A Method for Testing Object Localization as a Function of Eod Amplitude in the Weakly Electric Fish Brachyhypopomus Pinnicaudatus

I would like to thank Dr. Philip Stoddard for his patience and guidance throughout the past four years. He has not only taught me about behavior and electricity, but he has also taught me how to think scientifically. Vielka Salazar for making herself available to answer my questions and to help me with my projects. Montserrat Alfaro for providing me with support under times of frustration. Fabian A. Pal, who has often made himself available when I needed help to finish my projects, for being supportive, and for believing in me and my abilities. Most importantly, I would like to thank my parents who have shown tremendous support and patience during the past years. I would also like to thank the Honors Committee, specially Dr. Richards for taking the time to review my thesis and helping me modify it. Finally, I would like to thank the MARC program for providing me with financial assistance and the opportunity to perform this project.

From First Contact to Close Encounters: A Developmentally Deep Perceptual System for a Humanoid Robot

This thesis presents a perceptual system for a humanoid robot that integrates abilities such as object localization and recognition with the deeper developmental machinery required to forge those competences out of raw physical experiences. It shows that a robotic platform can build up and maintain a system for object localization, segmentation, and recognition, starting from very little. What the robot starts with is a direct solution to achieving figure/ground separation: it simply 'pokes around' in a region of visual ambiguity and watches what happens. If the arm passes through an area, that area is recognized as free space. If the arm collides with an object, causing it to move, the robot can use that motion to segment the object from the background. Once the robot can acquire reliable segmented views of objects, it learns from them, and from then on recognizes and segments those objects without further contact. Both low-level and high-level visual features can also be learned in this way, and examples are presented for both: orientation detection and affordance recognition, respectively. The motivation for this work is simple. Training on large corpora of annotated real-world data has proven crucial for creating robust solutions to perceptual problems such as speech recognition and face detection. But the powerful tools used during training of such systems are typically stripped away at deployment. Ideally they should remain, particularly for unstable tasks such as object detection, where the set of objects needed in a task tomorrow might be different from the set of objects needed today. The key limiting factor is access to training data, but as this thesis shows, that need not be a problem on a robotic platform that can actively probe its environment, and carry out experiments to resolve ambiguity. This work is an instance of a general approach to learning a new perceptual judgment: find special situations in which the perceptual judgment is easy and study these situations to find correlated features that can be observed more generally.

Generating Discriminative Objective Proposals via Submodular Ranking

Object recognition has long been a core problem in computer vision. To improve object spatial support and speed up object localization for object recognition, generating high-quality category-independent object proposals as the input for object recognition system has drawn attention recently. Given an image, we generate a limited number of high-quality and category-independent object proposals in advance and used as inputs for many computer vision tasks. We present an efficient dictionary-based model for image classification task. We further extend the work to a discriminative dictionary learning method for tensor sparse coding. In the first part, a multi-scale greedy-based object proposal generation approach is presented. Based on the multi-scale nature of objects in images, our approach is built on top of a hierarchical segmentation. We first identify the representative and diverse exemplar clusters within each scale. Object proposals are obtained by selecting a subset from the multi-scale segment pool via maximizing a submodular objective function, which consists of a weighted coverage term, a single-scale diversity term and a multi-scale reward term. The weighted coverage term forces the selected set of object proposals to be representative and compact; the single-scale diversity term encourages choosing segments from different exemplar clusters so that they will cover as many object patterns as possible; the multi-scale reward term encourages the selected proposals to be discriminative and selected from multiple layers generated by the hierarchical image segmentation. The experimental results on the Berkeley Segmentation Dataset and PASCAL VOC2012 segmentation dataset demonstrate the accuracy and efficiency of our object proposal model. Additionally, we validate our object proposals in simultaneous segmentation and detection and outperform the state-of-art performance. To classify the object in the image, we design a discriminative, structural low-rank framework for image classification. We use a supervised learning method to construct a discriminative and reconstructive dictionary. By introducing an ideal regularization term, we perform low-rank matrix recovery for contaminated training data from all categories simultaneously without losing structural information. A discriminative low-rank representation for images with respect to the constructed dictionary is obtained. With semantic structure information and strong identification capability, this representation is good for classification tasks even using a simple linear multi-classifier.

