Sistema visual para Ground Truth de sistemas autónomos

Este trabalho visa contribuir para o desenvolvimento de um sistema de visão multi-câmara para determinação da localização, atitude e seguimento de múltiplos objectos, para ser utilizado na unidade de robótica do INESCTEC, e resulta da necessidade de ter informação externa exacta que sirva de referência no estudo, caracterização e desenvolvimento de algoritmos de localização, navegação e controlo de vários sistemas autónomos. Com base na caracterização dos veículos autónomos existentes na unidade de robótica do INESCTEC e na análise dos seus cenários de operação, foi efectuado o levantamento de requisitos para o sistema a desenvolver. Foram estudados os fundamentos teóricos, necessários ao desenvolvimento do sistema, em temas relacionados com visão computacional, métodos de estimação e associação de dados para problemas de seguimento de múltiplos objectos . Foi proposta uma arquitectura para o sistema global que endereça os vários requisitos identi cados, permitindo a utilização de múltiplas câmaras e suportando o seguimento de múltiplos objectos, com ou sem marcadores. Foram implementados e validados componentes da arquitectura proposta e integrados num sistema para validação, focando na localização e seguimento de múltiplos objectos com marcadores luminosos à base de Light-Emitting Diodes (LEDs). Nomeadamente, os módulos para a identi cação dos pontos de interesse na imagem, técnicas para agrupar os vários pontos de interesse de cada objecto e efectuar a correspondência das medidas obtidas pelas várias câmaras, método para a determinação da posição e atitude dos objectos, ltro para seguimento de múltiplos objectos. Foram realizados testes para validação e a nação do sistema implementado que demonstram que a solução encontrada vai de encontro aos requisitos, e foram identi cadas as linhas de trabalho para a continuação do desenvolvimento do sistema global.

Application of Visual-Inertial SLAM for 3D Mapping of Underground Environments

The underground scenarios are one of the most challenging environments for accurate and precise 3d mapping where hostile conditions like absence of Global Positioning Systems, extreme lighting variations and geometrically smooth surfaces may be expected. So far, the state-of-the-art methods in underground modelling remain restricted to environments in which pronounced geometric features are abundant. This limitation is a consequence of the scan matching algorithms used to solve the localization and registration problems. This paper contributes to the expansion of the modelling capabilities to structures characterized by uniform geometry and smooth surfaces, as is the case of road and train tunnels. To achieve that, we combine some state of the art techniques from mobile robotics, and propose a method for 6DOF platform positioning in such scenarios, that is latter used for the environment modelling. A visual monocular Simultaneous Localization and Mapping (MonoSLAM) approach based on the Extended Kalman Filter (EKF), complemented by the introduction of inertial measurements in the prediction step, allows our system to localize himself over long distances, using exclusively sensors carried on board a mobile platform. By feeding the Extended Kalman Filter with inertial data we were able to overcome the major problem related with MonoSLAM implementations, known as scale factor ambiguity. Despite extreme lighting variations, reliable visual features were extracted through the SIFT algorithm, and inserted directly in the EKF mechanism according to the Inverse Depth Parametrization. Through the 1-Point RANSAC (Random Sample Consensus) wrong frame-to-frame feature matches were rejected. The developed method was tested based on a dataset acquired inside a road tunnel and the navigation results compared with a ground truth obtained by post-processing a high grade Inertial Navigation System and L1/L2 RTK-GPS measurements acquired outside the tunnel. Results from the localization strategy are presented and analyzed.

Visual SLAM for 3D large-scale seabed acquisition employing underwater vehicles

This paper presents a novel technique to align partial 3D reconstructions of the seabed acquired by a stereo camera mounted on an autonomous underwater vehicle. Vehicle localization and seabed mapping is performed simultaneously by means of an Extended Kalman Filter. Passive landmarks are detected on the images and characterized considering 2D and 3D features. Landmarks are re-observed while the robot is navigating and data association becomes easier but robust. Once the survey is completed, vehicle trajectory is smoothed by a Rauch-Tung-Striebel filter obtaining an even better alignment of the 3D views and yet a large-scale acquisition of the seabed

Distribution of calcium-binding proteins in the chick visual system

The calcium-binding proteins calbindin (CB), calretinin (CR), and parvalbumin (PV) have been extensively studied over the last decade since they appear to be important as buffers of intracellular calcium. In the present study we investigated the distribution of these proteins in the chick visual system by means of conventional immunocytochemistry. The results indicated that CB, CR, and PV are widely distributed in retinorecipient areas of the chick brain. In some regions, all three calcium-binding proteins were present at different intensities and often in different neurons such as in the dorsolateral thalamic complex. In other areas, such as the nucleus geniculatus lateralis ventralis, only CB and CR were detected, whereas PV was absent. These results show that these three calcium-binding proteins are differentially distributed in the visual system of the chick, with varying degrees of co-localization

