欢迎访问《图学学报》 分享到：
图学学报

图学学报

• 图像与视频处理 • 上一篇    下一篇

基于卷积神经网络的实时人群密度估计

  

  1. 西安科技大学通信与信息工程学院，陕西西安 710054
  • 出版日期:2018-08-31 发布日期:2018-08-21
  • 基金资助:
    陕西省重点研发计划项目(2017GY-095)

Real-Time Crowd Density Estimation Based on Convolutional Neural Networks

  1. College of Communication and Information Engineering, Xi’an University of Seience and Technology, Xi’an Shaanxi 710054, China
  • Online:2018-08-31 Published:2018-08-21

PDF (PC)

251

摘要： 针对传统实时人群密度估计方法存在误差大、分类效果不佳等缺陷，提出了基于
卷积神经网络的实时人群密度估计方法。通过对比4 种常见网络结构：AlexNet、VGGNet、
GoogLeNet 和ResNet 的准确度与实时性，选择综合性较好的GoogLeNet 作为人群密度估计的
模型，利用关键帧截取技术实现人群密度的实时估计并简要分析人群密度特征图。最后用实例
验证了该方法的实时性与准确度，证明了其可行性。

关键词: 人群密度, 卷积神经网络, 视频处理, 实时估计

Abstract: In response to the deficiencies such as big error and poor performance in the traditional
method of real-time crowd density estimation, a new one based on CNN is proposed. By comparing
the accuracy and real-time of four common network structures—AlexNet, VGGNet, GoogLeNet, and
ResNet, the GoogLeNet which has relatively better comprehensive performance is chosen as the
model for crowd density estimation. We used the key-frame extraction technology to realize real-time
crowd density estimation and briefly analyze the crowd density feature map. Finally, examples are
analyzed to verify the real time, accuracy, and feasibility of this new method of real-time crowd
density estimation.

Key words: crowd density, convolutional neural networks, video processing, real-time estimation