Exploring the World's Visual History

Thesis (Ph.D.)--University of Washington, 2016-08

Field Evaluation of a Competitive Lateral-flow Assay for Detection of Alternaria brassicae in Vegetable Brassica Crops

On-site detection of inoculum of polycyclic plant pathogens could potentially contribute to management of disease outbreaks. A 6-min, in-field competitive immunochromatographic lateral flow device (CLFD) assay was developed for detection of Alternaria brassicae (the cause of dark leaf spot in brassica crops) in air sampled above the crop canopy. Visual recording of the test result by eye provides a detection threshold of approximately 50 dark leaf spot conidia. Assessment using a portable reader improved test sensitivity. In combination with a weather-driven infection model, CLFD assays were evaluated as part of an in-field risk assessment to identify periods when brassica crops were at risk from A. brassicae infection. The weather-driven model overpredicted A. brassicae infection. An automated 7-day multivial cyclone air sampler combined with a daily in-field CLFD assay detected A. brassicae conidia air samples from above the crops. Integration of information from an in-field detection system (CLFD) with weather-driven mathematical models predicting pathogen infection have the potential for use within disease management systems.

Relocating the Frame: Object-Oriented (1.) and Locative Art (2.) Environments

The locative project is in a condition of emergence, an embryonic state in which everything is still up for grabs, a zone of consistency yet to emerge. As an emergent practice locative art, like locative media generally, it is simultaneously opening up new ways of engaging in the world and mapping its own domain. (Drew Hemment, 2004) Artists and scientists have always used whatever emerging technologies existed at their particular time throughout history to push the boundaries of their fields of practice. The use of new technologies or the notion of ‘new’ media is neither particularly new nor novel. Humans are adaptive, evolving and will continue to invent and explore technological innovation. This paper asks the following questions: what role does adaptive and/or intelligent art play in the future of public spaces, and how does this intervention alter the relationship between theory and practice? Does locative or installation-based art reach more people, and does ‘intelligent’ or ‘smart’ art have a larger role to play in the beginning of this century? The speakers will discuss their current collaborative prototype and within the presentation demonstrate how software art has the potential to activate public spaces, and therefore contribute to a change in spatial or locative awareness. It is argued that the role and perhaps even the representation of the audience/viewer is left altered through this intervention. 1. A form of electronic imagery created by a collection of mathematically defined lines and/or curves. 2. An experiential form of art which engages the viewer both from within a specific location and in response to their intentional or unintentional input.

Leveraging Multiple Features for Image Retrieval and Matching

The goal of image retrieval and matching is to find and locate object instances in images from a large-scale image database. While visual features are abundant, how to combine them to improve performance by individual features remains a challenging task. In this work, we focus on leveraging multiple features for accurate and efficient image retrieval and matching. We first propose two graph-based approaches to rerank initially retrieved images for generic image retrieval. In the graph, vertices are images while edges are similarities between image pairs. Our first approach employs a mixture Markov model based on a random walk model on multiple graphs to fuse graphs. We introduce a probabilistic model to compute the importance of each feature for graph fusion under a naive Bayesian formulation, which requires statistics of similarities from a manually labeled dataset containing irrelevant images. To reduce human labeling, we further propose a fully unsupervised reranking algorithm based on a submodular objective function that can be efficiently optimized by greedy algorithm. By maximizing an information gain term over the graph, our submodular function favors a subset of database images that are similar to query images and resemble each other. The function also exploits the rank relationships of images from multiple ranked lists obtained by different features. We then study a more well-defined application, person re-identification, where the database contains labeled images of human bodies captured by multiple cameras. Re-identifications from multiple cameras are regarded as related tasks to exploit shared information. We apply a novel multi-task learning algorithm using both low level features and attributes. A low rank attribute embedding is joint learned within the multi-task learning formulation to embed original binary attributes to a continuous attribute space, where incorrect and incomplete attributes are rectified and recovered. To locate objects in images, we design an object detector based on object proposals and deep convolutional neural networks (CNN) in view of the emergence of deep networks. We improve a Fast RCNN framework and investigate two new strategies to detect objects accurately and efficiently: scale-dependent pooling (SDP) and cascaded rejection classifiers (CRC). The SDP improves detection accuracy by exploiting appropriate convolutional features depending on the scale of input object proposals. The CRC effectively utilizes convolutional features and greatly eliminates negative proposals in a cascaded manner, while maintaining a high recall for true objects. The two strategies together improve the detection accuracy and reduce the computational cost.

