RetinaStudio: A bioinspired framework to encode visual information

The retina is a very complex neural structure, which performs spatial, temporal, and chromatic processing on visual information and converts it into a compact ‘digital’ format composed of neural impulses. This paper presents a new compiler-based framework able to describe, simulate and validate custom retina models. The framework is compatible with the most usual neural recording and analysis tools, taking advantage of the interoperability with these kinds of applications. Furthermore it is possible to compile the code to generate accelerated versions of the visual processing models compatible with COTS microprocessors, FPGAs or GPUs. The whole system represents an ongoing work to design and develop a functional visual neuroprosthesis. Several case studies are described to assess the effectiveness and usefulness of the framework.

Event-based visual servoing with features’ prediction

Event-based visual servoing is a recently presented approach that performs the positioning of a robot using visual information only when it is required. From the basis of the classical image-based visual servoing control law, the scheme proposed in this paper can reduce the processing time at each loop iteration in some specific conditions. The proposed control method enters in action when an event deactivates the classical image-based controller (i.e. when there is no image available to perform the tracking of the visual features). A virtual camera is then moved through a straight line path towards the desired position. The virtual path used to guide the robot improves the behavior of the previous event-based visual servoing proposal.

Dynamic visual servo control of a 4-axis joint tool to track image trajectories during machining complex shapes

A large part of the new generation of computer numerical control systems has adopted an architecture based on robotic systems. This architecture improves the implementation of many manufacturing processes in terms of flexibility, efficiency, accuracy and velocity. This paper presents a 4-axis robot tool based on a joint structure whose primary use is to perform complex machining shapes in some non-contact processes. A new dynamic visual controller is proposed in order to control the 4-axis joint structure, where image information is used in the control loop to guide the robot tool in the machining task. In addition, this controller eliminates the chaotic joint behavior which appears during tracking of the quasi-repetitive trajectories required in machining processes. Moreover, this robot tool can be coupled to a manipulator robot in order to form a multi-robot platform for complex manufacturing tasks. Therefore, the robot tool could perform a machining task using a piece grasped from the workspace by a manipulator robot. This manipulator robot could be guided by using visual information given by the robot tool, thereby obtaining an intelligent multi-robot platform controlled by only one camera.

Control of Redundant Joint Structures Using Image Information During the Tracking of Non-Smooth Trajectories

Visual information is increasingly being used in a great number of applications in order to perform the guidance of joint structures. This paper proposes an image-based controller which allows the joint structure guidance when its number of degrees of freedom is greater than the required for the developed task. In this case, the controller solves the redundancy combining two different tasks: the primary task allows the correct guidance using image information, and the secondary task determines the most adequate joint structure posture solving the possible joint redundancy regarding the performed task in the image space. The method proposed to guide the joint structure also employs a smoothing Kalman filter not only to determine the moment when abrupt changes occur in the tracked trajectory, but also to estimate and compensate these changes using the proposed filter. Furthermore, a direct visual control approach is proposed which integrates the visual information provided by this smoothing Kalman filter. This last aspect permits the correct tracking when noisy measurements are obtained. All the contributions are integrated in an application which requires the tracking of the faces of Asperger children.

Active Visual Features Based on Events to Guide Robot Manipulators in Tracking Tasks

Traditional visual servoing systems do not deal with the topic of moving objects tracking. When these systems are employed to track a moving object, depending on the object velocity, visual features can go out of the image, causing the fail of the tracking task. This occurs specially when the object and the robot are both stopped and then the object starts the movement. In this work, we have employed a retina camera based on Address Event Representation (AER) in order to use events as input in the visual servoing system. The events launched by the camera indicate a pixel movement. Event visual information is processed only at the moment it occurs, reducing the response time of visual servoing systems when they are used to track moving objects.