Electrophysiology of Oculomotor Delayed Response Tasks: A Model for the Maturation of Visual-Spatial Working Memory Networks

In the literature, persistent neural activity over frontal and parietal areas during the delay period of oculomotor delayed response (ODR) tasks has been interpreted as an active representation of task relevant information and response preparation. Following a recent ERP study (Tekok-Kilic, Tays, & Tkach, 2011 ) that reported task related slow wave differences over frontal and parietal sites during the delay periods of three ODR tasks, the present investigation explored developmental differences in young adults and adolescents during the same ODR tasks using 128-channel dense electrode array methodology and source localization. This exploratory study showed that neural functioning underlying visual-spatial WM differed between age groups in the Match condition. More specifically, this difference is localized anteriorly during the late delay period. Given the protracted maturation of the frontal lobes, the observed variation at the frontal site may indicate that adolescents and young adults may recruit frontal-parietal resources differently.

Localization and function of the endocannabinoid system throughout the retinogeniculate pathway of vervet monkeys

Le système endocannabinoïde (eCB) est présent dans le système nerveux central (SNC) de mammifères, incluant la rétine, et est responsable de la régulation de nombreux processus physiologiques. Bien que la présence du récepteur cannabinoïde de type 1 (CB1R) a bien été documenté dans la rétine de rongeurs et primates, il y a encore une controverse quant à la présence du récepteur cannabinoïde de type 2 (CB2R) au niveau du SNC. En utilisant la microscopie confocale, nous sommes les premiers à signaler les patrons d’expression du CB2R dans la rétine de singe. Nos résultats démontrent que le CB2R est exprimé exclusivement dans les cellules de Müller de la rétine du singe. En outre, nous avons comparé les différents patrons d’expression du système eCB dans la rétine de la souris, du toupaye, ainsi que du singe vervet et macaque. Nous rapportons que les distributions de CB1R, FAAH (fatty acid amid hydrolase), MAGL (monoacylglycerol lipase) et DAGLα (diacylglycerol lipase alpha) sont hautement conservées parmi ces espèces alors que CB2R et NAPE-PLD (N-acyl phosphatidylethanolamine phospholipase D) présentent différents profils d'expression. CB2R n'a pas été détecté dans les cellules neuronales de la rétine des primates. L’immunoréactivité de NAPE-PLD est présente dans les couches de la rétine de souris et toupayes, mais a été limitée à la couche des photorécepteurs des singes vervet et macaque. Pour étudier les corrélats neuronaux et le rôle de la signalisation du système eCB dans la rétine, nous avons établi un protocole standard pour l'électrorétinographie (ERG), puis enregistré la réponse ERG de la rétine après le blocage des récepteurs avec des antagonistes spécifiques pour CB1R (AM251) et CB2R (AM630). Comparé au témoin, dans des conditions photopiques, et à certaines intensités faibles du stimulus, le blocage de CB1R diminue l'amplitude de l'onde-b, alors qu’à des intensités plus élevées, le blocage de CB2R augmente l'amplitude des deux-ondes a et b. De plus, le blocage des récepteurs cannabinoïdes provoque une augmentation de la latence des deux ondes a et b. Dans des conditions d’adaptation à l'obscurité, le blocage de CB1R et CB2R réduit l’amplitudes de l'onde a seulement à des intensités plus élevées et réduit l’onde b à intensités plus faibles. Des augmentations significatives de latence ont été observées dans les deux cas. Ces résultats indiquent que les récepteurs CB1 et CB2 chez les primates non humains sont impliqués dans la fonction rétinienne conditions photopiques. En outre, nous avons évalué le profil d'expression du CB1R, de FAAH et de NAPE-PLD au-delà de la rétine dans le corps géniculé latéral des singes et nous rapportons pour la première fois que CB1R et FAAH sont exprimés davantage dans les couches magnocellulaires. La NAPE-PLD a été localisée à travers les couches magno- et parvocellulaires. Aucune de ces composantes n’est exprimée dans les couches koniocellulaires. Ces résultats nous aident à mieux comprendre les effets des cannabinoïdes sur le système visuel qui pourraient nous mener à trouver éventuellement de nouvelles cibles thérapeutiques.