Object recognition for autonomous objects: comparison of two approaches

Report for the scientific sojourn at the Swiss Federal Institute of Technology Zurich, Switzerland, between September and December 2007. In order to make robots useful assistants for our everyday life, the ability to learn and recognize objects is of essential importance. However, object recognition in real scenes is one of the most challenging problems in computer vision, as it is necessary to deal with difficulties. Furthermore, in mobile robotics a new challenge is added to the list: computational complexity. In a dynamic world, information about the objects in the scene can become obsolete before it is ready to be used if the detection algorithm is not fast enough. Two recent object recognition techniques have achieved notable results: the constellation approach proposed by Lowe and the bag of words approach proposed by Nistér and Stewénius. The Lowe constellation approach is the one currently being used in the robot localization project of the COGNIRON project. This report is divided in two main sections. The first section is devoted to briefly review the currently used object recognition system, the Lowe approach, and bring to light the drawbacks found for object recognition in the context of indoor mobile robot navigation. Additionally the proposed improvements for the algorithm are described. In the second section the alternative bag of words method is reviewed, as well as several experiments conducted to evaluate its performance with our own object databases. Furthermore, some modifications to the original algorithm to make it suitable for object detection in unsegmented images are proposed.

An Encoded Infrared Sheet Of Light Navigational Beacon System For Precise Localization Of Indoor Mobile Robot Vehicles

A new localization approach to increase the navigational capabilities and object manipulation of autonomous mobile robots, based on an encoded infrared sheet of light beacon system, which provides position errors smaller than 0.02m is presented in this paper. To achieve this minimal position error, a resolution enhancement technique has been developed by utilising an inbuilt odometric/optical flow sensor information. This system respects strong low cost constraints by using an innovative assembly for the digitally encoded infrared transmitter. For better guidance of mobile robot vehicles, an online traffic signalling capability is also incorporated. Other added features are its less computational complexity and online localization capability all these without any estimation uncertainty. The constructional details, experimental results and computational methodologies of the system are also described

Attentional Selection in Object Recognition

A key problem in object recognition is selection, namely, the problem of identifying regions in an image within which to start the recognition process, ideally by isolating regions that are likely to come from a single object. Such a selection mechanism has been found to be crucial in reducing the combinatorial search involved in the matching stage of object recognition. Even though selection is of help in recognition, it has largely remained unsolved because of the difficulty in isolating regions belonging to objects under complex imaging conditions involving occlusions, changing illumination, and object appearances. This thesis presents a novel approach to the selection problem by proposing a computational model of visual attentional selection as a paradigm for selection in recognition. In particular, it proposes two modes of attentional selection, namely, attracted and pay attention modes as being appropriate for data and model-driven selection in recognition. An implementation of this model has led to new ways of extracting color, texture and line group information in images, and their subsequent use in isolating areas of the scene likely to contain the model object. Among the specific results in this thesis are: a method of specifying color by perceptual color categories for fast color region segmentation and color-based localization of objects, and a result showing that the recognition of texture patterns on model objects is possible under changes in orientation and occlusions without detailed segmentation. The thesis also presents an evaluation of the proposed model by integrating with a 3D from 2D object recognition system and recording the improvement in performance. These results indicate that attentional selection can significantly overcome the computational bottleneck in object recognition, both due to a reduction in the number of features, and due to a reduction in the number of matches during recognition using the information derived during selection. Finally, these studies have revealed a surprising use of selection, namely, in the partial solution of the pose of a 3D object.

