Siwen Chen

Mr. Siwen Chen


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 October 2025 in Sensors
Verified
Journal Article
Open access
PDF file
JZJingtao Zhang
Jingtao Zhang
SCSiwen Chen
Siwen Chen
WWWei Wang
Wei Wang
QWQi Wang
Qi Wang
Drones offer a promising solution for automating distribution tower inspection, but real-time defect detection remains challenging due to limited computational resources and the small size of critical defects. This paper proposes TDD-YOLO, an optimized model based on YOLOv11n, which enhances small defect detection through four key improvements: (1) SPD-Conv preserves fine-grained details, (2) CBAM amplifies defect salience, (3) BiFPN enables efficient multi-scale fusion, and (4) a dedicated high-resolution detection head improves localization precision. Evaluated on a custom dataset, TDD-YOLO achieves an mAP@0.5 of 0.873, outperforming the baseline by 3.9%. When deployed on a Jetson Orin Nano at 640 × 640 resolution, the system achieves an average frame rate of 28 FPS, demonstrating its practical viability for real-time autonomous inspection.

27 September 2025 in Drones
Verified
Journal Article
Open access
PDF file
SCSiwen Chen
Siwen Chen
WWWei Wang
Wei Wang
Mingpeng YangMingpeng Yang
Mingpeng Yang
JZJingtao Zhang
Jingtao Zhang
The intelligent development of unmanned aerial vehicles (UAVs) will make power inspection work more convenient. However, challenges such as reliance on precise tower coordinates and the low accuracy in recognizing small targets limit its further development. In this regard, this study proposes an autonomous inspection method based on target detection, encompassing both flight route planning and defect detection. For route planning, the YOLOv8 model is lightly modified by incorporating the VanillaBlock module, the GSConv module, and structured pruning techniques to enable real-time tower detection. Based on the detection results and UAV states, an adaptive route planning strategy is then developed, effectively mitigating the dependence on predefined tower coordinates. For defect detection, the YOLOv8 model is further enhanced by introducing the SPD-Conv module, the CBAM, and the BiFPN multi-scale feature fusion network to improve detection performance for small targets. Compared with multiple baseline models, the computational cost of the improved lightweight model is reduced by 23.5%, while the detection accuracy is increased by 4.5%. Flight experiments further validate the effectiveness of the proposed route planning approach. The proposed fully autonomous inspection method provides valuable insights into enhancing the autonomy and intelligence of UAV-based power inspection systems.