Visual SLAM for 3D large-scale seabed acquisition employing underwater vehicles

This paper presents a novel technique to align partial 3D reconstructions of the seabed acquired by a stereo camera mounted on an autonomous underwater vehicle. Vehicle localization and seabed mapping is performed simultaneously by means of an Extended Kalman Filter. Passive landmarks are detected on the images and characterized considering 2D and 3D features. Landmarks are re-observed while the robot is navigating and data association becomes easier but robust. Once the survey is completed, vehicle trajectory is smoothed by a Rauch-Tung-Striebel filter obtaining an even better alignment of the 3D views and yet a large-scale acquisition of the seabed

A proposal to estimate the motion of an underwater vehicle through visual mosaicking

This thesis proposes a solution to the problem of estimating the motion of an Unmanned Underwater Vehicle (UUV). Our approach is based on the integration of the incremental measurements which are provided by a vision system. When the vehicle is close to the underwater terrain, it constructs a visual map (so called "mosaic") of the area where the mission takes place while, at the same time, it localizes itself on this map, following the Concurrent Mapping and Localization strategy. The proposed methodology to achieve this goal is based on a feature-based mosaicking algorithm. A down-looking camera is attached to the underwater vehicle. As the vehicle moves, a sequence of images of the sea-floor is acquired by the camera. For every image of the sequence, a set of characteristic features is detected by means of a corner detector. Then, their correspondences are found in the next image of the sequence. Solving the correspondence problem in an accurate and reliable way is a difficult task in computer vision. We consider different alternatives to solve this problem by introducing a detailed analysis of the textural characteristics of the image. This is done in two phases: first comparing different texture operators individually, and next selecting those that best characterize the point/matching pair and using them together to obtain a more robust characterization. Various alternatives are also studied to merge the information provided by the individual texture operators. Finally, the best approach in terms of robustness and efficiency is proposed. After the correspondences have been solved, for every pair of consecutive images we obtain a list of image features in the first image and their matchings in the next frame. Our aim is now to recover the apparent motion of the camera from these features. Although an accurate texture analysis is devoted to the matching pro-cedure, some false matches (known as outliers) could still appear among the right correspon-dences. For this reason, a robust estimation technique is used to estimate the planar transformation (homography) which explains the dominant motion of the image. Next, this homography is used to warp the processed image to the common mosaic frame, constructing a composite image formed by every frame of the sequence. With the aim of estimating the position of the vehicle as the mosaic is being constructed, the 3D motion of the vehicle can be computed from the measurements obtained by a sonar altimeter and the incremental motion computed from the homography. Unfortunately, as the mosaic increases in size, image local alignment errors increase the inaccuracies associated to the position of the vehicle. Occasionally, the trajectory described by the vehicle may cross over itself. In this situation new information is available, and the system can readjust the position estimates. Our proposal consists not only in localizing the vehicle, but also in readjusting the trajectory described by the vehicle when crossover information is obtained. This is achieved by implementing an Augmented State Kalman Filter (ASKF). Kalman filtering appears as an adequate framework to deal with position estimates and their associated covariances. Finally, some experimental results are shown. A laboratory setup has been used to analyze and evaluate the accuracy of the mosaicking system. This setup enables a quantitative measurement of the accumulated errors of the mosaics created in the lab. Then, the results obtained from real sea trials using the URIS underwater vehicle are shown.

Optokinetic stimulation induces illusory movement of both out-of-the-body and on-the-body hand-held visual objects

The coding of body part location may depend upon both visual and proprioceptive information, and allows targets to be localized with respect to the body. The present study investigates the interaction between visual and proprioceptive localization systems under conditions of multisensory conflict induced by optokinetic stimulation (OKS). Healthy subjects were asked to estimate the apparent motion speed of a visual target (LED) that could be located either in the extrapersonal space (visual encoding only, V), or at the same distance, but stuck on the subject's right index finger-tip (visual and proprioceptive encoding, V-P). Additionally, the multisensory condition was performed with the index finger kept in position both passively (V-P passive) and actively (V-P active). Results showed that the visual stimulus was always perceived to move, irrespective of its out- or on-the-body location. Moreover, this apparent motion speed varied consistently with the speed of the moving OKS background in all conditions. Surprisingly, no differences were found between V-P active and V-P passive conditions in the speed of apparent motion. The persistence of the visual illusion during the active posture maintenance reveals a novel condition in which vision totally dominates over proprioceptive information, suggesting that the hand-held visual stimulus was perceived as a purely visual, external object despite its contact with the hand.

Electrophysiological correlates of spatial orienting towards angry faces: a source localization study

The goal of this study was to examine behavioral and electrophysiological correlates of involuntary orienting toward rapidly presented angry faces in non-anxious, healthy adults using a dot-probe task in conjunction with high-density event-related potentials and a distributed source localization technique. Consistent with previous studies, participants showed hypervigilance toward angry faces, as indexed by facilitated response time for validly cued probes following angry faces and an enhanced P1 component. An opposite pattern was found for happy faces suggesting that attention was directed toward the relatively more threatening stimuli within the visual field (neutral faces). Source localization of the P1 effect for angry faces indicated increased activity within the anterior cingulate cortex, possibly reflecting conflict experienced during invalidly cued trials. No modulation of the early C1 component was found for affect or spatial attention. Furthermore, the face-sensitive N170 was not modulated by emotional expression. Results suggest that the earliest modulation of spatial attention by face stimuli is manifested in the P1 component, and provide insights about mechanisms underlying attentional orienting toward cues of threat and social disapproval.

