基于改进RT-DETR的水下目标检测  

Underwater Target Detection Based on Improved RT-DETR

作　　者：张路 魏本昌 魏鸿奥 周龙刚 ZHANG Lu;WEI Ben-Chang;WEI Hong-Ao;ZHOU Long-Gang(College of Electrical&Information Engineering,Hubei University of Automotive Technology,Shiyan 442002,China)

机构地区：[1]湖北汽车工业学院电气与信息工程学院,十堰442002

出　　处：《计算机系统应用》2024年第12期131-140,共10页Computer Systems & Applications

基　　金：湖北省教育厅项目(B2019077)。

摘　　要：水下目标检测技术在海洋探测中具有重要的现实意义.针对水下场景复杂,以及存在遮挡重叠导致目标特征提取有限的问题,提出了一种适用于水下目标检测的FERT-DETR网络.该模型首先提出了一种特征提取模块Faster-EMA,用于替换RT-DETR中ResNet18的BasicBlock,能够在有效降低模型参数量和模型深度的同时,显著提升对水下目标的特征提取能力;其次在编码部分使用级联群体注意力模块AIFI-CGA,减少多头注意力中的计算冗余,提高注意力的多样性;最后使用高水平筛选特征金字塔HS-FPN替换CCFM,实现多层次融合,提高检测的准确性和鲁棒性.实验结果表明,所提算法FERT-DETR在URPC2020数据集和DUO数据集上比RT-DETR检测准确率提高了3.1%和1.7%,参数量压缩了14.7%,计算量减少了9.2%,能够有效改善水下复杂环境中不同尺寸目标漏检、误检的问题.Underwater target detection has practical significance in ocean exploration.This study proposes a FERT-DETR network suitable for underwater target detection to address the issues of complex underwater environments and limited target feature extraction due to occlusion and overlap.The proposed model first introduces a feature extraction module,Faster EMA,to replace the BasicBlock of ResNet18 in RT-DETR,which can significantly improve its capability to extract features of underwater targets while effectively reducing the number of parameters and depth of the model.Secondly,a cascaded group attention module,AIFI-CGA,is used in the encoding part to reduce computational redundancy in multi-head attention and improve attention diversity.Finally,a feature pyramid for high-level filtering named HS-FPN is used to replace CCFM,achieving multi-level fusion and improving the accuracy and robustness of detection.The experimental results show that the proposed algorithm,FERT-DETR,improves detection accuracy by 3.1%and 1.7%compared to RT-DETR on the URPC2020 and DUO datasets respectively,compresses the number of parameters by 14.7%,and reduces computational complexity by 9.2%.It can effectively avoid missed and false detection of targets of different sizes in complex underwater environments.

关 键 词：计算机视觉 RT-DETR FasterNet 注意力机制 高水平筛选特征金字塔 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]