文献类型：期刊文献

中文题名：基于迁移学习的车辆目标识别

英文题名：Vehicle Target Recognition Based on Transfer Learning

作者：李慧[1];王艳娥[1]

第一作者：李慧

机构：[1]北京联合大学管理学院,北京100101

第一机构：北京联合大学管理学院

年份：2024

卷号：33

期号：11

起止页码：257-263

中文期刊名：计算机系统应用

外文期刊名：Computer Systems & Applications

收录：CSTPCD

基金：国家自然科学基金(62307001)。

语种：中文

中文关键词：车辆识别;迁移学习;残差优化;二次迁移

外文关键词：vehicle recognition;transfer learning;residual optimization;secondary transfer

摘要：为提高车辆识别的准确率及识别的实时性能,本文提出了一种基于迁移学习的车辆识别方法.该方法通过卷积神经网络和支持向量机结合并做进一步优化,提高车辆识别的准确率,并减少模型训练时间和提高模型的鲁棒性.该方法首先使用卷积神经网络在CIFAR-10数据集上训练好网络;然后结合残差优化的思想,使用更深的预训练网络结构提取细粒度特征;在模型网络的参数迁移过程中,只迁移预训练的卷积层参数,并添加全连接层在车辆数据集上进行微调;最后将提取的特征直接放入支持向量机中进行分类.通过详细的模型实验与结果分析,本方法能够最终达到的最高识别正确率为97.56%,单张图片识别时间260 ms,识别时间和正确率均得到了较好的优化.
To improve the accuracy and real-time performance of vehicle recognition,this study proposes a vehicle recognition method based on transfer learning.This optimized method improves the accuracy of vehicle recognition,reduces model training time,and improves the robustness of the model by integrating convolutional neural networks and support vector machines.This method first uses a convolutional neural network to train its network on the CIFAR-10 data set.Residual optimization is then applied to a deeper pre-trained network to extract fine-grained features.During the parameter transfer process of the model network,only the pre-trained parameters of the convolutional layer are transferred,and a fully connected layer is added for fine-tuning on the vehicle data set.Finally,the extracted features are directly put into the support vector machine for classification.Detailed model experiments and result analysis demonstrate that this method achieves the highest recognition accuracy of 97.56%and a recognition time of 260 ms per single image,indicating optimized performance in both recognition time and accuracy.