Visual sensor fusion for active security in robotic industrial environments

This work presents a method of information fusion involving data captured by both a standard CCD camera and a ToF camera to be used in the detection of the proximity between a manipulator robot and a human. Both cameras are assumed to be located above the work area of an industrial robot. The fusion of colour images and time of light information makes it possible to know the 3D localization of objects with respect to a world coordinate system. At the same time this allows to know their colour information. Considering that ToF information given by the range camera contains innacuracies including distance error, border error, and pixel saturation, some corrections over the ToF information are proposed and developed to improve the results. The proposed fusion method uses the calibration parameters of both cameras to reproject 3D ToF points, expressed in a common coordinate system for both cameras and a robot arm, in 2D colour images. In addition to this, using the 3D information, the motion detection in a robot industrial environment is achieved, and the fusion of information is applied to the foreground objects previously detected. This combination of information results in a matrix that links colour and 3D information, giving the possibility of characterising the object by its colour in addition to its 3D localization. Further development of these methods will make it possible to identify objects and their position in the real world, and to use this information to prevent possible collisions between the robot and such objects.

Visual sensor fusion for active security in robotic industrial environments

This work presents a method of information fusion involving data captured by both a standard charge-coupled device (CCD) camera and a time-of-flight (ToF) camera to be used in the detection of the proximity between a manipulator robot and a human. Both cameras are assumed to be located above the work area of an industrial robot. The fusion of colour images and time-of-flight information makes it possible to know the 3D localization of objects with respect to a world coordinate system. At the same time, this allows to know their colour information. Considering that ToF information given by the range camera contains innacuracies including distance error, border error, and pixel saturation, some corrections over the ToF information are proposed and developed to improve the results. The proposed fusion method uses the calibration parameters of both cameras to reproject 3D ToF points, expressed in a common coordinate system for both cameras and a robot arm, in 2D colour images. In addition to this, using the 3D information, the motion detection in a robot industrial environment is achieved, and the fusion of information is applied to the foreground objects previously detected. This combination of information results in a matrix that links colour and 3D information, giving the possibility of characterising the object by its colour in addition to its 3D localisation. Further development of these methods will make it possible to identify objects and their position in the real world and to use this information to prevent possible collisions between the robot and such objects.

Automatic attention lateral asymmetry in visual discrimination tasks

There is evidence that automatic visual attention favors the right side. This study investigated whether this lateral asymmetry interacts with the right hemisphere dominance for visual location processing and left hemisphere dominance for visual shape processing. Volunteers were tested in a location discrimination task and a shape discrimination task. The target stimuli (S2) could occur in the left or right hemifield. They were preceded by an ipsilateral, contralateral or bilateral prime stimulus (S1). The attentional effect produced by the right S1 was larger than that produced by the left S1. This lateral asymmetry was similar between the two tasks suggesting that the hemispheric asymmetries of visual mechanisms do not contribute to it. The finding that it was basically due to a longer reaction time to the left S2 than to the right S2 for the contralateral S1 condition suggests that the inhibitory component of attention is laterally asymmetric.

Methylmercury localization in Danio rerio retina after trophic and subchronic exposure: A basis for neurotoxicology

Methylmercury is a known neurotoxic organometal which affects visual functions and few studies concerns to wild fish are available. The autometallography mercury distribution in the retina of Danio rerio was mapped using light and electron microscopy. Abundant mercury deposits were found in the photoreceptor layer (outer and inner segments of the photoreceptors) and in the inner and outer nuclear layers. Occasionally, the presence of mercury deposits in plexiform layers was observed and very rarely in the ganglion cell layer. Also the occurrence of mercury deposits in cells from the disc region was observed, but not in the nerve fiber layer. An interesting difference was found between mercury accumulation in the central and peripheral regions of the retina. These results demonstrate that mercury after trophic exposure to Danio rerio is able to cross the blood-retina barrier and accumulate in the cells of the retina even under subchronic exposure. (C) 2010 Elsevier Inc. All rights reserved.

Real-Time Visual SLAM Using Pre - Existing Floor Lines as Landmarks and a Single Camera

SANTANA, André M.; SANTIAGO, Gutemberg S.; MEDEIROS, Adelardo A. D. Real-Time Visual SLAM Using Pre-Existing Floor Lines as Landmarks and a Single Camera. In: CONGRESSO BRASILEIRO DE AUTOMÁTICA, 2008, Juiz de Fora, MG. Anais... Juiz de Fora: CBA, 2008.