Simultaneous Multi-face Zoom Tracking for 3-D People-Flow Analysis with Face Identification
Simultaneous Multi-face Zoom Tracking for 3-D People-Flow Analysis with Face Identification
复制标题
DOI：
10.1109/msn50589.2020.00073
复制
发表时间：
2020-12
期刊：
影响因子：
--
通讯作者：
Liheng Shen;Shaopeng Hu;Kohei Shimasaki;T. Senoo;I. Ishii
中科院分区：
文献类型：
--
作者：
Liheng Shen;Shaopeng Hu;Kohei Shimasaki;T. Senoo;I. Ishii
我们开发了一种基于双摄像头的多面变焦跟踪系统，该系统通过将镜子驱动云台摄像头与用于变焦视图的超快凝视控制和用于 3D 宽视图的 RGB-D 摄像头相结合，同时捕获变焦目标。在我们的系统中，RGB-D 相机在宽视野中检测多个人，并通过基于 CNN 的姿态估计输出其关键点的 3D 位置。镜面驱动云台相机同时将视点切换到鼻子关键点的方向，以放大其面部图像以进行人员识别。我们使用具有人员识别功能的 3D 人流分析的实验结果来展示我们的系统性能，其中具有 120 个视点/秒切换的镜像驱动云台摄像机可有效地充当五个虚拟 24 fps 云台摄像机，以跟踪和缩放室内场景中五个步行者的面部。
We developed a dual-camera-based multi-face zoom-tracking system that captures zoomed targets simultaneously by combining a mirror-drive pan-tilt camera with ultrafast gaze control for zoomed views and an RGB-D camera for 3D wide view. In our system, the RGB-D camera detects multiple persons in the wide view and outputs the 3-D positions of their keypoints with CNN-based pose estimation. The mirror-drive pan-tilt camera simultaneously switches its viewpoints to the directions of the nose keypoints to zoom on their face images to perform person identification. We demonstrate our system performance using experimental results of a 3-D people-flow analysis with person identification, where the mirror-drive pantilt camera with 120-viewpoints/s-switching functions effectively as five virtual 24-fps pan-tilt cameras to track and zoom on the faces of five walking persons in an indoor scene.