\/wp-json\/wp\/v2\/posts\/12483\/revisions"}],"predecessor-version":[{"id":12510,"href":"https:\/\/coie-nahrain.edu.iq\/en\/wp-json\/wp\/v2\/posts\/12483\/revisions\/12510"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/coie-nahrain.edu.iq\/en\/wp-json\/wp\/v2\/media\/12484"}],"wp:attachment":[{"href":"https:\/\/coie-nahrain.edu.iq\/en\/wp-json\/wp\/v2\/media?parent=12483"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/coie-nahrain.edu.iq\/en\/wp-json\/wp\/v2\/categories?post=12483"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/coie-nahrain.edu.iq\/en\/wp-json\/wp\/v2\/tags?post=12483"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}