基于卷积神经网络的人行道识别算法研究  

Research on Sidewalk Identification Algorithm based on Convolutional Neural Network

作　　者：胡彩霞 熊平[1] 周欣星 Hu Caixia;Xiong Ping;Zhou Xinxing(Department of Biomedical Engineering,Central South University,Changsha Hunan 410083,China;The First Hospital of Hunan University of Chinese Medicine,Changsha Hunan 410000,China)

机构地区：[1]中南大学生物医学工程系,湖南长沙410083 [2]湖南中医药大学第一附属医院,湖南长沙410000

出　　处：《信息与电脑》2017年第21期53-55,共3页Information & Computer

摘　　要：笔者利用卷积神经网络识别出图像中人行道与机动车道,该算法可应用于导盲系统与无人驾驶领域。具体算法分为如下几步:首先通过滑窗算法得到训练和测试的样本,然后使用卷积神经网络识别滑窗,最后合并属于人行道区域的滑窗,得到整个人行道区域。结果表明,该算法能够适用于多类不同样式的人行道检测,本算法测试了1 000幅不同人行道类别的图像,识别率达到97.6%,该本算法具有较好的鲁棒性。This paper uses the convolution neural network algorithm to identify sidewalk and motorways.The algorithm can be applied to the guidance system and the unmanned field.The algorithm is divided into the following steps:firstly,using the sliding window algorithm to get training samples,and then using the convolution neural network to identify the sliding window,and finally merging the sidewalk area.The results show that the algorithm can be applied to various types of sidewalk detection.The algorithm tests 1000 images involving different types of sidewalk,the r ecognition rate is 97.6%,and the algorithm has good robustness.

关 键 词：卷积神经网络 人行道区域 识别 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]