Face Detection and Facial Feature Localization for multi-pose faces and complex backgroundimages

The objective of this thesis work, is to propose an algorithm to detect the faces in a digital image with complex background. A lot of work has already been done in the area of face detection, but drawback of some face detection algorithms is the lack of ability to detect faces with closed eyes and open mouth. Thus facial features form an important basis for detection. The current thesis work focuses on detection of faces based on facial objects. The procedure is composed of three different phases: segmentation phase, filtering phase and localization phase. In segmentation phase, the algorithm utilizes color segmentation to isolate human skin color based on its chrominance properties. In filtering phase, Minkowski addition based object removal (Morphological operations) has been used to remove the non-skin regions. In the last phase, Image Processing and Computer Vision methods have been used to find the existence of facial components in the skin regions.This method is effective on detecting a face region with closed eyes, open mouth and a half profile face. The experiment’s results demonstrated that the detection accuracy is around 85.4% and the detection speed is faster when compared to neural network method and other techniques.

Molecular analysis of $\beta$1,4-galactosyl-transferase localization to the cell surface and participation in cell adhesion

$\beta$1,4-Galactosyltransferase (GalTase) is unusual among the glycosyltransferases in that it is found in two subcellular compartments where it performs different functions. In the trans-Golgi complex, GalTase participates in oligosaccharide biosynthesis as do other glycosyltransferases. GalTase is also found on the cell surface, where it associates with the cytoskeleton and functions as a receptor for extracellular oligosaccharide ligands. Although we know much regarding GalTase function on the cell surface, little is known about the mechanisms underlying its transport to the plasma membrane. Cloning of the GalTase gene revealed that there are two GalTase proteins (i.e., long and short) with different size cytoplasmic tails. This raises the possibility that differences in the cytoplasmic domain of GalTase may influence its subcellular distribution. The object of this study was to examine this hypothesis directly through the use of molecular, immunological, and biochemical approaches.^ To examine whether the two GalTase proteins are targeted to different subcellular compartments, F9 embryonal carcinoma cells were transfected with either long or short GalTase cDNAs and intracellular and cell surface enzyme levels measured. Cell surface GalTase activity was enriched in cells overexpressing the long, but not the form of short GalTase. Furthermore, a dominant negative mutation in cell surface GalTase was created by transfecting cells with GalTase cDNAs encoding a truncated version of long GalTase devoid of the extracellular catalytic domain. Overexpressing the complete cytoplasmic and transmembrane domains of long GalTase led to a loss of GalTase-dependent cellular adhesion by specifically displacing surface GalTase from its cytoskeletal associations. In contrast, overexpressing the analogous truncated protein of short GalTase had no effect on cell adhesion. Finally, chloramphenicol acetyltransferase (CAT) reporter proteins were used to determine directly whether the cytoplasmic domains of long and short GalTase were responsible for differential subcellular distribution. The cytoplasmic and transmembrane domains of long GalTase led to CAT expression on the ceil surface and its association with the detergent-insoluble cytoskeleton; the analogous fusion protein containing short GalTase was restricted to the Golgi compartment. These results suggest that the cytoplasmic domain unique to long GalTase is responsible for targeting a portion of this protein to the cell surface and associating it with the cytoskeleton, enabling it to function as a cell adhesion molecule. ^

