计算机与现代化

• 人工智能 • 上一篇    下一篇

基于YOLOv3与ResNet50的摄影机器人人脸识别跟踪系统

  

  1. (南京理工大学机械工程学院,江苏南京210094)
  • 收稿日期:2019-08-15 出版日期:2020-04-22 发布日期:2020-04-24
  • 作者简介:陈凯(1995-),男,江苏张家港人,硕士研究生,研究方向:机器人,机器视觉,E-mail: 479333165@qq.com; 祖莉(1977-),女,副教授,博士,研究方向:智能机械系统,高等机构学,机械设计及理论; 欧屹(1982-),男,副研究员,博士,研究方向:机器人技术,高端装备及功能部件。

Face Recognition and Tracking System of Photographic Robot #br# Based on YOLOv3 and ResNet50

  1. (School of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing 210094, China)
  • Received:2019-08-15 Online:2020-04-22 Published:2020-04-24

摘要: 虚拟演播室下,针对需要摄影机器人来自动完成对主持人的识别并对其进行镜头跟踪的任务,提出一种在基于YOLOv3完成人脸检测的基础上,构建ResNet50网络,对主持人进行人脸识别及镜头跟踪的系统。为提高其在开放集上人脸识别的精度,基于CASIA-FaceV5与PubFig数据集构建人脸训练集,在改进的ResNet50模型上完成模型的联合监督训练。结合摄影机器人运动控制算法进行实验,实验表明该系统具有较好的识别精度与实时性,能够满足虚拟演播室下摄影机器人人脸跟踪要求。

关键词: 虚拟演播室, 摄影机器人, 人脸识别, YOLOv3, ResNet50

Abstract: In the virtual studio,aiming at the task that the photographic robot needs completing automatical face recognition and shot tracking of the host, a system of face recognition and shot tracking for the host based on YOLOv3 face detection and ResNet50 construction is proposed. In order to improve the accuracy of face recognition for photographic robots on open sets, a host face training set based on CASIA-FaceV5 and PubFig data sets is constructed, and the model is trained on modified ResNet50 with joint supervision. An experiment is carried out by combining with the motion control algorithm of photographic robot, the experiment shows that the face recognition tracking system has robust recognition accuracy and real-time performance, and can meet the requirements of face tracking of photographic robot in the virtual studio.

Key words: virtual studio, photographic robot, face recognition, YOLOv3, ResNet50

中图分类号: