(英)基于低分辨率红外阵列传感器的头部运动检测
DOI:
作者:
作者单位:

福州大学物理与信息工程学院

作者简介:

通讯作者:

中图分类号:

基金项目:

国家自然科学基金(62071125)福建省自然科学基金(2021J01581、2018J01805)、福州大学科研基金(GXRC-18083)资助项目


Head motion detection based on low resolution infrared array sensor
Author:
Affiliation:

College of Physics and Information Engineering, Fuzhou University

Fund Project:

the National Natural Science Foundation of China under Grant 62071125,the Natural Science Foundation of Fujian Province under Grant 2021J01581and 2018J01805, and the Scientific Research Foundation of Fuzhou University under Grant GXRC-18083

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    在驾驶和在线课堂这类持续时间较长的行为中,人们容易出现分心而导致事故发生或上课效率差。为检测这类分心行为,提出了一种基于低分辨率红外阵列传感器的头部运动检测方法,它在实现行为监测的同时也保护了个人隐私。首先,基于图像处理的方法提取了人体的显著区域,然后设计了一种三维图像融合算法来提取时空域的变化信息。最后,设计了一个改进的残差网络来实现头部运动分类。面向驾驶和在线课堂应用场景设计了10种头部运动。实验结果表明,在50厘米到100厘米的检测范围内,平均识别率为96.76%,处理速度为每秒9帧,优于现有的算法。将该系统应用于车内实测,也达到了93.7%的准确率。

    Abstract:

    People easily get distracted or tired after long-duration actions such as driving and online classes, which can lead to accidents or poor efficiency. To detect such human behaviors, a head motion detection method based on low-resolution infrared array sensors is proposed with the protection of personal privacy. First, prominent areas of the human body are extracted based on image processing techniques. Then a 3D image fusion algorithm is developed to extract the change information in the spatiotemporal domain. Finally, an improved residual network is developed to achieve head motion classification. Ten head movements are designed for driving and online classroom scenarios. Experimental results show that in the detection range of 50cm to 100cm, our average recognition rate is 96.76%, and the processing speed is 9 frames per second, which is better than the existing state-of-the-art algorithms. The accuracy of the system is 93.7% when it is applied to the vehicle experiment.

    参考文献
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2022-07-17
  • 最后修改日期:2022-11-04
  • 录用日期:2022-11-10
  • 在线发布日期:
  • 出版日期: