Contribuições para a localização e mapeamento em robótica através da identificação visual de lugares

Tese de doutoramento, Informática (Engenharia Informática), Universidade de Lisboa, Faculdade de Ciências, 2015

An exploration of pre-attentive visual discrimination using event-related potentials

The Mismatch Negativity (MMN) has been characterised as a ‘pre-attentive’ component of an Event-Related Potential (ERP) that is related to discriminatory processes. Although well established in the auditory domain, characteristics of the MMN are less well characterised in the visual domain. The five main studies presented in this thesis examine visual cortical processing using event-related potentials. Novel methodologies have been used to elicit visual detection and discrimination components in the absence of a behavioural task. Developing paradigms in which a behavioural task is not required may have important clinical applications for populations, such as young children, who cannot comply with the demands of an active task. The ‘pre-attentive’ nature of visual MMN has been investigated by modulating attention. Generators and hemispheric lateralisation of visual MMN have been investigated by using pertinent clinical groups. A three stimulus visual oddball paradigm was used to explore the elicitation of visual discrimination components to a change in the orientation of stimuli in the absence of a behavioural task. Monochrome stimuli based on pacman figures were employed that differed from each other only in terms of the orientation of their elements. One such stimulus formed an illusory figure in order to capture the participant’s attention, either in place of, or alongside, a behavioural task. The elicitation of a P3a to the illusory figure but not to the standard or deviant stimuli provided evidence that the illusory figure captured attention. A visual MMN response was recorded in a paradigm with no task demands. When a behavioural task was incorporated into the paradigm, a P3b component was elicited consistent with the allocation of attentional resources to the task. However, visual discrimination components were attenuated revealing that the illusory figure was unable to command all attentional resources from the standard deviant transition. The results are the first to suggest that the visual MMN is modulated by attention. Using the same three stimulus oddball paradigm, generators of visual MMN were investigated by recording potentials directly from the cortex of an adolescent undergoing pre-surgical evaluation for resection of a right anterior parietal lesion. To date no other study has explicitly recorded activity related to the visual MMN intracranially using an oddball paradigm in the absence of a behavioural task. Results indicated that visual N1 and visual MMN could be temporally and spatially separated, with visual MMN being recorded more anteriorly than N1. The characteristic abnormality in retinal projections in albinism afforded the opportunity to investigate each hemisphere in relative isolation and was used, for the first time, as a model to investigate lateralisation of visual MMN and illusory contour processing. Using the three stimulus oddball paradigm, no visual MMN was elicited in this group, and so no conclusions regarding the lateralisation of visual MMN could be made. Results suggested that both hemispheres were equally capable of processing an illusory figure. As a method of presenting visual test stimuli without conscious perception, a continuous visual stream paradigm was developed that used a briefly presented checkerboard stimulus combined with masking for exploring stimulus detection below and above subjective levels of perception. A correlate of very early cortical processing at a latency of 60-80 ms (CI) was elicited whether stimuli were reported as seen or unseen. Differences in visual processing were only evident at a latency of 90 ms (CII) implying that this component may represent a correlate of visual consciousness/awareness. Finally, an oddball sequence was introduced into the visual stream masking paradigm to investigate whether visual MMN responses could be recorded without conscious perception. The stimuli comprised of black and white checkerboard elements differing only in terms of their orientation to form an x or a +. Visual MMN was not recorded when participants were unable to report seeing the stimulus. Results therefore suggest that behavioural identification of the stimuli was required for the elicitation of visual MMN and that visual MMN may require some attentional resources. On the basis of these studies it is concluded that visual MMN is not entirely independent of attention. Further, the combination of clinical and non-clinical investigations provides a unique opportunity to study the characterisation and localisation of putative mechanisms related to conscious and non-conscious visual processing.

