红外与毫米波学报, 2022, 41 (6): 1092, 网络出版: 2023-02-06
GPNet:轻量型红外图像目标检测算法
GPNet:Lightweight infrared image target detection algorithm
摘要
针对资源受限的红外成像系统准确、实时检测目标的需求,提出了一种轻量型的红外图像目标检测算法GPNet。采用GhostNet优化特征提取网络,使用改进的PANet进行特征融合,利用深度可分离卷积替换特定位置的普通3×3卷积,可以更好地提取多尺度特征并减少参数量。公共数据集上的实验表明,本文算法与YOLOv4、YOLOv5-m相比,参数量分别降低了81%和42%;与YOLOX-m相比,平均精度均值提高了2.5%,参数量降低了51%;参数量为12.3 M,检测时间为14 ms,实现了检测准确性和参数量的平衡。
Abstract
A lightweight infrared image target detection algorithm GPNet is proposed to address the need for accurate and real-time target detection in resource-constrained infrared imaging systems. The feature extraction network is optimized using GhostNet, feature fusion is performed using an improved PANet, and a depth-separable convolution is used to replace the ordinary 3×3 convolution at specific locations to better extract multi-scale features and reduce the number of parameters. Experiments on public datasets show that the algorithm in this paper reduces the number of parameters by 81% and 42% compared with YOLOv4 and YOLOv5-m, respectively; the average mean accuracy is improved by 2.5% and the number of parameters is reduced by 51% compared with YOLOX-m; the number of parameters is 12.3 M and the detection time is 14 ms, which achieves a balance between detection accuracy and number of parameters.
李现国, 曹明腾, 李滨, 刘意, 苗长云. GPNet:轻量型红外图像目标检测算法[J]. 红外与毫米波学报, 2022, 41(6): 1092. Xian-Guo LI, Ming-Teng CAO, Bin LI, Yi LIU, Chang-Yun MIAO. GPNet:Lightweight infrared image target detection algorithm[J]. Journal of Infrared and Millimeter Waves, 2022, 41(6): 1092.