Method of UAV Aerial Image Analysis Based on SSIM and MSE for Assessing the Reliability of Technical Systems

This article presents an automated method for analyzing aerial images from unmanned aerial vehicles (UAVs), aimed at improving the reliability of technical systems and tracking changes in natural and anthropogenic processes. The objective of this work is to develop an algorithm that ensures accurate detection of anomalies and prediction of potential failure threats based on image processing. The methodology involves the application of the Structural Similarity Index (SSIM) and Mean Squared Error (MSE) for assessing spatial variations between adjacent segments of the imagery. The proposed approach is characterized by high stability to changes in illumination, low computational costs, and the possibility of integration into autonomous UAV systems. This work is based on computer modeling and statistical analysis of anomaly detection accuracy. The algorithm was tested on various datasets of aerial images using machine vision techniques and mathematical statistics to evaluate the effectiveness of the proposed method. The results include the development and validation of the algorithm, the construction of SSIM and MSE heatmaps, as well as the evaluation of the accuracy and reliability of the method. The obtained data confirm its effectiveness in automated monitoring of infrastructure facilities and the assessment of environmental risks. The scope of application of the developed method encompasses automated surveillance of engineering structures, monitoring the condition of agricultural lands, analyzing the consequences of natural disasters, and environmental control. The method can be integrated into intelligent control systems for the reliability of technical objects. In conclusion, the developed algorithm significantly enhances the accuracy of anomaly detection, minimizes the influence of external factors, and automates the aerial image processing workflow. Its application contributes to improving the reliability of technical systems and reducing the probability of failures through the early identification of potential threats. Scientific Novelty: The scientific novelty lies in the development of a new method for assessing spatial variations based on a combination of the Structural Similarity Index (SSIM) and Mean Squared Error (MSE), which provides high accuracy in anomaly detection. In contrast to traditional image analysis methods, the proposed algorithm is characterized by robustness to changing imaging conditions, and its computational efficiency allows for real-time application. Furthermore, the method can be integrated into autonomous monitoring systems, expanding the capabilities of intelligent data analysis from UAVs. The obtained results and proposed solutions can be used to improve technologies for automated condition monitoring of objects and analysis of the dynamics of natural processes.

UAV, Aerial images, SSIM, MSE, Spatially invariant matching, Change detection, Technical system reliability, automated image analysis, failure risk prediction, intelligent control systems