Open Access

ARTICLE

Improved YOLO11 for Maglev Train Foreign Object Detection

Qinzhen Fang^1,2, Dongliang Peng^1,2, Lu Zeng^1,2,*, Zixuan Jiang^1,2

1 School of Electrical Engineering and Automation, Jiangxi University of Science and Technology, Ganzhou, 341000, China
2 Jiangxi Key Laboratory of Maglev Rail Transit Equipment, Ganzhou, 341000, China

* Corresponding Author: Lu Zeng. Email:

Journal on Artificial Intelligence 2025, 7, 469-484. https://doi.org/10.32604/jai.2025.073016

Received 09 September 2025; Accepted 11 October 2025; Issue published 06 November 2025

Abstract

To address the issues of small target miss detection, false positives in complex scenarios, and insufficient real-time performance in maglev train foreign object intrusion detection, this paper proposes a multi-module fusion improvement algorithm, YOLO11-FADA (Fusion of Augmented Features and Dynamic Attention), based on YOLO11. The model achieves collaborative optimization through three key modules: The Local Feature Augmentation Module (LFAM) enhances small target features and mitigates feature loss during down-sampling through multi-scale feature parallel extraction and attention fusion. The Dynamically Tuned Self-Attention (DTSA) module introduces learnable parameters to adjust attention weights dynamically, and, in combination with convolution, expands the receptive field to suppress complex background interference. The Weighted Convolution 2D (wConv2D) module optimizes convolution kernel weights using symmetric density functions and sparsification, reducing the parameter count by 30% while retaining core feature extraction capabilities. YOLO11-FADA achieves a mAP@0.5 of 0.907 on a custom maglev train foreign object dataset, improving by 3.0% over the baseline YOLO11 model. The model’s computational complexity is 7.3 GFLOPs, with a detection speed of 118.6 FPS, striking a balance between detection accuracy and real-time performance, thereby offering an efficient solution for rail transit safety monitoring.

---

Keywords

---