A Head Pose Tracking System Using RGB-D Camera
نویسندگان
چکیده
In this paper, a fast head pose tracking system is introduced. It uses iterative closest point algorithm to register a dense face template to depth data captured by Kinect. It can achieve 33fps processing speed without specific optimization. To improve tracking robustness, head movement prediction is applied. We propose a novel scheme that can train several simple predictors together, enhancing the overall prediction accuracy. Experimental results confirm its effectiveness for head movement prediction.
منابع مشابه
AR Visualization of Thermal 3D Model by Hand-held Cameras
In this paper, we propose a system for AR visualization of thermal distribution on the environment. Our system is based on color 3D model and thermal 3D model of the target scene generated by KinectFusion using a thermal camera coupled with an RGB-D camera. In off-line phase, Viewpoint Generative Learning (VGL) is applied to the colored 3D model for collecting its stable keypoints descriptors. ...
متن کاملReal-Time Camera Tracking and 3D Reconstruction Using Signed Distance Functions
The ability to quickly acquire 3D models is an essential capability needed in many disciplines including robotics, computer vision, geodesy, and architecture. In this paper we present a novel method for real-time camera tracking and 3D reconstruction of static indoor environments using an RGB-D sensor. We show that by representing the geometry with a signed distance function (SDF), the camera p...
متن کامل3D Hand Pose Detection in Egocentric RGB-D Images
We focus on the task of everyday hand pose estimation from egocentric viewpoints. For this task, we show that depth sensors are particularly informative for extracting near-field interactions of the camera wearer with his/her environment. Despite the recent advances in full-body pose estimation using Kinect-like sensors, reliable monocular hand pose estimation in RGB-D images is still an unsolv...
متن کاملEfficient Online Surface Correction for Real-time Large-Scale 3D Reconstruction
State-of-the-art methods for large-scale 3D reconstruction from RGB-D sensors usually reduce drift in camera tracking by globally optimizing the estimated camera poses in real-time without simultaneously updating the reconstructed surface on pose changes. We propose an efficient on-the-fly surface correction method for globally consistent dense 3D reconstruction of large-scale scenes. Our appro...
متن کاملPeople Re-identification in Non-overlapping Field-of-views using Cumulative Brightness Transform Function and Body Segments in Different Color Spaces
Non-overlapping field-of-view (FOV) cameras are used in surveillance system to cover a wider area. Tracking in such systems is generally performed in two distinct steps. In the first step, people are identified and tracked in the FOV of a single camera. In the second step, re-identification of the people is carried out to track them in the whole area under surveillance. Various conventional fea...
متن کامل