Comparative Evaluation of YOLO Models for Human Position Recognition with UAVs During a Flood
Open Access
- 25 December 2025
- journal article
- research article
- Published by MDPI AG in Applied System Innovation
- Vol. 9 (1) , 6
Abstract
Reliable recognition of people on water from UAV imagery remains a challenging task due to strong glare, wave-induced distortions, partial submersion, and small visual scale of targets. This study proposes a hybrid method for human detection and position recognition in aquatic environments by integrating the YOLO12 object detector with optical-flow-based motion analysis, Kalman tracking, and BlazePose skeletal estimation. A combined training dataset was formed using four complementary sources, enabling the detector to generalize across heterogeneous maritime and flood-like scenes. YOLO12 demonstrated superior performance compared to earlier You Only Look Once (YOLO) generations, achieving the highest accuracy (mAP@0.5 = 0.95) and the lowest error rates on the test set. The hybrid configuration further improved recognition robustness by reducing false positives and partial detections in conditions of intense reflections and dynamic water motion. Real-time experiments on a Raspberry Pi 5 platform confirmed that the full system operates at 21 FPS, supporting onboard deployment for UAV-based search-and-rescue missions. The presented method improves localization reliability, enhances interpretation of human posture and motion, and facilitates prioritization of rescue actions. These findings highlight the practical applicability of YOLO12-based hybrid pipelines for real-time survivor detection in flood response and maritime safety workflows.Keywords
Funding Information
- Volkswagen Foundation (9D167)
- Łukasiewicz Research Network—Industrial Research Institute for Automation and Measurements PIAP
This publication has 35 references indexed in Scilit:
- YOLO advances to its genesis: a decadal and comprehensive review of the You Only Look Once (YOLO) seriesArtificial Intelligence Review, 2025
- Comparison of CNN-Based Architectures for Detection of Different Object ClassesAI, 2024
- A skeleton-based method for exercise recognition based on 3D coordinates of human jointsIAES International Journal of Artificial Intelligence (IJ-AI), 2024
- DETERMINATION AND COMPARISON METHODS OF BODY POSITIONS ON STREAM VIDEORadio Electronics, Computer Science, Control, 2023
- Human Pose Estimation Using Thermal ImagesIEEE Access, 2023
- Robust human detection system in flood related images with data augmentationMultimedia Tools and Applications, 2022
- A comparative study of optical flow methods for fluid mechanicsExperiments in Fluids, 2021
- REFERENCE POINTS METHOD FOR HUMAN HEAD MOVEMENTS TRACKINGRadio Electronics, Computer Science, Control, 2020
- Detection of bodies in maritime rescue operations using unmanned aerial vehicles with multispectral camerasJournal of Field Robotics, 2018
- Creating a drowning chain of survivalResuscitation, 2014