Analysis of temperature time-series: embedding dynamics into the MDS method

Global warming and the associated climate changes are being the subject of intensive research due to their major impact on social, economic and health aspects of the human life. Surface temperature time-series characterise Earth as a slow dynamics spatiotemporal system, evidencing long memory behaviour, typical of fractional order systems. Such phenomena are difficult to model and analyse, demanding for alternative approaches. This paper studies the complex correlations between global temperature time-series using the Multidimensional scaling (MDS) approach. MDS provides a graphical representation of the pattern of climatic similarities between regions around the globe. The similarities are quantified through two mathematical indices that correlate the monthly average temperatures observed in meteorological stations, over a given period of time. Furthermore, time dynamics is analysed by performing the MDS analysis over slices sampling the time series. MDS generates maps describing the stations’ locus in the perspective that, if they are perceived to be similar to each other, then they are placed on the map forming clusters. We show that MDS provides an intuitive and useful visual representation of the complex relationships that are present among temperature time-series, which are not perceived on traditional geographic maps. Moreover, MDS avoids sensitivity to the irregular distribution density of the meteorological stations.

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.

Probabilistic Egomotion for Stereo Visual Odometry

We present a novel approach of Stereo Visual Odometry for vehicles equipped with calibrated stereo cameras. We combine a dense probabilistic 5D egomotion estimation method with a sparse keypoint based stereo approach to provide high quality estimates of vehicle’s angular and linear velocities. To validate our approach, we perform two sets of experiments with a well known benchmarking dataset. First, we assess the quality of the raw velocity estimates in comparison to classical pose estimation algorithms. Second, we added to our method’s instantaneous velocity estimates a Kalman Filter and compare its performance with a well known open source stereo Visual Odometry library. The presented results compare favorably with state-of-the-art approaches, mainly in the estimation of the angular velocities, where significant improvements are achieved.

Results of computer assisted navigation in Total Knee Arthroplasty (TKA): comparison with the conventional method

The aim of this retrospective study was to compare the clinical and radiographic results after TKA (PFC, DePuy), performed either by computer assisted navigation (CAS, Brainlab, Johnson&Johnson) or by conventional means. Material and methods: Between May and December 2006 we reviewed 36 conventional TKA performed between 2002 and 2003 (group A) and 37 navigated TKA performed between 2005 and 2006 (group B) by the same experienced surgeon. The mean age in group A was 74 years (range 62-90) and 73 (range 58-85) in group B with a similar age distribution. The preoperative mechanical axes in group A ranged from -13° varus to +13° valgus (mean absolute deviation 6.83°, SD 3.86), in group B from -13° to +16° (mean absolute deviation 5.35, SD 4.29). Patients with a previous tibial osteotomy or revision arthroplasty were excluded from the study. Examination was done by an experienced orthopedic resident independent of the surgeon. All patients had pre- and postoperative long standing radiographs. The IKSS and the WOMAC were utilized to determine the clinical outcome. Patient's degree of satisfaction was assessed on a visual analogous scale (VAS). Results: 32 of the 37 navigated TKAs (86,5%) showed a postoperative mechanical axis within the limits of 3 degrees of valgus or varus deviation compared to only 24 (66%) of the 36 standard TKAs. This difference was significant (p = 0.045). The mean absolute deviation from neutral axis was 3.00° (range -5° to +9°, SD: 1.75) in group A in comparison to 1.54° (range -5° to +4°, SD: 1.41) in group B with a highly significant difference (p = 0.000). Furthermore, both groups showed a significant postoperative improvement of their mean IKSS-values (group A: 89 preoperative to 169 postoperative, group B 88 to 176) without a significant difference between the two groups. Neither the WOMAC nor the patient's degree of satisfaction - as assessed by VAS - showed significant differences. Operation time was significantly higher in group B (mean 119.9 min.) than in group A (mean 99.6 min., p <0.000). Conclusion: Our study showed consistent significant improvement of postoperative frontal alignment in TKA by computer assisted navigation (CAS) compared to standard methods, even in the hands of a surgeon well experienced in standard TKA implantation. However, the follow-up time of this study was not long enough to judge differences in clinical outcome. Thus, the relevance of computer navigation for clinical outcome and survival of TKA remains to be proved in long term studies to justify the longer operation time. References 1 Stulberg SD. Clin Orth Rel Res. 2003;(416):177-84. 2 Chauhan SK. JBJS Br. 2004;86(3):372-7. 3 Bäthis H, et al. Orthopäde. 2006;35(10):1056-65.

