Dynamically Optimized Object Detection Algorithms for Aviation Safety

Infrared imaging technology demonstrates significant advantages in aviation safety monitoring due to its exceptional all-weather operational capability and anti-interference characteristics, particularly in scenarios requiring real-time detection of aerial objects such as airport airspace management...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Electronics (Basel) Jg. 14; H. 17; S. 3536
Hauptverfasser: Qu, Yi, Wang, Cheng, Xiao, Yilei, Ju, Haijuan, Wu, Jing
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Basel MDPI AG 04.09.2025
Schlagworte:
Accuracy
Aeronautics
Air safety
Aircraft accidents & safety
Algorithms
Aviation
Background noise
Clutter
Computer vision
Convolution
Decoupling
Deep learning
Design
Efficiency
False alarms
Imaging systems
Infrared imaging
Infrared tracking
Learning strategies
Midair collisions
Monitoring
Neural networks
Object recognition
Optimization
Parameters
Pyramids
Radiation
Real time
Safety and security measures
Signal to noise ratio
Spatial resolution
Surveillance
Target detection
ISSN:2079-9292, 2079-9292
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Infrared imaging technology demonstrates significant advantages in aviation safety monitoring due to its exceptional all-weather operational capability and anti-interference characteristics, particularly in scenarios requiring real-time detection of aerial objects such as airport airspace management. However, traditional infrared target detection algorithms face critical challenges in complex sky backgrounds, including low signal-to-noise ratio (SNR), small target dimensions, and strong background clutter, leading to insufficient detection accuracy and reliability. To address these issues, this paper proposes the AFK-YOLO model based on the YOLO11 framework: it integrates an ADown downsampling module, which utilizes a dual-branch strategy combining average pooling and max pooling to effectively minimize feature information loss during spatial resolution reduction; introduces the KernelWarehouse dynamic convolution approach, which adopts kernel partitioning and a contrastive attention-based cross-layer shared kernel repository to address the challenge of linear parameter growth in conventional dynamic convolution methods; and establishes a feature decoupling pyramid network (FDPN) that replaces static feature pyramids with a dynamic multi-scale fusion architecture, utilizing parallel multi-granularity convolutions and an EMA attention mechanism to achieve adaptive feature enhancement. Experiments demonstrate that the AFK-YOLO model achieves 78.6% mAP on a self-constructed aerial infrared dataset—a 2.4 percentage point improvement over the baseline YOLO11—while meeting real-time requirements for aviation safety monitoring (416.7 FPS), reducing parameters by 6.9%, and compressing weight size by 21.8%. The results demonstrate the effectiveness of dynamic optimization methods in improving the accuracy and robustness of infrared target detection under complex aerial environments, thereby providing reliable technical support for the prevention of mid-air collisions.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2079-9292
2079-9292
DOI:10.3390/electronics14173536