基于深度学习的交通拥堵检测

Traffic congestion detection based on deep learning

针对交通拥堵检测,提出一种利用深度学习中卷积神经网络(convolutional neural network, CNN)对交通拥堵图像进行检测的方法。首先,使用基于TensorFlow框架设计了含有三层卷积层的神经网络分类模型。其次,利用道路拥堵与非拥堵图片对分类模型进行训练,并进行评估。最后,利用训练完成的模型进行道路拥堵检测,与多种深度学习分类模型分类方法进行对比实验,表明该卷积神经网络模型能够更有效地进行拥堵检测,检测准确率达到了98.1%。

Aimed at traffic congestion detection,a method of detecting traffic congestion images using convolutional neural network(CNN)was proposed.First,a neural network classification model with three layers of convolutional layers was designed based on the TensorFlow framework.Then,the classification model was trained and evaluated using road congestion and non-congestion pictures.Finally,the well-trained model was used to carry out road congestion detection.Compared with many other deep learning classification models,the proposed convolutional neural network model showed high efficiency in congestion detection,and the detection accuracy reached 98.1%.