计算机工程与应用2024，Vol.60Issue(13)：200-208,9.DOI:10.3778/j.issn.1002-8331.2312-0153
RepViTS-YOLOX:水下模糊及遮挡目标检测方法
RepViTS-YOLOX:Underwater Blurred and Occluded Target Detection Method
摘要
Abstract
The RepViTS-YOLOX method is proposed to address target blurring and occlusion in underwater target detec-tion,improving upon the YOLOX framework.This approach employs RepViTS for feature extraction and incorporates structural reparameterization to enhance underwater target feature extraction and model inference speed.It features a spa-tial and channel reconstruction convolution(SCConv)module to better focus on blurred targets.The feature fusion net-work uses cross-scale and multi-scale fusion to better interpret occluded target characteristics.Additionally,a task-specific context decoupling head(TSCODE)is introduced for more accurate localization and classification of occluded targets.Experiments on the RUOD dataset show that RepViTS-YOLOX achieves 85.7% detection accuracy,surpassing YOLOX by 3.8 percentage points.These findings indicate that the method effectively improves the detection of blurred and occluded underwater targets,thus enhancing the precision of underwater target detection.关键词
YOLOX/目标检测/结构重参数化/解耦检测头/注意力机制Key words
YOLOX/target detection/structural re-parameterization/decouple detection head/attention mechanism分类
信息技术与安全科学引用本文复制引用
陶洋,朱腾,钟邦乾,周昆,周立群..RepViTS-YOLOX:水下模糊及遮挡目标检测方法[J].计算机工程与应用,2024,60(13):200-208,9.基金项目
国家重点研发计划(2019YFB2102001). （2019YFB2102001）