Nonparametric Message Passing Methods for Cooperative Localization and Tracking

The objective of this thesis is the development of cooperative localization and tracking algorithms using nonparametric message passing techniques. In contrast to the most well-known techniques, the goal is to estimate the posterior probability density function (PDF) of the position of each sensor. This problem can be solved using Bayesian approach, but it is intractable in general case. Nevertheless, the particle-based approximation (via nonparametric representation), and an appropriate factorization of the joint PDFs (using message passing methods), make Bayesian approach acceptable for inference in sensor networks. The well-known method for this problem, nonparametric belief propagation (NBP), can lead to inaccurate beliefs and possible non-convergence in loopy networks. Therefore, we propose four novel algorithms which alleviate these problems: nonparametric generalized belief propagation (NGBP) based on junction tree (NGBP-JT), NGBP based on pseudo-junction tree (NGBP-PJT), NBP based on spanning trees (NBP-ST), and uniformly-reweighted NBP (URW-NBP). We also extend NBP for cooperative localization in mobile networks. In contrast to the previous methods, we use an optional smoothing, provide a novel communication protocol, and increase the efficiency of the sampling techniques. Moreover, we propose novel algorithms for distributed tracking, in which the goal is to track the passive object which cannot locate itself. In particular, we develop distributed particle filtering (DPF) based on three asynchronous belief consensus (BC) algorithms: standard belief consensus (SBC), broadcast gossip (BG), and belief propagation (BP). Finally, the last part of this thesis includes the experimental analysis of some of the proposed algorithms, in which we found that the results based on real measurements are very similar with the results based on theoretical models.

Camera localization using trajectories and maps

We propose a new Bayesian framework for automatically determining the position (location and orientation) of an uncalibrated camera using the observations of moving objects and a schematic map of the passable areas of the environment. Our approach takes advantage of static and dynamic information on the scene structures through prior probability distributions for object dynamics. The proposed approach restricts plausible positions where the sensor can be located while taking into account the inherent ambiguity of the given setting. The proposed framework samples from the posterior probability distribution for the camera position via data driven MCMC, guided by an initial geometric analysis that restricts the search space. A Kullback-Leibler divergence analysis is then used that yields the final camera position estimate, while explicitly isolating ambiguous settings. The proposed approach is evaluated in synthetic and real environments, showing its satisfactory performance in both ambiguous and unambiguous settings.

Probabilistic visual recognition of artificial landmarks for simultaneous localization and mapping

Probabilistic robotics most often applied to the problem of simultaneous localisation and mapping (SLAM), requires measures of uncertainty to accompany observations of the environment. This paper describes how uncertainty can be characterised for a vision system that locates coloured landmarks in a typical laboratory environment. The paper describes a model of the uncertainty in segmentation, the internal cameral model and the mounting of the camera on the robot. It explains the implementation of the system on a laboratory robot, and provides experimental results that show the coherence of the uncertainty model.

The Localization Procedures of the Vector of Weighting Coefficients on the Set of Teaching Experts in the Tasks of Consuming

In terms of binary relations the author analyses the task of an individual consumers’ choice on the teaching excerpts set. It is suggested to analyse the function of consumer’s value as additive reduction. For localization of the vector of weighting coefficients of additive reduction the procedures based on metrics of object distance towards the ideal point are suggested.

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.

Microsatellite In Aeschynomene Falcata (leguminosae): Diversity, Cross-amplification, And Chromosome Localization.

Aeschynomene falcata is an important forage species; however, because of low seed production, it is underutilized as forage species. Aeschynomene is a polyphyletic genus with a challenging taxonomic position. Two subgenera have been proposed, and it is suggested that Aeschynomene can be split in 2 genera. Thus, new markers, such as microsatellite sequences, are desirable for improving breeding programs for A. falcata. Based on transferability and in situ localization, these microsatellite sequences can be applied as chromosome markers in the genus Aeschynomene and closely related genera. Here, we report the first microsatellite library developed for this genus; 11 microsatellites were characterized, with observed and expected heterozygosities ranging from 0.0000 to 0.7143 and from 0.1287 to 0.8360, respectively. Polymorphic information content varied from 0.1167 to 0.7786. The departure from Hardy-Weinberg equilibrium may have resulted from frequent autogamy, which is characteristic of A. falcata. Of the 11 microsatellites, 9 loci were cross-amplified in A. brevipes and A. paniculata and 7 in Dalbergia nigra and Machaerium vestitum. Five of these 7 cross-amplified microsatellites were applied as probes during the in situ hybridization assay and 2 showed clear signals on A. falcata chromosomes, ensuring their viability as chromosome markers.