Estimating Gesture Accuracy in Motion-Based Health Games

This manuscript details a technique for estimating gesture accuracy within the context of motion-based health video games using the MICROSOFT KINECT. We created a physical therapy game that requires players to imitate clinically significant reference gestures. Player performance is represented by the degree of similarity between the performed and reference gestures and is quantified by collecting the Euler angles of the player's gestures, converting them to a three-dimensional vector, and comparing the magnitude between the vectors. Lower difference values represent greater gestural correspondence and therefore greater player performance. A group of thirty-one subjects was tested. Subjects achieved gestural correspondence sufficient to complete the game's objectives while also improving their ability to perform reference gestures accurately.

Portable 3D laser-camera calibration system with color fusion for SLAM

Nowadays, the use of RGB-D sensors have focused a lot of research in computer vision and robotics. These kinds of sensors, like Kinect, allow to obtain 3D data together with color information. However, their working range is limited to less than 10 meters, making them useless in some robotics applications, like outdoor mapping. In these environments, 3D lasers, working in ranges of 20-80 meters, are better. But 3D lasers do not usually provide color information. A simple 2D camera can be used to provide color information to the point cloud, but a calibration process between camera and laser must be done. In this paper we present a portable calibration system to calibrate any traditional camera with a 3D laser in order to assign color information to the 3D points obtained. Thus, we can use laser precision and simultaneously make use of color information. Unlike other techniques that make use of a three-dimensional body of known dimensions in the calibration process, this system is highly portable because it makes use of small catadioptrics that can be placed in a simple manner in the environment. We use our calibration system in a 3D mapping system, including Simultaneous Location and Mapping (SLAM), in order to get a 3D colored map which can be used in different tasks. We show that an additional problem arises: 2D cameras information is different when lighting conditions change. So when we merge 3D point clouds from two different views, several points in a given neighborhood could have different color information. A new method for color fusion is presented, obtaining correct colored maps. The system will be tested by applying it to 3D reconstruction.

Portable 3D laser-camera calibration system with color fusion for SLAM

Paper submitted to the 43rd International Symposium on Robotics (ISR2012), Taipei, Taiwan, Aug. 29-31, 2012.

3D Maps Representation Using GNG

Current RGB-D sensors provide a big amount of valuable information for mobile robotics tasks like 3D map reconstruction, but the storage and processing of the incremental data provided by the different sensors through time quickly become unmanageable. In this work, we focus on 3D maps representation and propose the use of the Growing Neural Gas (GNG) network as a model to represent 3D input data. GNG method is able to represent the input data with a desired amount of neurons or resolution while preserving the topology of the input space. Experiments show how GNG method yields a better input space adaptation than other state-of-the-art 3D map representation methods.

Evaluation of sampling method effects in 3D non-rigid registration

Since the beginning of 3D computer vision problems, the use of techniques to reduce the data to make it treatable preserving the important aspects of the scene has been necessary. Currently, with the new low-cost RGB-D sensors, which provide a stream of color and 3D data of approximately 30 frames per second, this is getting more relevance. Many applications make use of these sensors and need a preprocessing to downsample the data in order to either reduce the processing time or improve the data (e.g., reducing noise or enhancing the important features). In this paper, we present a comparison of different downsampling techniques which are based on different principles. Concretely, five different downsampling methods are included: a bilinear-based method, a normal-based, a color-based, a combination of the normal and color-based samplings, and a growing neural gas (GNG)-based approach. For the comparison, two different models have been used acquired with the Blensor software. Moreover, to evaluate the effect of the downsampling in a real application, a 3D non-rigid registration is performed with the data sampled. From the experimentation we can conclude that depending on the purpose of the application some kernels of the sampling methods can improve drastically the results. Bilinear- and GNG-based methods provide homogeneous point clouds, but color-based and normal-based provide datasets with higher density of points in areas with specific features. In the non-rigid application, if a color-based sampled point cloud is used, it is possible to properly register two datasets for cases where intensity data are relevant in the model and outperform the results if only a homogeneous sampling is used.

Integrated architecture for vision-based indoor localization and mapping of a quadrotor micro-air vehicle

