Plane detection from monocular image sequences

AIRES, Kelson R. T. ; ARAÚJO, Hélder J. ; MEDEIROS, Adelardo A. D. . Plane Detection from Monocular Image Sequences. In: VISUALIZATION, IMAGING AND IMAGE PROCESSING, 2008, Palma de Mallorca, Spain. Proceedings..., Palma de Mallorca: VIIP, 2008

Localização e mapeamento simultâneos de ambientes planos usando visão monocular e representação híbrida do ambiente

The goal of this work is to propose a SLAM (Simultaneous Localization and Mapping) solution based on Extended Kalman Filter (EKF) in order to make possible a robot navigates along the environment using information from odometry and pre-existing lines on the floor. Initially, a segmentation step is necessary to classify parts of the image in floor or non floor . Then the image processing identifies floor lines and the parameters of these lines are mapped to world using a homography matrix. Finally, the identified lines are used in SLAM as landmarks in order to build a feature map. In parallel, using the corrected robot pose, the uncertainty about the pose and also the part non floor of the image, it is possible to build an occupancy grid map and generate a metric map with the obstacle s description. A greater autonomy for the robot is attained by using the two types of obtained map (the metric map and the features map). Thus, it is possible to run path planning tasks in parallel with localization and mapping. Practical results are presented to validate the proposal

Localização de robôs móveis autônomos utilizando fusão sensorial de odometria e visão monocular

The development and refinement of techniques that make simultaneous localization and mapping (SLAM) for an autonomous mobile robot and the building of local 3-D maps from a sequence of images, is widely studied in scientific circles. This work presents a monocular visual SLAM technique based on extended Kalman filter, which uses features found in a sequence of images using the SURF descriptor (Speeded Up Robust Features) and determines which features can be used as marks by a technique based on delayed initialization from 3-D straight lines. For this, only the coordinates of the features found in the image and the intrinsic and extrinsic camera parameters are avaliable. Its possible to determine the position of the marks only on the availability of information of depth. Tests have shown that during the route, the mobile robot detects the presence of characteristics in the images and through a proposed technique for delayed initialization of marks, adds new marks to the state vector of the extended Kalman filter (EKF), after estimating the depth of features. With the estimated position of the marks, it was possible to estimate the updated position of the robot at each step, obtaining good results that demonstrate the effectiveness of monocular visual SLAM system proposed in this paper

Plane detection from monocular image sequences

AIRES, Kelson R. T. ; ARAÚJO, Hélder J. ; MEDEIROS, Adelardo A. D. . Plane Detection from Monocular Image Sequences. In: VISUALIZATION, IMAGING AND IMAGE PROCESSING, 2008, Palma de Mallorca, Spain. Proceedings..., Palma de Mallorca: VIIP, 2008

Plane Detection Using Affine Homography

AIRES, Kelson R. T.; ARAÚJO, Hélder J.; MEDEIROS, Adelardo A. D. Plane Detection Using Affine Homography. In: CONGRESSO BRASILEIRO DE AUTOMÁTICA, 2008, Juiz de Fora, MG: Anais... do CBA 2008.

Efeito da suplementação com retinol palmitato em codornas (Coturnix coturnx japonica) nos níveis de retinol na gema dos ovos

Vitamin A deficiency is a serious public health problem in developing countries, and it causes death and blindness among children in the developing countries. The fortification of food could be an important source of vitamins to control deficiency. 60 Coturnix coturnix japonica quails were used in a randomized design with duration of seven weeks. The birds were assigned into five treatments with four repetitions. The objective was to evaluate the influence of the supplementation with different levels of retinyl palmitate (2,000 IU, 4,000 IU, 8,000IU and 16,000 IU) in quails under the levels of retinyl in egg yolks. The method used to dose retinyl in yolks of quail eggs was High Performance Liquid Chromatography and the enzymatic method to quantify the cholesterol concentration. The weight and production of eggs was significantly modified by the supplementation with retinyl in the birds. The results showed a gradual increase in the incorporation of retinyl in the egg yolk as a response to the supplementation, reaching values 384% higher than the control values. By the end of the supplementations a significant reduction in the concentrations of retinyl in the eggs yolk was observed. The most lasting supplementations were with 8,000 IU and 16,000 IU which lasted for three weeks. The cholesterol content in eggs was not significantly modified. The consumption of one egg enriched with 16000UI of retinol palmitate in the present study, by day, would probably reach 10 and 7,3% of the daily recommendations of this micronutrient for children of 1 to 3 years of age, and for 4 to 8 years, respectively. The nutritional value of eggs, related to the vitamin A, can be improved by supplementation of quails

