DER-YOLO: A Lightweight Stage-Wise Feature Calibration Network for Onboard Real-Time Small-Object Detection
Sensors · 14.07.2026 · 26 (14) · 4462
DOI: 10.3390/s26144462 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 14.07.2026. Verfasst von Jiapei Wei und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Automotive Engineering, School of Mechanical and Electrical Engineering, Tianshui Normal University, Tianshui 741000, China. Die Arbeit nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Universiti Putra Malaysia, Gansu Provincial Education Department.
Abstract (Originalsprache)
Accurate real-time detection of small traffic objects remains a critical challenge for onboard vision-based traffic perception, particularly under conditions of weak texture, scale variation, occlusion, and limited computational resources. To address these challenges, this paper proposes DER-YOLO, a lightweight small-object-oriented detector built upon YOLO11n, specifically designed for complex traffic scenes. DER-YOLO introduces stage-wise feature calibration across the backbone, neck, and pre-head stages to enhance small-object representation. First, a Decoupled Global Context C3k2 (DGC-C3k2) module strengthens contextual representation for weak and low-saliency traffic objects after local feature extraction. Second, an ECA-guided Cross-scale Adaptive Fusion (ECAF) module adaptively balances high-level semantic cues and shallow high-resolution details to improve multi-scale feature interaction. Third, a Refined Large Selective Kernel (RLSK) module refines high-resolution spatial responses before the P3 detection head, enhancing small-object localization. Extensive experiments on KITTI and BDD100K demonstrate that DER-YOLO improves detection accuracy while maintaining real-time inference. On KITTI, it achieves 86.95% mAP@0.5 and 60.89% mAP@0.5:0.95, with small-object AP@0.5:0.95 increasing from 27.0% to 29.3%. On BDD100K, it achieves 55.05% mAP@0.5 and 29.21% mAP@0.5:0.95, with small-object AP@0.5:0.95 increasing from 12.6% to 15.2%. With 2.744 M parameters, 7.401 GFLOPs, and over 100 FPS, DER-YOLO provides an effective and lightweight solution for real-time small-object detection in onboard traffic perception scenarios.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Automotive Engineering, School of Mechanical and Electrical Engineering, Tianshui Normal University, Tianshui 741000, China.
- Department of Mechanical and Manufacturing Engineering, Faculty of Engineering, Universiti Putra Malaysia, Serdang 43400, Malaysia.
- Laboratory of Biocomposite Technology, Institute of Tropical Forestry and Forest Products, Universiti Putra Malaysia, Serdang 43400, Malaysia.
- Department of Communication Technology and Network, Faculty of Computer Science and Information Technology, Universiti Putra Malaysia, Serdang 43400, Malaysia.
ORCID-Profile: Jiapei Wei, Azizan As'arry, Khairil Anas Md Rezali, Mohd Zuhri Mohamed Yusoff
Förderung
- Universiti Putra Malaysia
- Gansu Provincial Education Department
Zitieren
APA
Wei, J., As'arry, A., Md Rezali, K. A., Mohamed Yusoff, M. Z., Hussin, M., & Mu, T. (2026). DER-YOLO: A Lightweight Stage-Wise Feature Calibration Network for Onboard Real-Time Small-Object Detection. Sensors, 26(14), 4462. https://doi.org/10.3390/s26144462
Vancouver
Wei J, As'arry A, Md Rezali KA, Mohamed Yusoff MZ, Hussin M, Mu T. DER-YOLO: A Lightweight Stage-Wise Feature Calibration Network for Onboard Real-Time Small-Object Detection. Sensors. 2026;26(14):4462. doi:10.3390/s26144462
BibTeX
@article{Wei2026,
author = {Wei, Jiapei and As'arry, Azizan and Md Rezali, Khairil Anas and Mohamed Yusoff, Mohd Zuhri and Hussin, Masnida and Mu, Tong},
title = {DER-YOLO: A Lightweight Stage-Wise Feature Calibration Network for Onboard Real-Time Small-Object Detection},
journal = {Sensors},
year = {2026},
volume = {26},
number = {14},
pages = {4462},
doi = {10.3390/s26144462}
}
EUVIMED