Remaining rod activity mediates visual behavior in adult Rpe65-/- mice.

Purpose: C57/Bl6, Cpfl1-/- (Cone photoreceptors function loss 1; pure rod function), Gnat1alpha-/- (rod alpha-transducin; pure cone function) and Rpe65-/-;Rho-/- double knock-out mice were studied in order to distinguish the respective contributions of the different photoreceptor (PR) systems that enable light perception and mediate a visual reflex in adult Rpe65-/- mice using a simple behavioural procedure. Methods: Visual function was estimated using a rotating automatized optomotor drum covered with vertical black and white stripes at spatial frequencies of 0.025 to 0.5 cycles per degree (cpd) in both photopic and scotopic conditions. To evaluate the contribution as well as the light intensity threshold of each PR system, we tested the mouse strains with different luminances. Results: Stripe rotation elicits head movements in wild-type (WT) animals in photopic and scotopic conditions depending on the spatial frequency, whereas Cpfl1-/- mice show a reduced activity in the photopic condition and Gnat1alpha-/- mice an almost absent response in the scotopic condition. Interestingly, a robust visual response is obtained with Rpe65-/- knockout mice at 0.075 cpd and 0.1 cpd in the photopic condition. The residual rod function in the Rpe65-/- animals was demonstrated by testing Rpe65-/-;Rho-/- mice that present no response in photopic conditions. Conclusions: The optomotor test is a simple method to estimate the visual function, and to evaluate the respective contributions of rod and cone systems. Using this test, we demonstrate that in Rpe65-/- mice, devoid of functional cones and of detectable 11-cis-retinal protein, rods mimic in part the cone function by mediating vision in photopic conditions.

Cognitive Behavior Therapy for Obsessive-Compulsive Behavior in Children with Autism Spectrum Disorder: A Comparison of Hierarchical Linear Modelling and Visual Analysis

Behavioral researchers commonly use single subject designs to evaluate the effects of a given treatment. Several different methods of data analysis are used, each with their own set of methodological strengths and limitations. Visual inspection is commonly used as a method of analyzing data which assesses the variability, level, and trend both within and between conditions (Cooper, Heron, & Heward, 2007). In an attempt to quantify treatment outcomes, researchers developed two methods for analysing data called Percentage of Non-overlapping Data Points (PND) and Percentage of Data Points Exceeding the Median (PEM). The purpose of the present study is to compare and contrast the use of Hierarchical Linear Modelling (HLM), PND and PEM in single subject research. The present study used 39 behaviours, across 17 participants to compare treatment outcomes of a group cognitive behavioural therapy program, using PND, PEM, and HLM on three response classes of Obsessive Compulsive Behaviour in children with Autism Spectrum Disorder. Findings suggest that PEM and HLM complement each other and both add invaluable information to the overall treatment results. Future research should consider using both PEM and HLM when analysing single subject designs, specifically grouped data with variability.

Investigations On The Development Of An Ann Model & Visual Manipulation Approach For 2-D Dft Computation In Image Processing

This thesis is an outcome of the investigations carried out on the development of an Artificial Neural Network (ANN) model to implement 2-D DFT at high speed. A new definition of 2-D DFT relation is presented. This new definition enables DFT computation organized in stages involving only real addition except at the final stage of computation. The number of stages is always fixed at 4. Two different strategies are proposed. 1) A visual representation of 2-D DFT coefficients. 2) A neural network approach. The visual representation scheme can be used to compute, analyze and manipulate 2D signals such as images in the frequency domain in terms of symbols derived from 2x2 DFT. This, in turn, can be represented in terms of real data. This approach can help analyze signals in the frequency domain even without computing the DFT coefficients. A hierarchical neural network model is developed to implement 2-D DFT. Presently, this model is capable of implementing 2-D DFT for a particular order N such that ((N))4 = 2. The model can be developed into one that can implement the 2-D DFT for any order N upto a set maximum limited by the hardware constraints. The reported method shows a potential in implementing the 2-D DF T in hardware as a VLSI / ASIC