Guidance of robot arms using depth data from RGB-D camera

Image Based Visual Servoing (IBVS) is a robotic control scheme based on vision. This scheme uses only the visual information obtained from a camera to guide a robot from any robot pose to a desired one. However, IBVS requires the estimation of different parameters that cannot be obtained directly from the image. These parameters range from the intrinsic camera parameters (which can be obtained from a previous camera calibration), to the measured distance on the optical axis between the camera and visual features, it is the depth. This paper presents a comparative study of the performance of D-IBVS estimating the depth from three different ways using a low cost RGB-D sensor like Kinect. The visual servoing system has been developed over ROS (Robot Operating System), which is a meta-operating system for robots. The experiments prove that the computation of the depth value for each visual feature improves the system performance.

Towards a real-time 3D object recognition pipeline on mobile GPGPU computing platforms using low-cost RGB-D sensors

In this project, we propose the implementation of a 3D object recognition system which will be optimized to operate under demanding time constraints. The system must be robust so that objects can be recognized properly in poor light conditions and cluttered scenes with significant levels of occlusion. An important requirement must be met: the system must exhibit a reasonable performance running on a low power consumption mobile GPU computing platform (NVIDIA Jetson TK1) so that it can be integrated in mobile robotics systems, ambient intelligence or ambient assisted living applications. The acquisition system is based on the use of color and depth (RGB-D) data streams provided by low-cost 3D sensors like Microsoft Kinect or PrimeSense Carmine. The range of algorithms and applications to be implemented and integrated will be quite broad, ranging from the acquisition, outlier removal or filtering of the input data and the segmentation or characterization of regions of interest in the scene to the very object recognition and pose estimation. Furthermore, in order to validate the proposed system, we will create a 3D object dataset. It will be composed by a set of 3D models, reconstructed from common household objects, as well as a handful of test scenes in which those objects appear. The scenes will be characterized by different levels of occlusion, diverse distances from the elements to the sensor and variations on the pose of the target objects. The creation of this dataset implies the additional development of 3D data acquisition and 3D object reconstruction applications. The resulting system has many possible applications, ranging from mobile robot navigation and semantic scene labeling to human-computer interaction (HCI) systems based on visual information.

ViDRILO: The Visual and Depth Robot Indoor Localization with Objects information dataset

In this article we describe a semantic localization dataset for indoor environments named ViDRILO. The dataset provides five sequences of frames acquired with a mobile robot in two similar office buildings under different lighting conditions. Each frame consists of a point cloud representation of the scene and a perspective image. The frames in the dataset are annotated with the semantic category of the scene, but also with the presence or absence of a list of predefined objects appearing in the scene. In addition to the frames and annotations, the dataset is distributed with a set of tools for its use in both place classification and object recognition tasks. The large number of labeled frames in conjunction with the annotation scheme make this dataset different from existing ones. The ViDRILO dataset is released for use as a benchmark for different problems such as multimodal place classification and object recognition, 3D reconstruction or point cloud data compression.

Evidencia científica y recomendaciones sobre cribado de agudeza visual: revisión bibliográfica

Fundamentos: En los ámbitos científico e institucional existe controversia sobre cuándo recomendar la práctica del cribado visual en la población. El objetivo de este trabajo es valorar el nivel de evidencia científica que existe sobre el cribado visual para determinar si las recomendaciones existentes son o no adecuadas. Métodos: Revisión sistemática de artículos científicos consultando las bases de datos MedLine y The Cochranre Library Plus, sin restricción de fecha, en los idiomas español e inglés. Se incluyó literatura gris mediante búsqueda manual. No se hicieron restricciones respecto al tipo de estudio. Se revisaron los abstracts y en los casos necesarios los artículos completos, teniéndose en cuenta finalmente todos los artículos que incluían recomendaciones sobre cribado de agudeza visual y eliminando el resto. Resultados: Se seleccionaron 6 artículos. La mayoría de las recomendaciones realizadas por las sociedades fueron a través de guías de práctica clínica o artículos de opinión. Respecto a los diseños de los artículos científicos localizados hubo 2 ensayos aleatorios controlados, 3 ensayos no controlados y 1 estudio transversal. Conclusiones: Los estudios sobre adultos no permiten determinar que las recomendaciones realizadas por las sociedades científicas tengan una base científica sólida. En el caso de los niños, los estudios y las sociedades científicas no aclaran cuál es la edad más idónea para realizar cribado visual.

