基于卷积神经网络的地铁客流识别系统应用  

Application of Subway Passenger Flow Identification System Based on Convolution Neural Network

作　　者：庞婷婷[1] 王玮[1] PANG Tingting;WANG Wei(School of Traffic and Transportation,Xi’an Traffic Engineering Institute,Xi’an 710000,China)

机构地区：[1]西安交通工程学院交通运输学院,陕西西安710000

出　　处：《微型电脑应用》2022年第8期151-153,共3页Microcomputer Applications

摘　　要：地铁车厢客流的识别易受到环境干扰,为了提高车厢客流识别的准确率,提出了一种基于卷积神经网络的客流识别算法。该算法以车厢监控图像为研究对象,采用GoogleNet卷积神经网络模型,选用Relu函数作为激活函数,通过对Inception模块的结构优化,有效提升网络运行速度和准确率。实验表明,该算法具有较高的训练收敛速度和检测准确率。In order to improve the accuracy of passenger flow identification,a passenger flow identification algorithm based on convolution neural network is proposed.The algorithm takes the car monitoring image as the research object,adopts the GoogleNet convolution neural network model,selects the Relu function as the activation function.The system effectively improves the network speed and accuracy by optimizing the structure of the perception module.The experimental results show that the algorithm has high training convergence speed and detection accuracy.

关 键 词：图像处理 卷积神经网络 样本训练 客流识别 

分 类 号：TP36[自动化与计算机技术—计算机系统结构]