Statistical evaluation of texture analysis from the biocrystallization method

The consumers are becoming more concerned about food quality, especially regarding how, when and where the foods are produced (Haglund et al., 1999; Kahl et al., 2004; Alföldi, et al., 2006). Therefore, during recent years there has been a growing interest in the methods for food quality assessment, especially in the picture-development methods as a complement to traditional chemical analysis of single compounds (Kahl et al., 2006). The biocrystallization as one of the picture-developing method is based on the crystallographic phenomenon that when crystallizing aqueous solutions of dihydrate CuCl2 with adding of organic solutions, originating, e.g., from crop samples, biocrystallograms are generated with reproducible crystal patterns (Kleber & Steinike-Hartung, 1959). Its output is a crystal pattern on glass plates from which different variables (numbers) can be calculated by using image analysis. However, there is a lack of a standardized evaluation method to quantify the morphological features of the biocrystallogram image. Therefore, the main sakes of this research are (1) to optimize an existing statistical model in order to describe all the effects that contribute to the experiment, (2) to investigate the effect of image parameters on the texture analysis of the biocrystallogram images, i.e., region of interest (ROI), color transformation and histogram matching on samples from the project 020E170/F financed by the Federal Ministry of Food, Agriculture and Consumer Protection(BMELV).The samples are wheat and carrots from controlled field and farm trials, (3) to consider the strongest effect of texture parameter with the visual evaluation criteria that have been developed by a group of researcher (University of Kassel, Germany; Louis Bolk Institute (LBI), Netherlands and Biodynamic Research Association Denmark (BRAD), Denmark) in order to clarify how the relation of the texture parameter and visual characteristics on an image is. The refined statistical model was accomplished by using a lme model with repeated measurements via crossed effects, programmed in R (version 2.1.0). The validity of the F and P values is checked against the SAS program. While getting from the ANOVA the same F values, the P values are bigger in R because of the more conservative approach. The refined model is calculating more significant P values. The optimization of the image analysis is dealing with the following parameters: ROI(Region of Interest which is the area around the geometrical center), color transformation (calculation of the 1 dimensional gray level value out of the three dimensional color information of the scanned picture, which is necessary for the texture analysis), histogram matching (normalization of the histogram of the picture to enhance the contrast and to minimize the errors from lighting conditions). The samples were wheat from DOC trial with 4 field replicates for the years 2003 and 2005, “market samples”(organic and conventional neighbors with the same variety) for 2004 and 2005, carrot where the samples were obtained from the University of Kassel (2 varieties, 2 nitrogen treatments) for the years 2004, 2005, 2006 and “market samples” of carrot for the years 2004 and 2005. The criterion for the optimization was repeatability of the differentiation of the samples over the different harvest(years). For different samples different ROIs were found, which reflect the different pictures. The best color transformation that shows efficiently differentiation is relied on gray scale, i.e., equal color transformation. The second dimension of the color transformation only appeared in some years for the effect of color wavelength(hue) for carrot treated with different nitrate fertilizer levels. The best histogram matching is the Gaussian distribution. The approach was to find a connection between the variables from textural image analysis with the different visual criteria. The relation between the texture parameters and visual evaluation criteria was limited to the carrot samples, especially, as it could be well differentiated by the texture analysis. It was possible to connect groups of variables of the texture analysis with groups of criteria from the visual evaluation. These selected variables were able to differentiate the samples but not able to classify the samples according to the treatment. Contrarily, in case of visual criteria which describe the picture as a whole there is a classification in 80% of the sample cases possible. Herewith, it clearly can find the limits of the single variable approach of the image analysis (texture analysis).