Percursos para novas imagens: a produção audiovisual por não videntes

The purpose is to write a reflection on the audiovisual production by the visually impaired. The starting point for this research was a documentary video production workshop offered by the Instituto de Educação e Reabilitação de Cegos do Rio Grande do Norte - IERC / RN, with the participation of blind people with low vision and sighted employees of the institution. The research approach follows the precepts of complex thinking, where work is woven into the network, along with the researched. The theoretical framework is based on the theory of French sociologist Edgar Morin, and other important thinkers for this work, namely: Erving Goffman, Paulo Freire, Michel Foucault, Edward Said, Jacques Aumont, Phillpe Dubois, as well as scholars who think and theorize about his own condition and conduct discussions on the issue of blindness: Francisco Jose de Lima, Evgen Bavcar Jacques Lusseyran and Joana Belarmino. The research was formulated based on the statement in the interest of respondents to understand and produce visual images using video as a tool. In this sense, the methodology adopted approaches of action research in constructing the text and dialogue with the participation of those involved in the project. The technique of gathering the information was based on ethnographic description describing the dynamics of the workshop, the relationships between participants, relationship to the other that sees and the manner of operation of equipment. The main focus is the relationship based on dialogue of information, attitudes and ways of knowing from experience and capacity developed and obstacles for blind people to produce visual images using other benchmarks, such as touch, smell and time dimension and space, and add references that give new meaning to the guidelines based on visuality of ministering to the workshop. It is also held to discuss aspects related to the concept of image with sociological reflection about the audiovisual production made by blind people socially constructed and perpetuated by what Edgar Morin called cultural imprinting. Thus we attempted to walk the route with its obstacles and achievements in the production of new images that were seen

A Acessibilidade como veículo de inclusão social: proposta de dispositivo computacional para os deficientes visuais da cidade de Natal/RN

This study aims to propose a computing device mechanism which is capable to permit a tactile communication between individuals with visual impairment (blindness or low vision) through the Internet or through a local area network (LAN - Local Network Address). The work was developed under the research projects that currently are realized in the LAI (Laboratory of Integrated Accessibility) of the Federal University of Rio Grande do Norte. This way, the research was done in order to involve a prototype capable to recognize geometries by students considered blind from the Institute of Education and Rehabilitation of Blind of Rio Grande do Norte (IERC-RN), located in Alecrim neighborhood, Natal/RN. Besides this research, another prototype was developed to test the communication via a local network and Internet. To analyze the data, a qualitative and quantitative approach was used through simple statistical techniques, such as percentages and averages, to support subjective interpretations. The results offer an analysis of the extent to which the implementation can contribute to the socialization and learning of the visually impaired. Finally, some recommendations are suggested for the development of future researches in order to facilitate the proposed mechanism.

Abordagem da ergonomia para análise da acessibilidade a hóspedes com deficiência visual em hotéis: soluções de inclusão de pessoas cegas e com baixa visão

This study evaluates the level of accessibility for people with visual impairment (blindness and low vision) hotels in the city of Natal-RN, Brazil, and provides principles, guidelines and means of projective make hotels accessible, to promote comfort, autonomy and security of these people. We used a qualitative research methodology and quantitative trait descriptive, analytical and interpretive. Was taken as a base for field studies Ergonomic Analysis of Work, beginning with a study of the demands of accessibility of hotels and analyzing the modeling activity in these establishments through the application of interactional and observational techniques, such as film, photographic records, conversational actions and observation protocols. A protocol was developed and applied to evaluate the compliance of accessibility of hotels in the face of Brazilian technical standard NBR 9050 (2004). We used methods of Cognitive Task Analysis (CTA) associated with simulated activities to identify the processes of decision making and analyzing the observables of the activities performed by people with visual impairment (POS). Interviews were conducted with people who are blind and low vision in various cities in order to meet accessibility difficulties they faced in hotels and recommendations for improvement that they indicate. The mapping results showed that of 16 hotels 4 and 5 star studied in Natal-RN, reached only 7% of the 50 items of the protocol, while none of them reached 70% of the items. About the results obtained in simulated activities and analyzed from the ATC, we saw that the hotel where it was performed this step shows a need to adequately address the guests with visual impairments

