Antoni Jaume-i-Capó

Interactive Rehabilitation System for Improvement of Balance Therapies in People With Cerebral Palsy

The present study covers a new experimental system, designed to improve the balance and postural control of adults with cerebral palsy. This system is based on a serious game for balance rehabilitation therapy, designed using the prototype development paradigm and features for rehabilitation with serious games: feedback, adaptability, motivational elements, and monitoring. In addition, the employed interaction technology is based on computer vision because motor rehabilitation consists of body movements that can be recorded, and because vision capture technology is noninvasive and can be used for clients who have difficulties in holding physical devices. Previous research has indicated that serious games help to motivate clients in therapy sessions; however, there remains a paucity of clinical evidence involving functionality. We rigorously evaluated the effects of physiotherapy treatment on balance and gait function of adult subjects with cerebral palsy undergoing our experimental system. A 24-week physiotherapy intervention program was conducted with nine adults from a cerebral palsy center who exercised weekly in 20-min sessions. Findings demonstrated a significant increase in balance and gait function scores resulting in indicators of greater independence for our participating adults. Scores improved from 16 to 21 points in a scale of 28, according to the Tinetti Scale for risk of falls, moving from high fall risk to moderate fall risk. Our promising results indicate that our experimental system is feasible for balance rehabilitation therapy.

Toward natural interaction through visual recognition of body gestures in real-time

In most of the existing human-computer interfaces, enactive knowledge as new natural interaction paradigm has not been fully exploited yet. Recent technological advances have created the possibility to enhance naturally and significantly the interface perception by means of visual inputs, the so-called Vision-Based Interfaces (VBI). In the present paper, we explore the recovery of the users body posture by means of combining robust computer vision techniques and a well known inverse kinematics algorithm in real-time. Specifically, we focus on recognizing the users motions with a particular mean, that is, a body gesture. Defining an appropriate representation of the users body posture based on a temporal parameterization, we apply non-parametric techniques to learn and recognize the users body gestures. This scheme of recognition has been applied to control a computer videogame in real-time to show the viability of the presented approach.

Use of serious games for motivational balance rehabilitation of cerebral palsy patients

Research studies show that serious games help to motivate users in rehabilitation and therapy is better when users are motivated. In this work we experiment with serious games for cerebral palsy patients, who rarely show capacity increases with therapy which causes them demotivation. For this reason, we have implemented balance rehabilitation video games for this group of patients. The video games were developed using the prototype development paradigm, respecting the requirements indicated by physiotherapists and including desirable features for rehabilitation serious games presented in the literature. A set of patients who abandoned therapy last year due to loss of motivation, has tested the video game for a period of 6 months. Whilst using the video game no patients have abandoned therapy, showing the appropriateness of games for this kind of patients.

Red Blood Cell Cluster Separation From Digital Images for Use in Sickle Cell Disease

The study of cell morphology is an important aspect of the diagnosis of some diseases, such as sickle cell disease, because red blood cell deformation is caused by these diseases. Due to the elongated shape of the erythrocyte, ellipse adjustment and concave point detection are applied widely to images of peripheral blood samples, including during the detection of cells that are partially occluded in the clusters generated by the sample preparation process. In the present study, we propose a method for the analysis of the shape of erythrocytes in peripheral blood smear samples of sickle cell disease, which uses ellipse adjustments and a new algorithm for detecting notable points. Furthermore, we apply a set of constraints that allow the elimination of significant image preprocessing steps proposed in previous studies. We used three types of images to validate our method: artificial images, which were automatically generated in a random manner using a computer code; real images from peripheral blood smear sample images that contained normal and elongated erythrocytes; and synthetic images generated from real isolated cells. Using the proposed method, the efficiency of detecting the two types of objects in the three image types exceeded 99.00%, 98.00%, and 99.35%, respectively. These efficiency levels were superior to the results obtained with previously proposed methods using the same database, which is available at http://erythrocytesidb.uib.es/. This method can be extended to clusters of several cells and it requires no user inputs.