RICH AND EFFICIENT VISUAL DATA REPRESENTATION

Increasing the size of training data in many computer vision tasks has shown to be very effective. Using large scale image datasets (e.g. ImageNet) with simple learning techniques (e.g. linear classifiers) one can achieve state-of-the-art performance in object recognition compared to sophisticated learning techniques on smaller image sets. Semantic search on visual data has become very popular. There are billions of images on the internet and the number is increasing every day. Dealing with large scale image sets is intense per se. They take a significant amount of memory that makes it impossible to process the images with complex algorithms on single CPU machines. Finding an efficient image representation can be a key to attack this problem. A representation being efficient is not enough for image understanding. It should be comprehensive and rich in carrying semantic information. In this proposal we develop an approach to computing binary codes that provide a rich and efficient image representation. We demonstrate several tasks in which binary features can be very effective. We show how binary features can speed up large scale image classification. We present learning techniques to learn the binary features from supervised image set (With different types of semantic supervision; class labels, textual descriptions). We propose several problems that are very important in finding and using efficient image representation.

Lie detection and children: Impact of the mode of presentation

Although a great deal of research has examined lie-detection among adults, little research has examined the differences between audio and visual mediums for deception among children. In the current study participants were presented (n = 42) with recordings of four children, each describing his/her experience of getting glasses. Two of the accounts were truthful, two were fabricated. Half of the participants were presented with videos, half were presented with audio-recordings. Following the presentation of each recording, participants responded to questions regarding the truthfulness of each child’s account. Results showed that when evaluating truth-tellers, participants’ lie-detection accuracy was significantly greater than chance. Within the video condition, non-parents were shown to report significantly more lie-related cues than parents. Several deception cues were shown to be related to lie-detection accuracy.

Development of paper-based color test-strip for drug detection in aquatic environment: Application to oxytetracycline

The wide use of antibiotics in aquaculture has led to the emergence of resistant microbial species. It should be avoided/minimized by controlling the amount of drug employed in fish farming. For this purpose, the present work proposes test-strip papers aiming at the detection/semi-quantitative determination of organic drugs by visual comparison of color changes, in a similar analytical procedure to that of pH monitoring by universal pH paper. This is done by establishing suitable chemical changes upon cellulose, attributing the paper the ability to react with the organic drug and to produce a color change. Quantitative data is also enabled by taking a picture and applying a suitable mathematical treatment to the color coordinates given by the HSL system used by windows. As proof of concept, this approach was applied to oxytetracycline (OXY), one of the antibiotics frequently used in aquaculture. A bottom-up modification of paper was established, starting by the reaction of the glucose moieties on the paper with 3-triethoxysilylpropylamine (APTES). The so-formed amine layer allowed binding to a metal ion by coordination chemistry, while the metal ion reacted after with the drug to produce a colored compound. The most suitable metals to carry out such modification were selected by bulk studies, and the several stages of the paper modification were optimized to produce an intense color change against the concentration of the drug. The paper strips were applied to the analysis of spiked environmental water, allowing a quantitative determination for OXY concentrations as low as 30 ng/mL. In general, this work provided a simple, method to screen and discriminate tetracycline drugs, in aquaculture, being a promising tool for local, quick and cheap monitoring of drugs.

Integrated visual perception architecture for robotic clothes perception and manipulation

This thesis proposes a generic visual perception architecture for robotic clothes perception and manipulation. This proposed architecture is fully integrated with a stereo vision system and a dual-arm robot and is able to perform a number of autonomous laundering tasks. Clothes perception and manipulation is a novel research topic in robotics and has experienced rapid development in recent years. Compared to the task of perceiving and manipulating rigid objects, clothes perception and manipulation poses a greater challenge. This can be attributed to two reasons: firstly, deformable clothing requires precise (high-acuity) visual perception and dexterous manipulation; secondly, as clothing approximates a non-rigid 2-manifold in 3-space, that can adopt a quasi-infinite configuration space, the potential variability in the appearance of clothing items makes them difficult to understand, identify uniquely, and interact with by machine. From an applications perspective, and as part of EU CloPeMa project, the integrated visual perception architecture refines a pre-existing clothing manipulation pipeline by completing pre-wash clothes (category) sorting (using single-shot or interactive perception for garment categorisation and manipulation) and post-wash dual-arm flattening. To the best of the author’s knowledge, as investigated in this thesis, the autonomous clothing perception and manipulation solutions presented here were first proposed and reported by the author. All of the reported robot demonstrations in this work follow a perception-manipulation method- ology where visual and tactile feedback (in the form of surface wrinkledness captured by the high accuracy depth sensor i.e. CloPeMa stereo head or the predictive confidence modelled by Gaussian Processing) serve as the halting criteria in the flattening and sorting tasks, respectively. From scientific perspective, the proposed visual perception architecture addresses the above challenges by parsing and grouping 3D clothing configurations hierarchically from low-level curvatures, through mid-level surface shape representations (providing topological descriptions and 3D texture representations), to high-level semantic structures and statistical descriptions. A range of visual features such as Shape Index, Surface Topologies Analysis and Local Binary Patterns have been adapted within this work to parse clothing surfaces and textures and several novel features have been devised, including B-Spline Patches with Locality-Constrained Linear coding, and Topology Spatial Distance to describe and quantify generic landmarks (wrinkles and folds). The essence of this proposed architecture comprises 3D generic surface parsing and interpretation, which is critical to underpinning a number of laundering tasks and has the potential to be extended to other rigid and non-rigid object perception and manipulation tasks. The experimental results presented in this thesis demonstrate that: firstly, the proposed grasp- ing approach achieves on-average 84.7% accuracy; secondly, the proposed flattening approach is able to flatten towels, t-shirts and pants (shorts) within 9 iterations on-average; thirdly, the proposed clothes recognition pipeline can recognise clothes categories from highly wrinkled configurations and advances the state-of-the-art by 36% in terms of classification accuracy, achieving an 83.2% true-positive classification rate when discriminating between five categories of clothes; finally the Gaussian Process based interactive perception approach exhibits a substantial improvement over single-shot perception. Accordingly, this thesis has advanced the state-of-the-art of robot clothes perception and manipulation.

