Mengyang Li

Mengyang Li

Auto-generated profile, based on publicly available information

Mengyang Li

School of Geographic Sciences, Xinyang Normal University, Xinyang, China

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
7 November 2025 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
JNJiqiang Niu
Jiqiang Niu
MLMengyang Li
Mengyang Li
HLHao Lin
Hao Lin
YLYichen Liu
Yichen Liu
ZLZijian Liu
Zijian Liu
SNShaomian Niu
Shaomian Niu
Deep learning has emerged as the predominant approach for ship detection in synthetic aperture radar (SAR) imagery. Nevertheless, persistent challenges such as densely clustered vessels, intricate background complexity, and multiscale target variations often lead to incomplete feature extraction, resulting in false alarms and missed detections. To address these limitations, this study presents LD-YOLO, an enhanced model based on YOLOv8n, which incorporates three critical innovations. Dynamic convolution layers are strategically embedded within key backbone stages to adaptively adjust kernel parameters, enhancing multiscale feature discriminability while maintaining computational efficiency. The proposed C2f-LSK module combines decomposed large-kernel convolution with attention mechanisms, enabling dynamic optimization of receptive field contributions across different detection stages and effective modeling of global contextual information. Considering the characteristics of small vessels in SAR imagery and the impact of downsampling rates on image quality, a dedicated $160\times 160$ detection head is further integrated to preserve fine-grained details of small targets, complemented by bidirectional feature fusion to strengthen semantic context propagation. Extensive experiments validate the model’s superiority, achieving 98.2% of AP50 and 73.1% of AP50-95 on the SSDD benchmark, with consistent performance improvements demonstrated on HRSID (94.6% AP50) datasets. These advancements position LD-YOLO as a robust solution for maritime surveillance applications requiring high-precision SAR image analysis under complex operational conditions.

9 March 2026 in IEEE Access
Verified
Journal Article
Open access
JNJiqiang Niu
Jiqiang Niu
MLMengyang Li
Mengyang Li
HLHao Lin
Hao Lin
HLHongrui Li
Hongrui Li
ZLZijian Liu
Zijian Liu
ZWZiming Wang
Ziming Wang
Infrared remote sensing plays a vital role in all-weather maritime surveillance. However, the automatic detection of ships in infrared imagery is often hindered by low contrast, the prevalence of small-sized targets, and complex background clutter from sea waves. To overcome these practical challenges, this study proposes a novel detection framework named DGG-YOLO, based on an improved YOLOv8n architecture. The proposed model incorporates several key enhancements to boost detection performance in maritime scenarios, including a revised downsampling strategy with an additional 4× detection head to preserve fine-grained details of small ships. Furthermore, a newly designed C2f-GEM module integrated into the backbone network utilizes graph reasoning to model spatial relationships and effectively suppress noise and sea clutter. Additionally, an improved GFPN neck employs Pinwheel-shaped Convolution (PConv) and a Spatial-Channel Collaborative Attention (SCSA) mechanism for superior multi-scale feature fusion. Extensive experiments on the public ISDD dataset demonstrate that our model achieves a state-of-the-art performance of 94% mAP50, outperforming YOLOv8n and YOLO11n by 2.3% and 1.9%, respectively. Its superior generalization capability was further validated on the IRSDSS dataset. The results confirm that DGG-YOLO provides a robust and efficient solution for infrared-based ship detection, offering significant potential for enhancing applications in maritime security, traffic monitoring, and search-and-rescue operations.