Simulation of Face Pose Tracking System using Adaptive Vision Switching
Simulation of Face Pose Tracking System using Adaptive Vision Switching
复制标题
使用自适应视觉切换模拟面部姿势跟踪系统
DOI：
10.1109/sas.2019.8706000
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
M. Ishikawa
中科院分区：
文献类型：
--
作者：
Hyuno Kim;Ryohei Ito;Seohyun Lee;Y. Yamakawa;M. Ishikawa
本文提出了一种基于网络摄像机系统的自适应视觉切换的人脸姿态跟踪方法，并用人脸计算机图形模型进行了仿真验证。该方法提高了传统单目摄像机的位姿估计精度。此外，自适应视觉切换提供了一种新的姿势跟踪体验-姿势锁定，它具有包括动态条件下的人脸识别在内的对象识别任务的潜力。对所提出的系统进行了定量分析和跟踪演示，并进行了仿真。
In this paper, a face pose tracking method using adaptive vision switching with a networked camera system is proposed and verified through simulation with a facial computer graphics model. The proposed method improves the pose estimation accuracy of the conventional techniques that use monocular camera. Additionally, adaptive vision switching provides a new pose tracking experience, pose lock-on, which has the potential for object recognition tasks including face recognition under dynamic conditions. Quantitative analysis and tracking demonstration with simulations of the proposed system are conducted and described.