Atualmente os sistemas de pilotagem autónoma de quadricópteros estão a ser desenvolvidos de forma a efetuarem navegação em espaços exteriores, onde o sinal de GPS pode ser utilizado para definir waypoints de navegação, modos de position e altitude hold, returning home, entre outros. Contudo, o problema de navegação autónoma em espaços fechados sem que se utilize um sistema de posicionamento global dentro de uma sala, subsiste como um problema desafiante e sem solução fechada. Grande parte das soluções são baseadas em sensores dispendiosos, como o LIDAR ou como sistemas de posicionamento externos (p.ex. Vicon, Optitrack). Algumas destas soluções reservam a capacidade de processamento de dados dos sensores e dos algoritmos mais exigentes para sistemas de computação exteriores ao veículo, o que também retira a componente de autonomia total que se pretende num veículo com estas características. O objetivo desta tese pretende, assim, a preparação de um sistema aéreo não-tripulado de pequeno porte, nomeadamente um quadricóptero, que integre diferentes módulos que lhe permitam simultânea localização e mapeamento em espaços interiores onde o sinal GPS ´e negado, utilizando, para tal, uma câmara RGB-D, em conjunto com outros sensores internos e externos do quadricóptero, integrados num sistema que processa o posicionamento baseado em visão e com o qual se pretende que efectue, num futuro próximo, planeamento de movimento para navegação. O resultado deste trabalho foi uma arquitetura integrada para análise de módulos de localização, mapeamento e navegação, baseada em hardware aberto e barato e frameworks state-of-the-art disponíveis em código aberto. Foi também possível testar parcialmente alguns módulos de localização, sob certas condições de ensaio e certos parâmetros dos algoritmos. A capacidade de mapeamento da framework também foi testada e aprovada. A framework obtida encontra-se pronta para navegação, necessitando apenas de alguns ajustes e testes.

Deep Head Pose: Gaze-Direction Estimation in Multimodal Video

In this paper we present a convolutional neuralnetwork (CNN)-based model for human head pose estimation inlow-resolution multi-modal RGB-D data. We pose the problemas one of classification of human gazing direction. We furtherfine-tune a regressor based on the learned deep classifier. Next wecombine the two models (classification and regression) to estimateapproximate regression confidence. We present state-of-the-artresults in datasets that span the range of high-resolution humanrobot interaction (close up faces plus depth information) data tochallenging low resolution outdoor surveillance data. We buildupon our robust head-pose estimation and further introduce anew visual attention model to recover interaction with theenvironment. Using this probabilistic model, we show thatmany higher level scene understanding like human-human/sceneinteraction detection can be achieved. Our solution runs inreal-time on commercial hardware

Navegação de robô móvel em ambiente com humanos

Trabalho Final de Mestrado para obtenção do grau de Mestre em Engenharia Mecânica

Ús de Sensor Web Enablement per a gestió de dades marines i accés al servei d'observació de sensors a través de client Android

El present treball és un estudi de l'estat de Sensor Web Enablement (SWE) aplicat a l'àmbit marí d'investigació oceanogràfica. Per assolir aquest objectiu s'han avaluat les diferents solucions d'arquitectura de sistemes més adients a la problemàtica indicada i s'ha dissenyat un client de Sensor Observation Service (SOS) per plataforma mòbil Android que permeti consultar la descripció del sensor (SensorML) i conjunts d'observacions mitjançant estàndards oberts de SWE i peticions web (SOAP). Els dissenys anteriorment indicats han permès que quedés palès l'ampli ventall de possibilitats i avantatges que s'obtenen pel fet d'emprar SWE, ja que ens permet integrar fàcilment les dades proporcionades pels sensors i les pròpies descripcions dels sensors en diferents entorns, tal i com és el cas del disseny presentat en Android, a través d'estàndards oberts independents de les múltiples especificacions de cada fabricant, en un entorn, com és l'àmbit de la investigació marina on hi ha una gran heterogeneïtat de sensors i protocols.

Integració d'un sensor sonar d'escombrat lateral en un robot submarí

El grup de Visió per Computador i Robòtica (VICOROB) disposa de varis robotssubmarins per a la recerca i inspecció subaquàtica. Recentment s’ha adquiritun sensor sonar d’escombrat lateral el qual s’utilitza per realitzar imatgesacústiques del fons marí quan aquest es mou principalment a velocitat constanti mantenint el rumb.Els robots del grup VICOROB estan equipats amb diferents tipus de sensors icàmeres per analitzar el fons marí. Aquest sensors són de gran qualitat ipermeten conèixer de manera bastant satisfactòria l’entorn a les proximitats delrobot. Freqüentment però, aquest sensors estant sotmesos a diferentsrestriccions depenent de la seva naturalesa de funcionament, de tal maneraque es necessària la seva combinació per resoldre determinats problemes endiferents situacions.Amb aquest projecte, es pretén integrar un nou sistema de captura d’imatgessonores del fons marí, en un dels robots. Amb la integració d’aquest nousensor, s’espera obtenir una opció alternativa els sistemes actuals que puguiaportar informació addicional sobre el fons. Aquest sistema podrà ser utilitzatper realitzar tasques per les quals els altres sensors no estant preparats o béper complementar informació d’altres sensor

