INTELLIGENT SYSTEM FOR SITUATIONAL ANALYSIS OF UAV VIDEO STREAM BASED ON A PROBABILISTIC MODEL
Received: 2026-07-16 13:28:49
Published: 2026-04-18
Abstract
The paper addresses the problem of building an intelligent system for situational analysis of video streams obtained from an unmanned aerial vehicle. Unlike systems limited to object detection, the proposed approach is aimed at probabilistic interpretation of the observed scene. A previously developed universal UAV platform for computer vision applications is used as the hardware basis. The scientific novelty lies in formalizing situational analysis as a probabilistic classification problem based on aggregated video features with temporal dynamics taken into account. A logistic classification model is derived using the maximum likelihood principle and extended by introducing a dynamic component. The proposed approach is intended for monitoring engineering structures, technological facilities and infrastructure.
Keywords
List of references
About the Authors
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
