Xavier Suau

Real-Time Head and Hand Tracking Based on 2.5D Data

A novel real-time algorithm for head and hand tracking is proposed in this paper. This approach is based on data from a range camera, which is exploited to resolve ambiguities and overlaps. The position of the head is estimated with a depth-based template matching, its robustness being reinforced with an adaptive search zone. Hands are detected in a bounding box attached to the head estimate, so that the user may move freely in the scene. A simple method to decide whether the hands are open or closed is also included in the proposal. Experimental results show high robustness against partial occlusions and fast movements. Accurate hand trajectories may be extracted from the estimated hand positions, and may be used for interactive applications as well as for gesture classification purposes.

Real-time fingertip localization conditioned on hand gesture classification

A method to obtain accurate hand gesture classification and fingertip localization from depth images is proposed. The Oriented Radial Distribution feature is utilized, exploiting its ability to globally describe hand poses, but also to locally detect fingertip positions. Hence, hand gesture and fingertip locations are characterized with a single feature calculation. We propose to divide the difficult problem of locating fingertips into two more tractable problems, by taking advantage of hand gesture as an auxiliary variable. Along with the method we present the ColorTip dataset, a dataset for hand gesture recognition and fingertip classification using depth data. ColorTip contains sequences where actors wear a glove with colored fingertips, allowing automatic annotation. The proposed method is evaluated against recent works in several datasets, achieving promising results in both gesture classification and fingertip localization.

Real-time head and hand tracking based on 2.5D data

A novel real-time algorithm for head and hand tracking is proposed in this paper. This approach is based on data from a range camera, which is exploited to resolve ambiguities and overlaps. The position of the head is estimated with a depth-based template matching, its robustness being reinforced with an adaptive search zone. Hands are detected in a bounding box attached to the head estimate, so that the user may move freely in the scene. A simple method to decide whether the hands are open or closed is also included in the proposal. Experimental results show high robustness against partial occlusions and fast movements. Accurate hand trajectories may be extracted from the estimated hand positions, and may be used for interactive applications as well as for gesture classification purposes.

From silhouettes to 3D points to mesh: towards free viewpoint video

This paper presents a system for 3D reconstruction from video sequences acquired in multi-camera environments. In particular, the 3D surfaces of foreground objects in the scene are extracted and represented by polygon meshes. Three stages are concatenated to process multi-view data. First, a foreground segmentation method extracts silhouettes of objects of interest. Then, a 3D reconstruction strategy obtains a cloud of oriented points that lie on the surfaces of the objects of interest in a spatially bounded volume. Finally, a fast meshing algorithm provides a topologically correct interpolation of the surface points that can be used for both visualization and further mesh processing purposes. The quality of the results (computational load) obtained by our system compares favorably against a baseline system built from state-of-the-art techniques for similar processing times (quality of the results).

Gesture control interface for immersive panoramic displays

In this paper, we propose a gesture-based interface designed to interact with panoramic scenes. The system combines novel static gestures with a fast hand tracking method. Our proposal is to use static gestures as shortcuts to activate functionalities of the system (i.e. volume up/down, mute, pause, etc.), and hand tracking to freely explore the panoramic video. The overall system is multi-user, and incorporates a user identification module based on face recognition, which is able both to recognize returning users and to add new users online. The system exploits depth data, making it robust to challenging illumination conditions. We show through experimental results the performance of every component of the system compared to the state of the art. We also show the results of a usability study performed with several untrained users.

Detecting end-effectors on 2.5D data using geometric deformable models: Application to human pose estimation

End-effectors are usually related to the location of limbs, and their reliable detection enables robust body tracking as well as accurate pose estimation. Recent innovation in depth cameras has re-stated the pose estimation problem. We focus on the information provided by these sensors, for which we borrow the name 2.5D data from the Graphics community. In this paper we propose a human pose estimation algorithm based on topological propagation. Geometric Deformable Models are used to carry out such propagation, implemented according to the Narrow Band Level Set approach. A variant of the latter method is proposed, including a density restriction which helps preserving the topological properties of the object under analysis. Principal end-effectors are extracted from a directed graph weighted with geodesic distances, also providing a skeletal-like structure describing human pose. An evaluation against reference methods is performed with promising results. The proposed solution allows a frame-wise end-effector detection, with no temporal tracking involved, which may be generalized to the tracking of other objects beyond human body.

Multi-Resolution Illumination Compensation for foreground extraction

Illumination changes may lead to false foreground (FG) segmentation and tracking results. Most of the existing FG extraction algorithms obtain a background (BG) estimation from temporal statistical parameters. Such algorithms consider a quasi-static BG which does not change but slowly. Therefore, fast illumination changes are not taken into account by the BG estimator and they are considered as FG. The aim of the proposed algorithm is to reduce illumination effects in video sequences in order to improve foreground segmentation performances.

INTAIRACT: joint hand gesture and fingertip classification for touchless interaction

In this demo we present intAIRact, an online hand-based touchless interaction system. Interactions are based on easy-to-learn hand gestures, that combined with translations and rotations render a user friendly and highly configurable system. The main advantage with respect to existing approaches is that we are able to robustly locate and identify fingertips. Hence, we are able to employ a simple but powerful alphabet of gestures not only by determining the number of visible fingers in a gesture, but also which fingers are being observed. To achieve such a system we propose a novel method that jointly infers hand gestures and fingertip locations using a single depth image from a consumer depth camera. Our approach is based on a novel descriptor for depth data, the Oriented Radial Distribution (ORD) [1]. On the one hand, we exploit the ORD for robust classification of hand gestures by means of efficient k-NN retrieval. On the other hand, maxima of the ORD are used to perform structured inference of fingertip locations. The proposed method outperforms other state-of-the-art approaches both in gesture recognition and fingertip localization. An implementation of the ORD extraction on a GPU yields a real-time demo running at approximately 17fps on a single laptop.

Oriented radial distribution on depth data: Application to the detection of end-effectors

End-effectors are considered to be the main topological extremities of a given 3D body. Even if the nature of such body is not restricted, this paper focuses on the human body case. Detection of human extremities is a key issue in the human motion capture domain, being needed to initialize and update the tracker. Therefore, the effectiveness of human motion capture systems usually depends on the reliability of the obtained end-effectors. The increasing accuracy, low cost and easy installation of depth cameras has opened the door to new strategies to overcome the body pose estimation problem. With the objective of detecting the head, hands and feet of a human body, we propose a new local feature computed from depth data, which gives an idea of its curvature and prominence. Such feature is weighted depending on recent detections, providing also a temporal dimension. Based on this feature, some end-effector candidate blobs are obtained and classified into head, hands and feet according to three probabilistic descriptors.

Surface reconstruction by restricted and oriented propagation

This paper considers the problem of reconstructing a surface from a point set. More specifically, we propose a method which focuses on obtaining fast surface reconstructions for visual purposes. The proposed scheme is based on propagation in a voxelized space, which is performed in the directions defined by a propagation pattern, during an optimal number of iterations. Real-time applications are conceivable thanks to a low execution time and computational cost, keeping an acceptable visual quality of the reconstruction.