Open Access
Robust and accurate 2D-tracking-based 3D positioning method: application to head pose estimation
(Elsevier, 2019) Ariz Galilea, Mikel; Villanueva Larre, Arantxa; Cabeza Laguna, Rafael; Ingeniería Eléctrica, Electrónica y de Comunicación; Ingeniaritza Elektrikoa, Elektronikoaren eta Telekomunikazio Ingeniaritzaren
Head pose estimation (HPE) is currently a growing research field, mainly because of the proliferation of human–computer interfaces (HCI) in the last decade. It offers a wide variety of applications, including human behavior analysis, driver assistance systems or gaze estimation systems. This article aims to contribute to the development of robust and accurate HPE methods based on 2D tracking of the face, enhancing performance of both 2D point tracking and 3D pose estimation. We start with a baseline method for pose estimation based on POSIT algorithm. A novel weighted variant of POSIT is then proposed, together with a methodology to estimate weights for the 2D–3D point correspondences. Further, outlier detection and correction methods are also proposed in order to enhance both point tracking and pose estimation. With the aim of achieving a wider impact, the problem is addressed using a global approach: all the methods proposed are generalizable to any kind of object for which an approximate 3D model is available. These methods have been evaluated for the specific task of HPE using two different head pose video databases; a recently published one that reflects the expected performance of the system in current technological conditions, and an older one that allows an extensive comparison with state-of-the-art HPE methods. Results show that the proposed enhancements improve the accuracy of both 2D facial point tracking and 3D HPE, with respect to the implemented baseline method, by over 15% in normal tracking conditions and over 30% in noisy tracking conditions. Moreover, the proposed HPE system outperforms the state of the art on the two databases.
Open Access
Improved strategies for HPE employing learning-by-synthesis approaches
(IEEE, 2018) Larumbe Bergera, Andoni; Ariz Galilea, Mikel; Bengoechea Irañeta, José Javier; Segura, Rubén; Cabeza Laguna, Rafael; Villanueva Larre, Arantxa; Ingeniería Eléctrica, Electrónica y de Comunicación; Ingeniaritza Elektrikoa, Elektronikoaren eta Telekomunikazio Ingeniaritzaren
The first contribution of this paper is the presentation of a synthetic video database where the groundtruth of 2D facial landmarks and 3D head poses is available to be used for training and evaluating Head Pose Estimation (HPE) methods. The database is publicly available and contains videos of users performing guided and natural movements. The second and main contribution is the submission of a hybrid method for HPE based on Pose from Ortography and Scaling by Iterations (POSIT). The 2D landmark detection is performed using Random Cascaded-Regression Copse (R-CR-C). For the training stage we use, state of the art labeled databases. Learning-by-synthesis approach has been also used to augment the size of the database employing the synthetic database. HPE accuracy is tested by using two literature 3D head models. The tracking method proposed has been compared with state of the art methods using Supervised Descent Regressors (SDR) in terms of accuracy, achieving an improvement of 60%.
Open Access
Contributions to Head Pose Estimation methods
(2016) Ariz Galilea, Mikel; Cabeza Laguna, Rafael; Villanueva Larre, Arantxa; Ingeniería Eléctrica y Electrónica; Ingeniaritza Elektrikoa eta Elektronikoa
Head Pose Estimation (HPE) is currently a growing research field, mainly because of the proliferation of human-computer interfaces (HCI) in the last decade. It offers a wide variety of applications, including driver assistance systems, pose-invariant face recognition, human behavior analysis, or popular HCI applications such as gaze estimation systems. HCIs show an increasing tendency to integrate HPE as another bridge for interaction, since it is a rich form of communication. For instance, gaze tracking systems suffer in unconstrained environments because they are very sensitive to head motion, and HPE has become a key point for successful gaze estimation. This thesis thus aims to contribute to the development of robust and accurate HPE methods based on 2D tracking of the face in videos. With the idea of achieving a better understanding of every aspect of the HPE process, a complete framework has been created in the first part of the thesis as a pillar to sustain the rest of the work. This framework consists of both simulation and realistic environments for HPE algorithm analysis. It includes the recording of two head pose databases of videos, one with synthetically generated heads and the other one with real subjects. They have proven to be extremely useful tools for the purpose, and therefore we expect to make them available for the whole scientific community. The problem of 3D face reconstruction using only 2D images from the videos has received special attention. A whole chapter has been devoted to the study and comparison of different single-view and multi-view based reconstruction methods in a controlled simulation environment. This has allowed us to isolate the 3D model fitting problem, thus drawing several conclusions regarding the influence of this critical part in a HPE system. With the aim of achieving a wider impact with this thesis, the pose estimation problem is addressed from a general perspective in which techniques that are generalizable to any kind of 3D object are proposed. Starting from a basic pose estimation approach (2D tracking & POSIT), different alternatives have been developed to improve performance. On the one hand, a tracking accuracy index (TAI) calculation method has been proposed, based on invariant shape metrics obtained from interlandmark relationships. This allows us to apply weights that compensate for 2D tracking inaccuracies and optimize the 3D pose estimation. On the other hand, outlier detection and outlier correction methods that aim to improve the 2D tracking itself have been proposed, addressing the typical drifting problem of point-tracking systems, and hence improving the 3D pose estimation further. These global methods have then been specifically adapted to HPE and evaluated using two head pose databases: our real database, which reflects the expected performance in current technological conditions, and the BU database, a widely referenced older database that allows an extensive comparison with other state-of-the-art HPE methods.
Open Access
Optimizing interoperability between video-oculographic and electromyographic systems
(Rehabilitation Research & Development Service, 2011) Navallas Irujo, Javier; Ariz Galilea, Mikel; Villanueva Larre, Arantxa; San Agustín, Javier; Cabeza Laguna, Rafael; Ingeniería Eléctrica y Electrónica; Ingeniaritza Elektrikoa eta Elektronikoa
A new system is presented that enhances the interoperability between a video-oculographic (VOG) system for mouse movement control and an electromyographic (EMG) system for mouse click detection. The proposed VOG-EMG system combines gaze and muscle information to minimize the number of undesired clicks due to involuntary activations and environmental noise. We tested the system with 24 subjects, comparing three different configurations: one in which the VOG and EMG systems worked independently and two in which we used VOG gaze information to improve the EMG click detection. Results show that the number of false-positive click detections can be reduced when VOG and EMG information is combined. In addition, the third configuration, including extra processing, can reduce the activation delay produced because of the combined use of the VOG and EMG systems. The new VOG-EMG system is meant to be used in noisy environments in which the number of false clicks may impeach a reliable human-computer interaction.
Open Access
Hybrid method based on topography for robust detection of iris center and eye corners
(ACM (Association for Computing Machinery), 2013) Villanueva Larre, Arantxa; Ponz Sarvisé, Victoria; Sesma Sánchez, Laura; Ariz Galilea, Mikel; Porta Cuéllar, Sonia; Cabeza Laguna, Rafael; Ingeniería Eléctrica, Electrónica y de Comunicación; Ingeniaritza Elektrikoa, Elektronikoaren eta Telekomunikazio Ingeniaritzaren
A multi-stage procedure to detect eye features is presented. Multiresolution and topographic classification are used to detect the iris center. The eye corner is calculated combining valley detection and eyelid curve extraction. The algorithm is tested in the BioID database and in a proprietary database containing more than 1200 images. The results show that the suggested algorithm is robust and accurate. Regarding the iris center our method obtains the best average behavior for the BioID database compared to other available algorithms. Additional contributions are that our algorithm functions in real time and does not require complex post processing stages.