期刊文献+

基于卷积神经网络的高速公路拥堵识别技术研究 被引量:1

Research on Highway Congestion Recognition Technology Based on Convolutional Neural Network
下载PDF
导出
摘要 目前,交通拥堵问题日趋严重,对交通安全构成极大威胁,为提高监控视频识别准确率,文章基于卷积神经网络中GoogLeNet模型,提出了一种高速拥堵识别技术,利用卷积神经网络(Convolutional Neural Networks,CNN)在图像识别领域较强的学习能力,解决了监控视频识别准确率低的问题,促进了交通安全发展。 At present, traffic congestion is becoming more and more serious and poses a great threat to traffic safety. To improve the accuracy of surveillance video recognition, the article proposes a high-speed congestion recognition technology based on the GoogLeNet model in convolutional neural networks, which uses the strong learning ability of Convolutional Neural Networks(CNN) in the field of image recognition to solve the problem of low accuracy of surveillance video recognition and promote the development of traffic safety.
作者 刘宇峰 LIU Yufeng(Shanxi Transportation Holdings Group Co.,Ltd.,Taiyuan Shanxi 030000,China)
出处 《信息与电脑》 2022年第14期82-85,共4页 Information & Computer
关键词 交通拥堵 卷积神经网络(CNN) GoogLeNet traffic jams Convolutional Neural Networks(CNN) GoogLeNet
  • 引文网络
  • 相关文献

参考文献1

二级参考文献1

共引文献5

同被引文献4

引证文献1

二级引证文献2

;
使用帮助 返回顶部