基于RetinaNet-CPN网络的视频人体关键点检测
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

基金项目:

浙江省自然科学基金(LQ20F050010)


Video Human Body Keypoint Detection Based on RetinaNet-CPN Network
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 增强出版
  • |
  • 文章评论
    摘要:

    为解决基于视频流的人体关键点检测效果不佳及视频流切片后可能会发生运动模糊的问题, 提出了一种改进的RetinaNet-CPN网络对人体关键点进行检测, 有效解决切片后运动模糊图像的干扰并提高了人体关键点的检测准确率. 视频流切片后, 先用改进的RetinaNet网络检测出图片中的所有人并对每个目标框做模糊检测, 对大于阈值的目标框做去模糊处理, 最后用引入注意力机制的CPN网络提取关键点. 将RetinaNet衡量预测框与真实框差异的IOU函数改成DIOU后, 在仿真实验中目标检测AP提高了近3%; 对于模糊的图片, 利用匀速直线运动频谱特征估算出的模糊核与实际模糊核相差不大, 对其做去模糊处理后基本能恢复出原清晰图片; 同时引入注意力机制为各通道和特征层分配合理的权重, 使得CPN检测AP提高近1%, AR提升0.5%.

    Abstract:

    Concerning the problem of poor detection of human body keypoints based on video streams and possible motion blur after video stream slicing, an improved RetinaNet-CPN network is proposed to detect the keypoints, avoiding the interference of motion-blurred images after slicing and improving the detection accuracy of the keypoints. After the video stream is sliced, the improved RetinaNet network is first used to detect all the people in the picture and perform fuzzy detection on each target frame. The target frame larger than the threshold is deblurred, and finally, the keypoints are extracted with the CPN network with the attention mechanism. After the IOU function of RetinaNet to measure the difference between the predicted frame and the real frame is changed into DIOU, the target detection AP increases by nearly 3% in the simulation experiment. For blurry pictures, the blur kernel estimated with the spectrum feature of uniform linear motion is slightly different from the actual blur kernel, and the original clear picture can be restored after the deblurring. At the same time, the attention mechanism is adopted to assign reasonable weights to each channel and feature layer, which increases the CPN detection AP by nearly 1% and the AR by 0.5%.

    参考文献
    相似文献
    引证文献
引用本文

包晓安,吉鹏飞.基于RetinaNet-CPN网络的视频人体关键点检测.计算机系统应用,2021,30(11):138-144

复制
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:2021-01-13
  • 最后修改日期:2021-02-07
  • 录用日期:
  • 在线发布日期: 2021-10-22
  • 出版日期:
您是第位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京海淀区中关村南四街4号 中科院软件园区 7号楼305房间,邮政编码:100190
电话:010-62661041 传真: Email:csa (a) iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号