本文已被:浏览 743次 下载 2644次
Received:March 30, 2023 Revised:May 11, 2023
Received:March 30, 2023 Revised:May 11, 2023
中文摘要: 针对移动端目标检测算法需要模型参数量与计算量更少、推理速度更快和检测效果更好以及目标检测算法对于小目标误检、漏检及特征提取能力不足等问题, 提出一种基于YOLOv5改进的轻量化目标检测算法. 该算法使用轻量级网络MobileNetV2作为目标检测算法的骨干网络降低模型的参数量与计算量, 通过使用深度可分离卷积结合大卷积核的思想降低网络的计算量与参数量, 并提升了小目标的检测精度. 使用GhostConv来替换部分普通卷积, 进一步降低参数量与计算量. 本文算法在VOC竞赛数据集, COCO竞赛数据集两份数据集上均进行了多次对比实验, 结果表明本文算法相比于其他模型参数量更小、计算量更小、推理速度更快以及检测精度更高.
中文关键词: 轻量化 深度学习 特征金字塔网络(FPN) YOLOv5 大核卷积
Abstract:Mobile target detection algorithms require fewer model parameters, less computation, faster reasoning speed, and better detection effects. The target detection algorithms are prone to false detection of small targets and missing detection and have insufficient ability for feature extraction. To this end, this study proposes a lightweight small target detection algorithm based on YOLOv5. In this algorithm, the lightweight network MobileNetV2 is used as the backbone network of the target detection algorithm to reduce the number of parameters and calculation amount of the model. The deep separable convolution combined with a large convolution kernel is applied to decline the number of parameters and calculation amount, and improve the detection accuracy of small targets. GhostConv is adopted to replace part of common convolution to further decrease the number of parameters and computation amount. Multiple comparison experiments are carried out on VOC competition data sets and COCO competition data sets. The results show that compared with other models, the proposed algorithm has fewer parameters, less computation, faster reasoning speed, and higher detection accuracy.
文章编号: 中图分类号: 文献标志码:
基金项目:广东省基础与应用基础研究基金(2023A1515010168, 2019A1515010830); 广东省普通高校重点专项(2022ZDZX1018); 茂名市科技计划(2022S043); 广东石油化工学院博士启动项目(2019BS001)
引用文本:
管嘉程,任红卫,周宋佳.基于YOLOv5改进的轻量化目标检测.计算机系统应用,2023,32(9):132-142
GUAN Jia-Cheng,REN Hong-Wei,ZHOU Song-Jia.Improved Lightweight Target Detection Based on YOLOv5.COMPUTER SYSTEMS APPLICATIONS,2023,32(9):132-142
管嘉程,任红卫,周宋佳.基于YOLOv5改进的轻量化目标检测.计算机系统应用,2023,32(9):132-142
GUAN Jia-Cheng,REN Hong-Wei,ZHOU Song-Jia.Improved Lightweight Target Detection Based on YOLOv5.COMPUTER SYSTEMS APPLICATIONS,2023,32(9):132-142