Event-based visual servoing

Traditional visual servoing systems have been widely studied in the last years. These systems control the position of the camera attached to the robot end-effector guiding it from any position to the desired one. These controllers can be improved by using the event-based control paradigm. The system proposed in this paper is based on the idea of activating the visual controller only when something significant has occurred in the system (e.g. when any visual feature can be loosen because it is going outside the frame). Different event triggers have been defined in the image space in order to activate or deactivate the visual controller. The tests implemented to validate the proposal have proved that this new scheme avoids visual features to go out of the image whereas the system complexity is reduced considerably. Events can be used in the future to change different parameters of the visual servoing systems.

Combining visual features and Growing Neural Gas networks for robotic 3D SLAM

The use of 3D data in mobile robotics provides valuable information about the robot’s environment. Traditionally, stereo cameras have been used as a low-cost 3D sensor. However, the lack of precision and texture for some surfaces suggests that the use of other 3D sensors could be more suitable. In this work, we examine the use of two sensors: an infrared SR4000 and a Kinect camera. We use a combination of 3D data obtained by these cameras, along with features obtained from 2D images acquired from these cameras, using a Growing Neural Gas (GNG) network applied to the 3D data. The goal is to obtain a robust egomotion technique. The GNG network is used to reduce the camera error. To calculate the egomotion, we test two methods for 3D registration. One is based on an iterative closest points algorithm, and the other employs random sample consensus. Finally, a simultaneous localization and mapping method is applied to the complete sequence to reduce the global error. The error from each sensor and the mapping results from the proposed method are examined.

The orchestration of modes and EFL audio-visual comprehension: A multimodal discourse analysis of vodcasts

This thesis explores the role of multimodality in language learners’ comprehension, and more specifically, the effects on students’ audio-visual comprehension when different orchestrations of modes appear in the visualization of vodcasts. Firstly, I describe the state of the art of its three main areas of concern, namely the evolution of meaning-making, Information and Communication Technology (ICT), and audio-visual comprehension. One of the most important contributions in the theoretical overview is the suggested integrative model of audio-visual comprehension, which attempts to explain how students process information received from different inputs. Secondly, I present a study based on the following research questions: ‘Which modes are orchestrated throughout the vodcasts?’, ‘Are there any multimodal ensembles that are more beneficial for students’ audio-visual comprehension?’, and ‘What are the students’ attitudes towards audio-visual (e.g., vodcasts) compared to traditional audio (e.g., audio tracks) comprehension activities?’. Along with these research questions, I have formulated two hypotheses: Audio-visual comprehension improves when there is a greater number of orchestrated modes, and students have a more positive attitude towards vodcasts than traditional audios when carrying out comprehension activities. The study includes a multimodal discourse analysis, audio-visual comprehension tests, and students’ questionnaires. The multimodal discourse analysis of two British Council’s language learning vodcasts, entitled English is GREAT and Camden Fashion, using ELAN as the multimodal annotation tool, shows that there are a variety of multimodal ensembles of two, three and four modes. The audio-visual comprehension tests were given to 40 Spanish students, learning English as a foreign language, after the visualization of vodcasts. These comprehension tests contain questions related to specific orchestrations of modes appearing in the vodcasts. The statistical analysis of the test results, using repeated-measures ANOVA, reveal that students obtain better audio-visual comprehension results when the multimodal ensembles are constituted by a greater number of orchestrated modes. Finally, the data compiled from the questionnaires, conclude that students have a more positive attitude towards vodcasts in comparison to traditional audio listenings. Results from the audio-visual comprehension tests and questionnaires prove the two hypotheses of this study.