Method for targetless tracking subpixel in-plane movements

We present a targetless motion tracking method for detecting planar movements with subpixel accuracy. This method is based on the computation and tracking of the intersection of two nonparallel straight-line segments in the image of a moving object in a scene. The method is simple and easy to implement because no complex structures have to be detected. It has been tested and validated using a lab experiment consisting of a vibrating object that was recorded with a high-speed camera working at 1000 fps. We managed to track displacements with an accuracy of hundredths of pixel or even of thousandths of pixel in the case of tracking harmonic vibrations. The method is widely applicable because it can be used for distance measuring amplitude and frequency of vibrations with a vision system.

Fixation pattern analysis with microperimetry in nystagmus patients

Objective: To assess the usefulness of microperimetry (MP) as an additional objective method for characterizing the fixation pattern in nystagmus. Design: Prospective study. Participants: Fifteen eyes of 8 subjects (age, 12–80 years) with nystagmus from the Lluís Alcanyís Foundation (University of Valencia, Spain) were included. Methods: All patients had a comprehensive ophthalmologic examination including a microperimetric examination (MAIA, CenterVue, Padova, Italy). The following microperimetric parameters were evaluated: average threshold (AT), macular integrity index (MI), fixating points within a circle of 1° (P1) and 2° of radius (P2), bivariate contour ellipse area (BCEA) considering 63% and 95% of fixating points, and horizontal and vertical axes of that ellipse. Results: In monocular conditions, 6 eyes showed a fixation classified as stable, 6 eyes showed a relatively unstable fixation, and 3 eyes showed an unstable fixation. Statistically significant differences were found between the horizontal and vertical components of movement (p = 0.001), as well as in their ranges (p < 0.001). Intereye comparison showed differences between eyes in some subjects, but only statistically significant differences were found in the fixation coordinates X and Y (p < 0.001). No significant intereye differences were found between microperimetric parameters. Between monocular and binocular conditions, statistically significant differences in the X and Y coordinates were found in all eyes (p < 0.02) except one. No significant differences were found between MP parameters for monocular or binocular conditions. Strong correlations of corrected distance visual acuity (CDVA) with AT (r = 0.812, p = 0.014), MI (r = –0.812, p = 0.014), P1 (r = 0.729, p = 0.002), horizontal diameter of BCEA (r = –0.700, p = 0.004), and X range (r = –0.722, p = 0.005) were found. Conclusions: MP seems to be a useful technology for the characterization of the fixation pattern in nystagmus, which seems to be related to the level of visual acuity achieved by the patient.

A Novel Prediction Method for Early Recognition of Global Human Behaviour in Image Sequences

Human behaviour recognition has been, and still remains, a challenging problem that involves different areas of computational intelligence. The automated understanding of people activities from video sequences is an open research topic in which the computer vision and pattern recognition areas have made big efforts. In this paper, the problem is studied from a prediction point of view. We propose a novel method able to early detect behaviour using a small portion of the input, in addition to the capabilities of it to predict behaviour from new inputs. Specifically, we propose a predictive method based on a simple representation of trajectories of a person in the scene which allows a high level understanding of the global human behaviour. The representation of the trajectory is used as a descriptor of the activity of the individual. The descriptors are used as a cue of a classification stage for pattern recognition purposes. Classifiers are trained using the trajectory representation of the complete sequence. However, partial sequences are processed to evaluate the early prediction capabilities having a specific observation time of the scene. The experiments have been carried out using the three different dataset of the CAVIAR database taken into account the behaviour of an individual. Additionally, different classic classifiers have been used for experimentation in order to evaluate the robustness of the proposal. Results confirm the high accuracy of the proposal on the early recognition of people behaviours.

A connectionist computational method for face recognition

In this work, a modified version of the elastic bunch graph matching (EBGM) algorithm for face recognition is introduced. First, faces are detected by using a fuzzy skin detector based on the RGB color space. Then, the fiducial points for the facial graph are extracted automatically by adjusting a grid of points to the result of an edge detector. After that, the position of the nodes, their relation with their neighbors and their Gabor jets are calculated in order to obtain the feature vector defining each face. A self-organizing map (SOM) framework is shown afterwards. Thus, the calculation of the winning neuron and the recognition process are performed by using a similarity function that takes into account both the geometric and texture information of the facial graph. The set of experiments carried out for our SOM-EBGM method shows the accuracy of our proposal when compared with other state-of the-art methods.

A three-dimensional representation method for noisy point clouds based on growing self-organizing maps accelerated on GPUs

The research described in this thesis was motivated by the need of a robust model capable of representing 3D data obtained with 3D sensors, which are inherently noisy. In addition, time constraints have to be considered as these sensors are capable of providing a 3D data stream in real time. This thesis proposed the use of Self-Organizing Maps (SOMs) as a 3D representation model. In particular, we proposed the use of the Growing Neural Gas (GNG) network, which has been successfully used for clustering, pattern recognition and topology representation of multi-dimensional data. Until now, Self-Organizing Maps have been primarily computed offline and their application in 3D data has mainly focused on free noise models, without considering time constraints. It is proposed a hardware implementation leveraging the computing power of modern GPUs, which takes advantage of a new paradigm coined as General-Purpose Computing on Graphics Processing Units (GPGPU). The proposed methods were applied to different problem and applications in the area of computer vision such as the recognition and localization of objects, visual surveillance or 3D reconstruction.