Dynamical System Modeling and Stability Investigation�DSMSI-2025
May 08-10, 2025, Kyiv, Ukraine
Exploring Neural Network Methods for Software of Military Object Detection in UAV Images
Oleksii Bychkov, Kateryna Merkulova,
Yelyzaveta Zhabska, and Ivan Ivanenko�
Taras Shevchenko National University of Kyiv
Introduction
UAVs are aircraft that operate without a pilot onboard. These vehicles can be used in various fields, including military, civilian, and commercial applications. In the military sphere, UAVs are often used for intelligence gathering, reconnaissance, precision strike targeting, and even weapon deployment. In the civilian sector, they can be used for aerial photography, monitoring forests and land areas, search and rescue operations, and many other purposes.
UAVs are employed to address a wide range of civil and military tasks such as monitoring, photography, and mapping of terrain for scientific or other purposes, mail and cargo delivery, and providing assistance in emergency situations [1-3]. They are used in various sectors of the economy including agriculture, construction, and energy. UAVs used for military purposes can carry out reconnaissance tasks, such as covert aerial surveillance of the enemy.
The automation of detecting and classifying military objects in the video stream from UAVs during wartime is one of the key factors for ensuring national security and effective control. Building a video stream processing system that comes from UAVs, creating an automated target recognition system, is an extremely important task. Currently, the most complex information processing system is the UAV operator’s brain. However, the constant need for heightened attention, significant eye strain, and working at night imposes a heavy burden on the human operator [4].
This topic is highly relevant in wartime conditions, as drones play a key role in modern combat operations. Therefore, fast and accurate detection and classification of military objects in the video stream from UAVs is a crucial task that addresses the urgent security and defense needs of our nation.
Dynamical System Modeling and Stability Investigation, DSMSI-2025
Analysis of Related Solutions and Problem Definition
Software products for processing video streams from UAVs, designed for object detection:
• Pix4Dmapper – focuses on surface analysis.
• DroneDeploy – specializes in creating maps and 3D models.
• AgroScout – used for plant disease diagnostics and crop monitoring.
The software being developed will target a different domain—detection and classification of various types of objects related to military applications. This issue is especially relevant under wartime conditions, as drones have become an essential tool in modern warfare. Thus, the rapid identification of suspicious objects in the video stream from UAVs is a critical task in the current context.
Dynamical System Modeling and Stability Investigation, DSMSI-2025
Research Methods
There are already a variety of methods and algorithms that show good results in this area under certain conditions. Identifying the required military objects in the UAV video stream can be a challenging task, and choosing the best detection and classification algorithm is crucial for achieving high-accuracy recognition results. Three of the most popular and widely used methods for object detection and classification based on neural networks were chosen:
In Faster R-CNN, the Region Proposal Network (RPN) was introduced to generate candidate regions, while Fast R-CNN was used for object detection within these regions. These two stages were combined into a single network by sharing features. The RPN takes an image as input and returns a set of coordinates of rectangular regions (which are candidates for classification), along with probability scores indicating the likelihood of an object being present in those regions.
YOLO (You Only Look Once) is a single-stage object detector that achieves both speed and accuracy. This neural network is designed for object detection and is distinguished by its ability to quickly and accurately identify objects in images and videos. The model can process data in real-time. This is achieved because it does not perform the process of object localization at multiple levels of the image, which is typically common in other object detection architectures.
The SSD (Single Shot Multibox Detector) model utilizes the idea of a pyramidal hierarchy of network outputs for identifying objects at different scales. The image passes sequentially through convolutional layers, which reduce its dimensions. The output signal from the last layer of each size is used to make decisions regarding object detection, forming what is known as the "pyramidal feature" of the image.
Dynamical System Modeling and Stability Investigation, DSMSI-2025
Research Methodology
During the research process, these criteria will be applied to methods for detecting and classifying military objects in video streams from UAVs. Based on personal experience and information from open sources, the most relevant quality indicators for such methods are as follows:
1. Ratio of correctly identified objects to the total number of objects – this criterion allows to assess how effectively the model identifies objects in the video stream.
