This paper provides a comprehensive survey of existing detection techniques for photovoltaic (PV) panel overlays and faults, focusing on two main aspects: overlay detection and fault detection. For overlay detection, the methods are categorized into image processing and deep learning approaches, with an analysis of their advantages, disadvantages, and influencing factors. Additional methods that do not rely on image processing for overlay detection are also discussed. For fault detection, the methods are categorized into electrical parameter detection, image processing-based methods, and data mining and artificial intelligence-based methods, with a discussion on their advantages and disadvantages. The paper highlights the importance of detecting overlays and faults to enhance the performance and durability of PV power generation systems, minimize energy losses, increase system reliability, and reduce maintenance costs. It also emphasizes the role of these techniques in contributing to sustainable development by reducing reliance on conventional energy sources and mitigating environmental pollution. The introduction section outlines the challenges faced by PV power generation systems, such as weather conditions, shading effects, and surface contamination, and the significant impact of overlays on PV panel efficiency. It discusses the need for regular cleaning and maintenance, as well as the limitations of manual methods, leading to the exploration of machine vision techniques for automatic detection. The paper then delves into the details of overlay detection technology based on image processing, including image acquisition, preprocessing, feature extraction, and positioning. It reviews several methods, such as those using high-resolution cameras, drones, and satellite data, and compares their advantages and limitations. The section also discusses the impact of factors like weather conditions, lighting, overlay types, and camera parameters on detection accuracy. The deep learning-based overlay detection technology is also covered, emphasizing the selection and optimization of deep learning models, data preprocessing, and hyperparameter tuning. The paper reviews several state-of-the-art deep learning models and their performance in detecting and classifying overlays, highlighting their accuracy and efficiency. Finally, the paper concludes by discussing the future research directions and challenges in PV panel overlay and fault detection technologies, emphasizing the need for more robust and efficient methods to improve the performance and reliability of PV systems.This paper provides a comprehensive survey of existing detection techniques for photovoltaic (PV) panel overlays and faults, focusing on two main aspects: overlay detection and fault detection. For overlay detection, the methods are categorized into image processing and deep learning approaches, with an analysis of their advantages, disadvantages, and influencing factors. Additional methods that do not rely on image processing for overlay detection are also discussed. For fault detection, the methods are categorized into electrical parameter detection, image processing-based methods, and data mining and artificial intelligence-based methods, with a discussion on their advantages and disadvantages. The paper highlights the importance of detecting overlays and faults to enhance the performance and durability of PV power generation systems, minimize energy losses, increase system reliability, and reduce maintenance costs. It also emphasizes the role of these techniques in contributing to sustainable development by reducing reliance on conventional energy sources and mitigating environmental pollution. The introduction section outlines the challenges faced by PV power generation systems, such as weather conditions, shading effects, and surface contamination, and the significant impact of overlays on PV panel efficiency. It discusses the need for regular cleaning and maintenance, as well as the limitations of manual methods, leading to the exploration of machine vision techniques for automatic detection. The paper then delves into the details of overlay detection technology based on image processing, including image acquisition, preprocessing, feature extraction, and positioning. It reviews several methods, such as those using high-resolution cameras, drones, and satellite data, and compares their advantages and limitations. The section also discusses the impact of factors like weather conditions, lighting, overlay types, and camera parameters on detection accuracy. The deep learning-based overlay detection technology is also covered, emphasizing the selection and optimization of deep learning models, data preprocessing, and hyperparameter tuning. The paper reviews several state-of-the-art deep learning models and their performance in detecting and classifying overlays, highlighting their accuracy and efficiency. Finally, the paper concludes by discussing the future research directions and challenges in PV panel overlay and fault detection technologies, emphasizing the need for more robust and efficient methods to improve the performance and reliability of PV systems.