Sistema de supervisão aérea baseado em navegação visual para detecção de anomalias em instalações de petróleo e gás

This work deals with the development of a prototype of a helicopter quadrotor for monitoring applications in oil facilities. Anomaly detection problems can be resolved through monitoringmissions performed by a suitably instrumented quadrotor, i.e. infrared thermosensors should be embedded. The proposed monitoring system aims to reduce accidents as well as to make possible the use of non-destructive techniques for detection and location of leaks caused by corrosion. To this end, the implementation of a prototype, its stabilization and a navigation strategy have been proposed. The control strategy is based on dividing the problem into two control hierarchical levels: the lower level stabilizes the angles and the altitude of the vehicle at the desired values, while the higher one provide appropriate references signals to the lower level in order the quadrotor performs the desired movements. The navigation strategy for helicopter quadrotor is made using information provided by a acquisition image system (monocular camera) embedded onto the helicopter. Considering that the low-level control has been solved, the proposed vision-based navigation technique treats the problem as high level control strategies, such as, relative position control, trajectory generation and trajectory tracking. For the position control we use a control technique for visual servoing based on image features. The trajectory generation is done in a offline step, which is a visual trajectory composed of a sequence of images. For the trajectory tracking problem is proposed a control strategy by continuous servovision, thus enabling a navigation strategy without metric maps. Simulation and experimental results are presented to validate the proposal

Odometria visual baseada em técnicas de structure from motion

Visual Odometry is the process that estimates camera position and orientation based solely on images and in features (projections of visual landmarks present in the scene) extraced from them. With the increasing advance of Computer Vision algorithms and computer processing power, the subarea known as Structure from Motion (SFM) started to supply mathematical tools composing localization systems for robotics and Augmented Reality applications, in contrast with its initial purpose of being used in inherently offline solutions aiming 3D reconstruction and image based modelling. In that way, this work proposes a pipeline to obtain relative position featuring a previously calibrated camera as positional sensor and based entirely on models and algorithms from SFM. Techniques usually applied in camera localization systems such as Kalman filters and particle filters are not used, making unnecessary additional information like probabilistic models for camera state transition. Experiments assessing both 3D reconstruction quality and camera position estimated by the system were performed, in which image sequences captured in reallistic scenarios were processed and compared to localization data gathered from a mobile robotic platform

Técnicas visuais de localização e mapeamento simultâneos sem extração de primitivas geométricas da imagem

In Simultaneous Localization and Mapping (SLAM - Simultaneous Localization and Mapping), a robot placed in an unknown location in any environment must be able to create a perspective of this environment (a map) and is situated in the same simultaneously, using only information captured by the robot s sensors and control signals known. Recently, driven by the advance of computing power, work in this area have proposed to use video camera as a sensor and it came so Visual SLAM. This has several approaches and the vast majority of them work basically extracting features of the environment, calculating the necessary correspondence and through these estimate the required parameters. This work presented a monocular visual SLAM system that uses direct image registration to calculate the image reprojection error and optimization methods that minimize this error and thus obtain the parameters for the robot pose and map of the environment directly from the pixels of the images. Thus the steps of extracting and matching features are not needed, enabling our system works well in environments where traditional approaches have difficulty. Moreover, when addressing the problem of SLAM as proposed in this work we avoid a very common problem in traditional approaches, known as error propagation. Worrying about the high computational cost of this approach have been tested several types of optimization methods in order to find a good balance between good estimates and processing time. The results presented in this work show the success of this system in different environments

