咨询与建议

限定检索结果

文献类型

  • 1 篇 期刊文献

馆藏范围

  • 1 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 1 篇 工学
    • 1 篇 电气工程

主题

  • 1 篇 mobile systems
  • 1 篇 histogram of ori...
  • 1 篇 people detection
  • 1 篇 low-power circui...
  • 1 篇 algorithm and ar...
  • 1 篇 fast algorithms ...
  • 1 篇 hardware/softwar...
  • 1 篇 object class det...
  • 1 篇 always on

机构

  • 1 篇 stanford univ de...
  • 1 篇 stanford univ de...

作者

  • 1 篇 murmann boris
  • 1 篇 young christophe...
  • 1 篇 ta david
  • 1 篇 omid-zohoor alex

语言

  • 1 篇 英文
检索条件"主题词=object class detection and recognition"
1 条 记 录,以下是1-10 订阅
排序:
Toward Always-On Mobile object detection: Energy Versus Performance Tradeoffs for Embedded HOG Feature Extraction
收藏 引用
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2018年 第5期28卷 1102-1115页
作者: Omid-Zohoor, Alex Young, Christopher Ta, David Murmann, Boris Stanford Univ Dept Elect Engn Stanford CA 94305 USA Stanford Univ Dept Comp Sci Stanford CA 94305 USA
This paper studies the effects of front-end imager parameters on object detection performance and energy consumption. A custom version of histograms of oriented gradient (HOG) features based on 2-b pixel ratios is pre... 详细信息
来源: 评论