Desenvolupament d'un node sensor sense fils autoalimentat. Mòdul piezo-magnètic

En aquest projecte es pretén implementar un dispositiu capaç de ser auto-suficient i no dependre de cap tipus de pila, bateria o fil elèctric que l’abasteixi d’energia elèctrica. El dispositiu recol·lectarà la energia magnètica generada per la corrent elèctrica a un fil i la transformarà en energia elèctrica, que serà emmagatzemada per el seu posterior ús. A demès, aquest projecte s’ha desenvolupat en col·laboració amb un segon projecte, dintre del qual s’implementarà una xarxa de sensors, mitjançant el protocol MIWI. Aquest projecte es divideix en tres grans blocs. El primer bloc del projecte serà una introducció teòrica de tots els coneixements relacionats amb el concepte d’energy harvesting i els mecanismes físic implicats. Al segon bloc podrem veure com s’han realitzat els càlculs, simulacions i posada en marxa, dels diferents elements que formaran el dispositiu recol·lector d’energia. Per últim en el tercer bloc veurem el prototip ja implementat. Es valoraran els resultats obtinguts, i es veuran els temps que necessitarà per alimentar al microcontrolador.

Simulació de xarxes WSN (Wireless Sensor Network) per a la detecció d'incendis

Trabajo de final de carrera enfocado a la simulación de una WSN (Wireless Sensors Networks) mediante el programa Contiki 2.7 y el SO Ubuntu. La idea global del proyecto es conseguir simular un entorno con nodos sensores y, a posteriori, comprobar su correcto funcionamiento en motas reales, comprobando los resultados obtenidos en ambos entornos. De esta manera se puede facilitar la puesta en marcha de este tipo de redes inalámbricas en una aplicación real.

Integració d'un sensor sonar d'escombrat lateral en un robot submarí

El grup de Visió per Computador i Robòtica (VICOROB) disposa de varis robots submarins per a la recerca i inspecció subaquàtica. Recentment s’ha adquirit un sensor sonar d’escombrat lateral el qual s’utilitza per realitzar imatges acústiques del fons marí quan aquest es mou principalment a velocitat constant i mantenint el rumb. Els robots del grup VICOROB estan equipats amb diferents tipus de sensors i càmeres per analitzar el fons marí. Aquest sensors són de gran qualitat i permeten conèixer de manera bastant satisfactòria l’entorn a les proximitats del robot. Freqüentment però, aquest sensors estant sotmesos a diferents restriccions depenent de la seva naturalesa de funcionament, de tal manera que es necessària la seva combinació per resoldre determinats problemes en diferents situacions. Amb aquest projecte, es pretén integrar un nou sistema de captura d’imatges sonores del fons marí, en un dels robots. Amb la integració d’aquest nou sensor, s’espera obtenir una opció alternativa els sistemes actuals que pugui aportar informació addicional sobre el fons. Aquest sistema podrà ser utilitzat per realitzar tasques per les quals els altres sensors no estant preparats o bé per complementar informació d’altres sensor

Biomimetic sensor based on 5,10,15,20-tetrakis(pentafluorophenyl)-21H,23H- porphyrin iron (III) chloride and MWCNT for selective detection of 2,4-D

Exploitation of the electronic properties of carbon nanotubes for the development of voltammetric and amperometric sensors to monitor analytes of environmental relevance has increased in recent years. This work reports the development of a biomimetic sensor based on a carbon paste modified with 5,10,15,20-tetrakis(pentafluorophenyl)-21H,23H-porphyrin iron (III) chloride (a biomimetic catalyst of the P450 enzyme) and multi-wall carbon nanotubes (MWCNT), for the sensitive and selective detection of the herbicide 2,4- dichlorophenoxyacetic acid (2,4-D). The sensor was evaluated using cyclic voltammetry and amperometry, for electrochemical characterization and quantification purposes, respectively. Amperometric analyses were carried out at -100 mV vs. Ag/AgCl(KClsat), using a 0.1 mol L-1 phosphate buffer solution at pH 6.0 as the support electrolyte. Under these optimized analytical conditions, the sensor showed a linear response between 9.9 × 10-6 and 1.4 × 10-4 mol L-1, a sensitivity of 1.8 × 104 (±429) μA L mol -1, and limits of detection and quantification of 2.1 × 10 -6 and 6.8 × 10-6 mol L-1, respectively. The incorporation of functionalized MWCNT in the carbon paste resulted in a 10-fold increase in the response, compared to that of the biomimetic sensor without MWCNT. In addition, the low applied potential (-100 mV) used to obtain high sensitivity also contributed to the excellent selectivity of the proposed sensor. The viability of the application of this sensor for analysis of soil samples was confirmed by satisfactory recovery values, with a mean of 96% and RSD of 2.1% (n = 3). © 2013 Elsevier B.V.

Highly Sensitive Electrochemical Sensor for Determination of Vitamin D in Mixtures of Water-Ethanol

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)