文献知网节
  • 记笔记

Pedestrian Detection Algorithm Based on the Improved SSD

Shu-an LiuShi LvHailin ZhangJun Gong

College of Information Science and Engineering,Northeastern University

摘要:In recent years, pedestrian detection is a hot research topic in the field of computer vision and artificial intelligence, It is widely used in the fields of automatic driving safety and security and pedestrian analysis. But pedestrians as transfigure change target, and because the pedestrian dress differ in thousands ways, lead to the traditional pedestrian detection technology detection accuracy is not high, it restricts the development of pedestrian detection technology. With the development of deep learning, the pedestrian detection method based on deep learning greatly improves the accuracy of pedestrian detection. For the problem of low detection accuracy of small targets in SSD, this paper proposes an improved SSD pedestrian detection method based on the context information, by extracting the shallow features in the SSD convolutional neural network, fuses the shallow semantic information in the convolutional layer with the deep semantic information, and then detects the size of the pedestrian in the image. Features Redesigned pre-selection boxes with different aspect ratios, improve the SSD model test result is superior to the standard model of the SSD.
会议名称:

第31届中国控制与决策会议

会议时间:

2019-06-03

会议地点:

中国江西南昌

  • 专辑:

    信息科技

  • 专题:

    计算机软件及计算机应用; 自动化技术

  • 分类号:

    TP391.41;TP18

  • 手机阅读
    即刻使用手机阅读
    第一步

    扫描二维码下载

    "移动知网-全球学术快报"客户端

    第二步

    打开“全球学术快报”

    点击首页左上角的扫描图标

    第三步

    扫描二维码

    手机同步阅读本篇文献

  • CAJ下载
  • PDF下载

下载手机APP用APP扫此码同步阅读该篇文章

下载:6 页码:892-896 页数:5 大小:747k

引文网络
  • 参考文献
  • 引证文献
  • 共引文献
  • 同被引文献
  • 二级参考文献
  • 二级引证文献
  • 批量下载
相关推荐
  • 相似文献
  • 读者推荐
  • 相关基金文献
  • 相关法规
  • 关联作者
  • 相关视频