Avaliação da memória em portugueses com idade superior a 50 anos: Validação e dados normativos para o CVLT-9 e para os subtestes reprodução visual e faces da WMS – III

Dissertação de Mestrado apresentada ao Instituto Superior de Psicologia Aplicada para obtenção de grau de Mestre na especialidade de Psicologia Clínica.

O museu virtual Google Art Project : um estudo de caso em contexto de ensino-aprendizagem da educação visual

A educação na arte e pela arte confere a todos os seus intervenientes a estimulação da sua criatividade e da sua consciência cultural, proporcionando meios para se exprimirem e participarem ativamente no mundo que nos rodeia. A integração das tecnologias de informação e comunicação no processo de ensino-aprendizagem veio alargar o papel que a arte pode desempenhar neste processo, promovendo novas formas de aprender, de ensinar e de pensar. Assim, a utilização de ambientes virtuais em contexto educativo tem revelado um enorme potencial, sobretudo ao nível da comunicação e da interação entre alunos e obras de arte. Neste sentido, considerou-se importante desenvolver um estudo de caso em contexto de sala de aula da Educação Visual, promovendo uma aprendizagem baseada na articulação entre a observação, interpretação e análise da obra de arte e o museu virtual. Assim o principal objetivo deste estudo foi avaliar as potencialidades do Google Art Project, enquanto objeto de aprendizagem, na promoção da aprendizagem na área da literacia em artes. Para além disso, procurámos ainda avaliar se a utilização de ferramentas multimédia como o referido Google Art Project e o Quadro Interativo, constituem fatores de motivação na aprendizagem da disciplina de Educação Visual. Do ponto de vista metodológico desenvolvemos uma estratégia baseada na investigação-ação. Procurámos, por um lado, descobrir e compreender o significado de uma realidade vivida por um grupo de alunos e, por outro lado, refletir sobre a prática educativa com o intuito de a melhorar e transformar. Este estudo envolveu cinco turmas do sexto ano do ensino público. Para a recolha de dados utilizámos técnicas baseadas na conversação e na observação, no questionário e nas notas de campo. Os resultados deste estudo revelam que as ferramentas tecnológicas utilizadas podem efetivamente contribuir para a promoção da aprendizagem dos alunos na área da Educação Visual, mais concretamente ao nível do domínio da literacia artística, da representação e da interpretação visual.

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.

Whole-body cortisol increases after direct and visual contact with a predator in zebrafish, Danio rerio

Ornamental fish may be severely affected by a stressful environment. Stressors impair the immune response, reproduction and growth rate; thus, the identification of possible stressors will aid to improve the overall quality of ornamental fish. The aim of this study was to determine whole-body cortisol of adult zebrafish, Danio rerio, following visual or direct contact with a predator species. Zebrafish were distributed in three groups: the first group, which consisted of zebrafish reared completely isolated of the predator, was considered the negative control; the second group, in which the predator, Parachromis managuensis was stocked together with zebrafish, was considered the positive control; the third group consisted of zebrafish stocked in a glass aquarium, with direct visual contact with the predator. The mean whole-body cortisol concentration in zebrafish from the negative control was 6.78 +/- 1.12 ng g(-1), a concentration statistically lower than that found in zebrafish having visual contact with the predator (9.26 +/- 0.88 ng g(-1)) which, in turn, was statistically lower than the mean whole-body cortisol of the positive control group (12.35 +/- 1.59 ng g(-1)). The higher whole-body cortisol concentration found in fish from the positive control can be attributed to the detection, by the zebrafish, of relevant risk situations that may involve a combination of chemical, olfactory and visual cues. One of the functions of elevated cortisol is to mobilize energy from body resources to cope with stress. The elevation of whole-body cortisol in fish subjected to visual contact with the predator involves only the visual cue in the recognition of predation risk. We hypothesized that the zebrafish could recognize predator characteristics in P managuensis, such as length, shape, color and behavior. Nonetheless, the elevation of whole-body cortisol in zebrafish suggested that the visual contact of the predator may elicit a stress response in prey fish. This assertion has a strong practical application concerning the species distribution in ornamental fish markets in which prey species should not be allowed to see predator species. Minimizing visual contact between prey and predator fish may improve the quality, viability and welfare of small fish in ornamental fish markets. (c) 2007 Elsevier B.V. All rights reserved.