2. Intersection over Union (IoU) – this metric measures the accuracy with which the model determines the location of objects in the video stream.
3. Average object localization time – this criterion reflects the processing and localization speed of objects by the investigated method.
Dynamical System Modeling and Stability Investigation, DSMSI-2025
Research Methodology
Dynamical System Modeling and Stability Investigation, DSMSI-2025
Research Methodology
Dynamical System Modeling and Stability Investigation, DSMSI-2025
Research Methodology
Dynamical System Modeling and Stability Investigation, DSMSI-2025
Research Methodology
Dynamical System Modeling and Stability Investigation, DSMSI-2025
Research Results
Training process of the SSD model
Dynamical System Modeling and Stability Investigation, DSMSI-2025
Training process of the Faster R-CNN model
Training process of the YOLO model
Research Results
Dynamical System Modeling and Stability Investigation, DSMSI-2025
Final training results of the models
Experiment | classification_loss | localization_loss |
Faster R-CNN | 0.01114 | 0.01048 |
SSD | 0.1289 | 0.07844 |
YOLO | 0.579 | 0.2881 |
| R | IoUс | T |
Faster R-CNN | 0.94706 | 0.94158 | 0.09325 |
SSD | 0.90882 | 0.89421 | 0.0478 |
YOLO | 0.96176 | 0.90083 | 0.03345 |
Results of quality criteria calculations for identification methods
Research Results
Dynamical System Modeling and Stability Investigation, DSMSI-2025
IoU(N) function graphs for three methods
Research Results
Dynamical System Modeling and Stability Investigation, DSMSI-2025
Graphs of the R(N) function for three methods
Research Results
Dynamical System Modeling and Stability Investigation, DSMSI-2025
Graphs of the T(N) function for three methods
Conclusion
1. The Faster R-CNN-based method predicts the location of military targets most accurately (best for the IoU metric).
2. The YOLO-based method identifies military targets the fastest (best for the T metric).
As observed from the results, the SSD-based method did not outperform in any of the three quality criteria, so it is not considered a viable candidate for the future implementation of a military target detection and classification system for UAV video streams.
Thus, a more detailed analysis of the results for the Faster R-CNN and YOLO methods is necessary to determine the most relevant method based on the computed quality criteria. Since neither method showed the best results across all three criteria, the next step is to prioritize each quality criterion. This will allow for a selection based on the context of the task to be solved using these methods.
The R quality criterion, which evaluates the ability of the method to detect and classify military targets, is the most important and should be given the highest priority. This is because methods with a higher R value are capable of detecting more camouflaged military targets, such as people in military uniforms blending with the environment. This is particularly important in the context of territory monitoring and control using drones. The T quality criterion, which characterizes the speed of the method, should be given second priority because the methods will operate not with static images, but with real-time video streams from drones. To process and analyze all frames from the video stream in time, high-speed performance is essential. If the speed is insufficient, frames that may contain military targets will be skipped, resulting in missed detections. Therefore, the IoU quality criterion, which assesses the accuracy of object localization, takes third priority, as it is important for evaluating placement accuracy, but it does not carry as much weight as the ability to identify and classify objects.
Based on the established priorities, the most relevant method for the given context will be determined. According to the R quality criterion, which holds the highest priority, the Faster R-CNN and YOLO methods showed nearly identical results, making it impossible to determine a clear winner at this point. Moving to the T metric, which has the second priority, the clear winner is the YOLO-based method, as it is almost three times faster than the Faster R-CNN-based method based on the obtained results. Considering the final priority criterion, IoU, it was noted that Faster R-CNN performed 4.5% better than YOLO, but this advantage is minimal and not significant, as the IoU criterion holds the lowest priority. Therefore, given that the YOLO-based method was nearly three times faster than the Faster R-CNN-based method, the YOLO-based method was selected for the further development of the military target detection and classification system in UAV video streams.
Dynamical System Modeling and Stability Investigation, DSMSI-2025
Thank you for your attention