摘要
针对中低分辨率车型识别问题,建立一种改进的卷积神经网络(CNN)特征融合模型。采取特征融合策略对CNN中的不同低层特征进行融合重复利用。为防止出现过拟合现象,结合网络模型稀疏化的结构,使用数据增强方法优化训练数据。分析和实验结果表明,该模型不仅能产生更具区分性的特征,而且能避免由环境等因素引起的干扰,与传统CNN模型相比,具有更高的识别准确率。
An improved Convolution Neural Network(CNN)feature fusion model is proposed to solve the problem of mid-low resolution vehicle type recognition.The feature fusion strategy is adopted to fuse and reuse different low-level features in CNN.Among them,in order to prevent over-fitting,combined with the sparse structure of the network model,the data enhancement method is used to optimize the training data.Analysis and experimental results show that the model can not only produce more distinguishing features,but also avoid the interference caused by environmental factors to a certain extent.Compared with the traditional CNN model,it has higher recognition accuracy.
作者
薛丽霞
钟欣
汪荣贵
杨娟
胡敏
XUE Lixia;ZHONG Xin;WANG Ronggui;YANG Juan;HU Min(School of Computer and Information,Hefei University of Technology,Hefei 230009,China)
出处
《计算机工程》
CAS
CSCD
北大核心
2019年第1期233-238,245,共7页
Computer Engineering
基金
国家自然科学基金(61672202)
关键词
卷积神经网络
特征融合
稀疏化
中低分辨率
车型识别
Convolution Neural Network(CNN)
feature fusion
sparseness
mid-low resolution
vehicle type recognition