Power spectrum model of visual masking: simulations and empirical data

In the study of the spatial characteristics of the visual channels, the power spectrum model of visual masking is one of the most widely used. When the task is to detect a signal masked by visual noise, this classical model assumes that the signal and the noise are previously processed by a bank of linear channels and that the power of the signal at threshold is proportional to the power of the noise passing through the visual channel that mediates detection. The model also assumes that this visual channel will have the highest ratio of signal power to noise power at its output. According to this, there are masking conditions where the highest signal-to-noise ratio (SNR) occurs in a channel centered in a spatial frequency different from the spatial frequency of the signal (off-frequency looking). Under these conditions the channel mediating detection could vary with the type of noise used in the masking experiment and this could affect the estimation of the shape and the bandwidth of the visual channels. It is generally believed that notched noise, white noise and double bandpass noise prevent off-frequency looking, and high-pass, low-pass and bandpass noises can promote it independently of the channel's shape. In this study, by means of a procedure that finds the channel that maximizes the SNR at its output, we performed numerical simulations using the power spectrum model to study the characteristics of masking caused by six types of one-dimensional noise (white, high-pass, low-pass, bandpass, notched, and double bandpass) for two types of channel's shape (symmetric and asymmetric). Our simulations confirm that (1) high-pass, low-pass, and bandpass noises do not prevent the off-frequency looking, (2) white noise satisfactorily prevents the off-frequency looking independently of the shape and bandwidth of the visual channel, and interestingly we proved for the first time that (3) notched and double bandpass noises prevent off-frequency looking only when the noise cutoffs around the spatial frequency of the signal match the shape of the visual channel (symmetric or asymmetric) involved in the detection. In order to test the explanatory power of the model with empirical data, we performed six visual masking experiments. We show that this model, with only two free parameters, fits the empirical masking data with high precision. Finally, we provide equations of the power spectrum model for six masking noises used in the simulations and in the experiments.

The neuroscience of cognitive enhancement : enhanced attention, working memory and visual information processing speed using 3D-MOT

Des interventions ciblant l’amélioration cognitive sont de plus en plus à l’intérêt dans nombreux domaines, y compris la neuropsychologie. Bien qu'il existe de nombreuses méthodes pour maximiser le potentiel cognitif de quelqu’un, ils sont rarement appuyé par la recherche scientifique. D’abord, ce mémoire examine brièvement l'état des interventions d'amélioration cognitives. Il décrit premièrement les faiblesses observées dans ces pratiques et par conséquent il établit un modèle standard contre lequel on pourrait et devrait évaluer les diverses techniques ciblant l'amélioration cognitive. Une étude de recherche est ensuite présenté qui considère un nouvel outil de l'amélioration cognitive, une tâche d’entrainement perceptivo-cognitive : 3-dimensional multiple object tracking (3D-MOT). Il examine les preuves actuelles pour le 3D-MOT auprès du modèle standard proposé. Les résultats de ce projet démontrent de l’augmentation dans les capacités d’attention, de mémoire de travail visuel et de vitesse de traitement d’information. Cette étude représente la première étape dans la démarche vers l’établissement du 3D-MOT comme un outil d’amélioration cognitive.

Code pattern analysis of object-oriented programming languages

Code patterns, including programming patterns and design patterns, are good references for programming language feature improvement and software re-engineering. However, to our knowledge, no existing research has attempted to detect code patterns based on code clone detection technology. In this study, we build upon the previous work and propose to detect and analyze code patterns from a collection of open source projects using NiPAT technology. Because design patterns are most closely associated with object-oriented languages, we choose Java and Python projects to conduct our study. The tool we use for detecting patterns is NiPAT, a pattern detecting tool originally developed for the TXL programming language based on the NiCad clone detector. We extend NiPAT for the Java and Python programming languages. Then, we try to identify all the patterns from the pattern report and classify them into several different categories. In the end of the study, we analyze all the patterns and compare the differences between Java and Python patterns.