Open Access

ARTICLE

CLF-YOLOv8: Lightweight Multi-Scale Fusion with Focal Geometric Loss for Real-Time Night Maritime Detection

Zhonghao Wang^1,2, Xin Liu^1,2,*, Changhua Yue³, Haiwen Yuan⁴

1 Department of Ship and Port Engineering, Shandong Jiaotong University, Weihai, 264209, China
2 Department of Intelligent Shipping, Weihai Institute of Marine Information Science and Technology, Weihai, 264200, China
3 Department of Naval Architecture and Ocean Engineering, Weihai Ocean Vocational College, Weihai, 264209, China
4 Department of Shipping, Wuhan University of Technology, Wuhan, 430063, China

* Corresponding Author: Xin Liu. Email:

Computers, Materials & Continua 2026, 86(2), 1-23. https://doi.org/10.32604/cmc.2025.071813

Received 12 August 2025; Accepted 06 October 2025; Issue published 09 December 2025

Abstract

To address critical challenges in nighttime ship detection—high small-target missed detection (over 20%), insufficient lightweighting, and limited generalization due to scarce, low-quality datasets—this study proposes a systematic solution. First, a high-quality Night-Ships dataset is constructed via CycleGAN-based day-night transfer, combined with a dual-threshold cleaning strategy (Laplacian variance sharpness filtering and brightness-color deviation screening). Second, a Cross-stage Lightweight Fusion-You Only Look Once version 8 (CLF-YOLOv8) is proposed with key improvements: the Neck network is reconstructed by replacing Cross Stage Partial (CSP) structure with the Cross Stage Partial Multi-Scale Convolutional Block (CSP-MSCB) and integrating Bidirectional Feature Pyramid Network (BiFPN) for weighted multi-scale fusion to enhance small-target detection; a Lightweight Shared Convolutional and Separated Batch Normalization Detection-Head (LSCSBD-Head) with shared convolutions and layer-wise Batch Normalization (BN) reduces parameters to 1.8 M (42% fewer than YOLOv8n); and the Focal Minimum Point Distance Intersection over Union (Focal-MPDIoU) loss combines Minimum Point Distance Intersection over Union (MPDIoU) geometric constraints and Focal weighting to optimize low-overlap targets. Experiments show CLF-YOLOv8 achieves 97.6% mAP@0.5 (0.7% higher than YOLOv8n) with 1.8 M parameters, outperforming mainstream models in small-target detection, overlapping target discrimination, and adaptability to complex lighting.

---

Keywords

---