Spline Approaches for Anomaly Detection in UAV-Based Aerial Surveillance

This article presents a new approach to detecting anomalies in data obtained from unmanned aerial vehicles using spline models. The relevance of the study is driven by the need for fast and accurate identification of anomalies in real time, which is critical for military intelligence and civilian monitoring. The proposed model is based on the use of momentary characteristics, such as average illumination intensity and standard deviation, which allows for effective data parameterization and detection of anomalous observations. The advantage of the spline model is its ability to adapt to complex and heterogeneous image textures, which significantly reduces the risk of missing critical anomalies. The model also demonstrates high robustness to variations in the data, making it a reliable tool for analyzing images in different lighting and landscape conditions. Experiments using forest, road, and car textures have shown that the spline model is able to accurately identify anomalies, which increases the efficiency of analysis and allows for a quick response to detected changes.