基于改进CenterNet的轻量级目标检测算法  

LIGHTWEIGHT OBJECT DETECTION ALGORITHM BASED ON IMPROVED CENTERNET

作　　者：倪一华 闫胜业[1] Ni Yihua;Yan Shengye(School of Automation,Nanjing University of Information Science and Technology,Nanjing 210044,Jiangsu,China)

机构地区：[1]南京信息工程大学自动化学院,江苏南京210044

出　　处：《计算机应用与软件》2025年第4期135-141,149,共8页Computer Applications and Software

基　　金：国家自然科学基金项目(61300163)。

摘　　要：针对CenterNet检测算法存在网络参数量大且未能充分有效利用多尺度局部区域特征的问题,提出一种MIR-SPPA-CenterNet目标检测方法来改进CenterNet检测网络。具体来说,在CenterNet的骨干网络中引入混合反残差(MIR)模块以达到轻量化的效果,此外,还引入一种改进的带有注意力机制的空间金字塔(SPPA)结构,对多尺度局部区域特征进行池化、级联和筛选,使网络能够自适应地学习到更加全面有效的目标特征。实验证明,该方法在通用PASCAL VOC数据集上和自建L-KITTI数据集上均表现出更好的检测效果。Aimed at the problem that the CenterNet detection algorithm has a large number of network parameters and fails to fully and effectively utilize the multi-scale local region features,an MIR-SPPA-CenterNet detection method is proposed to improve the CenterNet detection network.Specifically,mixed invert residual(MIR)block was introduced into the backbone network of CenterNet to achieve a lightweight effect.In addition,an improved spatial pyramid pooling with attention(SPPA)block was introduced to pool,cascade,and filter multi-scale local area features so that the network could adaptively learn more comprehensive and effective target features.Experiments show that this method has better detection results on the general PASCAL VOC dataset and the self-built L-KITTI dataset.

关 键 词：目标检测 轻量化 CenterNet 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]