Geometry and Photometry in 3D Visual Recognition

The report addresses the problem of visual recognition under two sources of variability: geometric and photometric. The geometric deals with the relation between 3D objects and their views under orthographic and perspective projection. The photometric deals with the relation between 3D matte objects and their images under changing illumination conditions. Taken together, an alignment-based method is presented for recognizing objects viewed from arbitrary viewing positions and illuminated by arbitrary settings of light sources.

Computer Analysis of Visual Properties of Curved Objects

A method is presented for the visual analysis of objects by computer. It is particularly well suited for opaque objects with smoothly curved surfaces. The method extracts information about the object's surface properties, including measures of its specularity, texture, and regularity. It also aids in determining the object's shape. The application of this method to a simple recognition task ??e recognition of fruit ?? discussed. The results on a more complex smoothly curved object, a human face, are also considered.

A Statistical Image-Based Shape Model for Visual Hull Reconstruction and 3D Structure Inference

We present a statistical image-based shape + structure model for Bayesian visual hull reconstruction and 3D structure inference. The 3D shape of a class of objects is represented by sets of contours from silhouette views simultaneously observed from multiple calibrated cameras. Bayesian reconstructions of new shapes are then estimated using a prior density constructed with a mixture model and probabilistic principal components analysis. We show how the use of a class-specific prior in a visual hull reconstruction can reduce the effect of segmentation errors from the silhouette extraction process. The proposed method is applied to a data set of pedestrian images, and improvements in the approximate 3D models under various noise conditions are shown. We further augment the shape model to incorporate structural features of interest; unknown structural parameters for a novel set of contours are then inferred via the Bayesian reconstruction process. Model matching and parameter inference are done entirely in the image domain and require no explicit 3D construction. Our shape model enables accurate estimation of structure despite segmentation errors or missing views in the input silhouettes, and works even with only a single input view. Using a data set of thousands of pedestrian images generated from a synthetic model, we can accurately infer the 3D locations of 19 joints on the body based on observed silhouette contours from real images.

Vector-Based Integration of Local and Long-Range Information in Visual Cortex

Integration of inputs by cortical neurons provides the basis for the complex information processing performed in the cerebral cortex. Here, we propose a new analytic framework for understanding integration within cortical neuronal receptive fields. Based on the synaptic organization of cortex, we argue that neuronal integration is a systems--level process better studied in terms of local cortical circuitry than at the level of single neurons, and we present a method for constructing self-contained modules which capture (nonlinear) local circuit interactions. In this framework, receptive field elements naturally have dual (rather than the traditional unitary influence since they drive both excitatory and inhibitory cortical neurons. This vector-based analysis, in contrast to scalarsapproaches, greatly simplifies integration by permitting linear summation of inputs from both "classical" and "extraclassical" receptive field regions. We illustrate this by explaining two complex visual cortical phenomena, which are incompatible with scalar notions of neuronal integration.

Visual SLAM for underwater vehicles using video velocity log and natural landmarks

A visual SLAM system has been implemented and optimised for real-time deployment on an AUV equipped with calibrated stereo cameras. The system incorporates a novel approach to landmark description in which landmarks are local sub maps that consist of a cloud of 3D points and their associated SIFT/SURF descriptors. Landmarks are also sparsely distributed which simplifies and accelerates data association and map updates. In addition to landmark-based localisation the system utilises visual odometry to estimate the pose of the vehicle in 6 degrees of freedom by identifying temporal matches between consecutive local sub maps and computing the motion. Both the extended Kalman filter and unscented Kalman filter have been considered for filtering the observations. The output of the filter is also smoothed using the Rauch-Tung-Striebel (RTS) method to obtain a better alignment of the sequence of local sub maps and to deliver a large-scale 3D acquisition of the surveyed area. Synthetic experiments have been performed using a simulation environment in which ray tracing is used to generate synthetic images for the stereo system