Evaluating the Research in Automatic Emotion Recognition

ABSTRACT Aims: In this paper, we present a systematic literature review of the scientific research on the automatic recognition of personal emotions. Based on an overview of the existing evidence, we further discuss the main limitations, future directions, institutions, and influential figures in this field. Method: We conducted a systematic literature search of four electronic databases. Papers were systematically analysed in relation to specific research questions. Results: The literature review yielded a pool of 110 references, which was narrowed down to a final set of 32 based on inclusion and exclusion criteria. Findings reveal a growing volume of research in this field, with the USA and the UK leading these efforts and the researcher Maja Pantic as a pioneer and central figure in this area. Overall, our work revealed nine topics, with 98 databases identified. Further examination of the selected works exposed specific problems. Conclusions: Despite the growing number of existing research in each area of this vast field, most of the work is not systematic. To increase the efficiency and efficacy of obtaining information, we recommend the use of the standard systematic literature method in future efforts toward information syntheses on each of the topics.

Modeling depth for nonparametric foreground segmentation using RGBD devices

Abstract The problem of detecting changes in a scene and segmenting the foreground from background is still challenging, despite previous work. Moreover, new RGBD capturing devices include depth cues, which could be incorporated to improve foreground segmentation. In this work, we present a new nonparametric approach where a unified model mixes the device multiple information cues. In order to unify all the device channel cues, a new probabilistic depth data model is also proposed where we show how to handle the inaccurate data to improve foreground segmentation. A new RGBD video dataset is presented in order to introduce a new standard for comparison purposes of this kind of algorithms. Results show that the proposed approach can handle several practical situations and obtain good results in all cases.

Design Issues for Vision-Based Motor-Rehabilitation Serious Games

When rehabilitation sessions are for maintaining capacities, the demotivation of patients is common due to the difficulty in improving their situation. Recent experiments show that rehabilitation results are better when users are motivated and serious games can help to motivate patients in rehabilitation processes. We developed a rehabilitation serious-game for a set of patients who had abandoned therapy due to demotivation in the previous years. The serious-game was developed following desirable features for rehabilitation serious-games presented in the related research works. From this development, we present implementations guidelines for developing serious-games as motivational tool for rehabilitation therapies. The experiments performed in previous works validate that the interacting design issues defined help motivation in therapy and that they are adequate in rehabilitation therapy.

Improving Vision-Based Motor Rehabilitation Interactive Systems for Users with Disabilities Using Mirror Feedback

Observation is recommended in motor rehabilitation. For this reason, the aim of this study was to experimentally test the feasibility and benefit of including mirror feedback in vision-based rehabilitation systems: we projected the user on the screen. We conducted a user study by using a previously evaluated system that improved the balance and postural control of adults with cerebral palsy. We used a within-subjects design with the two defined feedback conditions (mirror and no-mirror) with two different groups of users (8 with disabilities and 32 without disabilities) using usability measures (time-to-start (T s) and time-to-complete (T c)). A two-tailed paired samples t-test confirmed that in case of disabilities the mirror feedback facilitated the interaction in vision-based systems for rehabilitation. The measured times were significantly worse in the absence of the users own visual feedback (T s = 7.09 (P < 0.001) and T c = 4.48 (P < 0.005)). In vision-based interaction systems, the input device is the users own body; therefore, it makes sense that feedback should be related to the body of the user. In case of disabilities the mirror feedback mechanisms facilitated the interaction in vision-based systems for rehabilitation. Results recommends developers and researchers use this improvement in vision-based motor rehabilitation interactive systems.

A tool for analytical simulation of B-splines surface deformation

A non-planar surface deformation model based on B-splines as finite elements is presented here. The model includes the variational formulation, the system of ordinary differential equations derived from it and its analytical solution. The model has been checked for a variety of surfaces such as tiles, half spheres, planes, etc. Furthermore, we are able to solve the system analytically by only moving a reduced number of control points to deform the surface. This makes the method faster, since numerical methods are no longer necessary.

Representation of Human Postures for Vision-Based Gesture Recognition in Real-Time

Using computer vision to sense and perceive the user and his/her actions in a Human-Computer Interaction context is often referred to as Vision-Based Interfaces. In this paper, we present a Vision-Based Interface guided by the user gestures. Previously to recognition, the users movements are obtained through a real-time vision-based motion capture system. This motion capture system is capable to estimate the user 3D body joints position in real-time. By means of an appropriate representation of limbs orientations based on temporal histograms, we present a scheme of gesture recognition that also works in real-time. This scheme of recognition has been tested through control of a classical computer videogame showing an excellent performance in on-line classification and it allows the possibility to achieve a learning phase in real-time due to its computational simplicity.