• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of Imaging Science and Technology >Pedestrian Detection at Night Using Deep Neural Networks and Saliency Maps
【24h】

Pedestrian Detection at Night Using Deep Neural Networks and Saliency Maps

机译：使用深层神经网络和显着图在夜间进行行人检测

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

This study focuses on real-time pedestrian detection using thermal images taken at night because a number of pedestrian-vehicle crashes occur from late at night to early dawn. However, the thermal energy between a pedestrian and the road differs depending on the season. We therefore propose the use of adaptive Boolean-map-based saliency (ABMS) to boost the pedestrian from the background based on the particular season. For pedestrian recognition, we use the convolutional neural network based pedestrian detection algorithm, you only look once (YOLO), which differs from conventional classifier-based methods. Unlike the original version, we combine YOLO with a saliency feature map constructed using ABMS as a hardwired kernel based on prior knowledge that a pedestrian has higher saliency than the background. The proposed algorithm was successfully applied to the thermal image dataset captured by moving vehicles, and its performance was shown to be better than that of other related state-of-the-art methods. (C) 2017 Society for Imaging Science and Technology.
机译：这项研究着重于使用夜间拍摄的热图像进行实时行人检测，因为从深夜到黎明，发生了许多行人车祸。但是，行人与道路之间的热能因季节而异。因此，我们建议使用基于自适应布尔图的显着性（ABMS）根据特定季节从背景中提升行人。对于行人识别，我们使用基于卷积神经网络的行人检测算法，您只看一次（YOLO），这与传统的基于分类器的方法不同。与原始版本不同，我们将YOLO与使用ABMS作为硬连线内核构建的显着性特征图结合起来，这是基于先验知识，即行人的显着性高于背景。该算法已成功应用于移动车辆捕获的热图像数据集，其性能优于其他相关技术。 （C）2017年影像科学与技术学会。

著录项

  • 来源
    《Journal of Imaging Science and Technology》 |2017年第6期|060403.1-060403.9|共9页
  • 作者

    Heo Duyoung; Lee Eunju; Ko Byoung Chul;

  • 作者单位

    Keimyung Univ, Dept Comp Engn, Daegu 704701, South Korea;

    Keimyung Univ, Dept Comp Engn, Daegu 704701, South Korea;

    Keimyung Univ, Dept Comp Engn, Daegu 704701, South Korea;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号