摘要
针对复杂的环境,结合图像预处理与深度学习神经网络,提出了一种道路交通标识识别算法。该方法不仅利用图像分割技术,而且利用卷积神经网络模型对道路交通标识进行了更准确的识别。首先,通过调节光照影响、去除复杂背景、数据增强和归一化等批量预处理操作,形成一个完整的数据集;然后,结合squeeze-andexcitation思想和残差网络结构,充分训练出自己的卷积神经网络模型;最后,将优化的网络模型用于道路交通标识的识别。实验结果表明,该方法使训练时间缩短了12%左右,识别精度可达99.26%。
This study proposes a road traffic identification algorithm based on image preprocessing and deep-learning neural networks for complex environments.The proposed method uses not only the image segmentation technology but also the convolutional neural network model to more accurately identify the road traffic signs.First,a complete dataset is obtained via batch preprocessing operations,including illumination effect adjustment,complex background elimination,data enhancement,and normalization.Next,the convolutional neural network model is sufficiently trained based on the combination of the squeeze-and-excitation network and residual network structure concepts.Finally,the optimized network model is used to identify the road traffic signs.The experimental result shows that the proposed method reduces the training time by approximately 12%and that the recognition accuracy can reach 99.26%.
作者
何锐波
狄岚
梁久祯
HE Ruibo;DI Lan;LIANG Jiuzhen(School of Artificial Intelligence and Computer Science,Jiangnan University,Wuxi 214122,China;The 28th Research Institute of China Electronics Technology Group Corporation,Nanjing 210007,China;School of Information Science and Engineering,Changzhou University,Changzhou 213164,China)
出处
《智能系统学报》
CSCD
北大核心
2020年第6期1121-1130,共10页
CAAI Transactions on Intelligent Systems
基金
江苏省研究生科研与实践创新计划项目(KYCX18_1872).
关键词
道路交通标识识别
图像分割
卷积神经网络
去除复杂背景
数据增强
归一化
压缩和激励网络
残差连接
road traffic identification
image segmentation
convolutional neural network
complex background elimination
data enhancement
normalization
squeeze-and-excitation network
residual connection
