OSFormer: One-Step Transformer for Infrared Video Small Object Detection
IEEE Transactions on Image Processing · 2025 · 34 · 5725-5736
DOI: 10.1109/tip.2025.3598426 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2025. Verfasst von Haolin Qin und 4 weiteren Autor:innen. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 57 Literaturangaben. Gefördert von: Aeronautical Science Foundation of China.
Abstract (Originalsprache)
Infrared video small object detection is pivotal in numerous security and surveillance applications. However, existing deep learning-based methods, which typically rely on a two-step paradigm of frame-by-frame detection followed by temporal refinement, struggle to effectively utilize temporal information. This is particularly challenging when detecting small objects against complex backgrounds. To address these issues, we introduce the One-Step Transformer (OSFormer), a novel method that pioneeringly integrates a small-object-friendly transformer with a one-step detection paradigm. Unlike traditional methods, OSFormer processes the video sequence only through a single inference, encoding the sequence into cube format data and tracking object motion trajectories. Additionally, we propose the Varied-Size Patch Attention (VPA) module, which generates patches of varying sizes to capture adaptive attention features, bridging the gap between transformer architectures and small object detection. To further enhance detection accuracy, OSFormer incorporates a Doppler Adaptive Filter, which integrates traditional filtering techniques into an end-to-end neural network to suppress background noise and accentuate small objects. OSFormer outperforms YOLOv8-s on both the AntiUAV dataset (+ $3.1\%~\text {mAP}_{50}$ , - $35.1\%~\text {Params}$ ) and the InfraredUAV dataset (+ $4.0\%~\text {mAP}_{50-95}$ , - $51.0\%~\text {FLOPs}$ ), demonstrating superior efficiency and effectiveness in small object detection. The code is available on https://github.com/q2479036243/OSFormer.
Förderung
- Aeronautical Science Foundation of China
Zitieren
APA
Qin, H., Xu, T., Tang, Y., Xu, F., & Li, J. (2025). OSFormer: One-Step Transformer for Infrared Video Small Object Detection. IEEE Transactions on Image Processing, 34, 5725-5736. https://doi.org/10.1109/tip.2025.3598426
Vancouver
Qin H, Xu T, Tang Y, Xu F, Li J. OSFormer: One-Step Transformer for Infrared Video Small Object Detection. IEEE Transactions on Image Processing. 2025;34:5725-5736. doi:10.1109/tip.2025.3598426
BibTeX
@article{Qin2025,
author = {Qin, Haolin and Xu, Tingfa and Tang, Yuan and Xu, Fengxiang and Li, Jianan},
title = {OSFormer: One-Step Transformer for Infrared Video Small Object Detection},
journal = {IEEE Transactions on Image Processing},
year = {2025},
volume = {34},
pages = {5725--5736},
doi = {10.1109/tip.2025.3598426}
}
EUVIMED