Um olho torto na literatura de Graciliano Ramos

This dissertation analyses, within a psychoanalytical e literary perspective, the enigma of blindness in Graciliano Ramos s work. The approach takes into account, mainly, the narratives of Histórias de Alexandre (Alexandre s tales) and Infância (Childhood memories) as both books speak of the same theme: the injured eye. The writer s work is scourged so that a broaden symbolism regarding the hurt eye can be found. The subject is discussed from three significant elements: fragmentation, helplessness and melancholy; all these form the creative aesthetic of Graciliano, merging into a single object. Fragmentation representing the internal shattered world of his characters, which is reflected in the environment; helplessness, directly related to feelings of rejection; and melancholy, characterized by a strong feeling of emptiness. The theme of isolation and loss is discussed based on Mourning and melancholy, by Freud, and other theorizers. There is also a brief dialogue with the Romantic and philosophical theories, which tries to explain the melancholic condition in the individual before moments of distress. Such theories are the support for the understanding of the helplessness of the hero in Graciliano Ramos´s literature and for the assumption that the blindness in the mistreated boy of the book Infância could be the language of the traumatic aspect that colors the entire text of the writer. As matter of fact, it constitutes in the lost object represented in the anguish of the author s characters

Olhar em terra de cego: a visualidade em Ensaio sobre a Cegueira

"Looking at earth from blind: travel in the visuality of the test on Blindness" is a literary Essay resulted from the experience of different points of view regarding the Essay on Blindness (1996), not only showing a Modern aesthetical tendency in dialog with the Baroque one, but also discussing subjects related to the History of Mentalities. The chapters are disposed as follows: The first one presents a short Excursus about the author and his work; the second one introduces the concept of Allegory exemplifying it with representative images of Romance; the third one presents tragic elements in dialog with the Bataille Eroticism in an Allegory of Feeling; the fourth one shows Stylistic Features used as a display mean of Comedy in Romance going towards the musicalness, being the features used to provoke laugh; the fifth and last one discusses about the study pertinence. To conclude, in favor of a Sight Education, the study considered authors such as: Ariès (1977), Bataille (2003), Bakhtin (2002, 2000, 1999), Benjamin (2000, 1996), Chauí (2005, 2000), Foucault (2006, 2005, 2004, 2002), Freud (1970), Hansen (2006), Lino (2004), Sartre (2005), Vovelle (1996)

Detecção de predadores por dicromatas e tricromatas humanos e a sua implicação na evolução da visão de cores em primatas

Among placental mammals, primates are the only ones to present trichromatic color vision. However, the distribution of trichromacy among primates is not homogeneous: Old World primates shows an uniform trichromacy (with all individuals being trichromats) and New World primates exhibit a color vision polymorphism (with dichromatic males and dichromatic or trichromatic females). Visual ecology studies have investigated which selective pressures may have been responsible for the evolution of trichromacy in primates, diverging from the dichromat standard found in other mammals. Cues associated with foraging and the socio-reproductive status were analyzed, indicating a trichromatic advantage for the rapid detection of visually conspicuous objects against a green background. However, dichromats are characterized by an efficient capture of cryptic and camouflaged stimuli. These advantages regarding phenotype may be responsible for the maintenance of the visual polymorphism in New World primates and for the high incidence of color blindness in humans (standing around 8% in Caucasian men). An important factor that has not yet been experimentally taken into account is the predation risk and its effect on the evolution of trichromacy in primates. To answer this question, we prepared and edited pictures of animals with different coats: oncillas (Leopardus spp.), puma (Puma concolor) and ferret (Galictis cuja). The specimens were taxidermized and the photographs were taken in three different vegetation scenarios (dense forest, cerrado and grassland). The images of the predators were manipulated so that they fit into two categories of stimulus size (small or large). After color calibration and photo editing, these were presented to 40 humans (20 dichromats and 20 trichromats) by a computer program, which presented a set of four photos at a time (one picture containing the taxidermized animal amid the background vegetation and three depicting only the background vegetation) and recorded the response latency and success rate of the subjects. The results show a trichromatic advantage in detecting potential predators. The predator detection was influenced by the background, the predator species, the dimension of the stimulus and the observer s visual phenotype. As humans have a high rate of dyschromatopsias, when compared to wild Catarrhini or human tribal populations, it is possible that the increased rate of dichromats is a result of reduced pressure for rapid predator detection. Since our species came to live in more cohesive groups and resistant to attack by predators, with the advent of agriculture and the formation of villages, it is possible that the lower risk of predation has reduced the selection in favor of trichromats