No description available.

In model-based recognition, ad hoc techniques are used to decide if a match of data to model is correct. Generally an empirically determined threshold is placed on the fraction of model features that must be matched. We rigorously derive conditions under which to accept a match, relating the probability of a random match to the fraction of model features accounted for, as a function of the number of model features, number of image features and the sensor noise. We analyze some existing recognition systems and show that our method yields results comparable with experimental data.

While navigating in an environment, a vision system has to be able to recognize where it is and what the main objects in the scene are. In this paper we present a context-based vision system for place and object recognition. The goal is to identify familiar locations (e.g., office 610, conference room 941, Main Street), to categorize new environments (office, corridor, street) and to use that information to provide contextual priors for object recognition (e.g., table, chair, car, computer). We present a low-dimensional global image representation that provides relevant information for place recognition and categorization, and how such contextual information introduces strong priors that simplify object recognition. We have trained the system to recognize over 60 locations (indoors and outdoors) and to suggest the presence and locations of more than 20 different object types. The algorithm has been integrated into a mobile system that provides real-time feedback to the user.

The elderly population is estimated to increase worldwide. One of the major health determinants identified in this population are injuries where one of the most prevalent causes are falls. The overall aim of this thesis was to describe and explore visual impairment and falls of inpatients and independently living elderly in the community and how daily life activities were influenced by visual ability and risk of falling. Methods in the studies were a quantitative retrospective descriptive design for study I followed by two quantitative retrospective and explorative studies where in study II perceived vision related quality of life and in study III performance-based visual ability were investigated. Study IV was a qualitative explorative study using classic grounded theory. In study I all falls of inpatients at a medical clinic 65 years and older (n=68) were registered during one year. In study II and III a random sample (n=212) of independently living elderly between 70 and 85 years of age participated in both studies. In study IV seven women and six men between 73 and 85 years of age from the two previous studies and six visual instructors (n=19) participated. The data in study I was collected during 2004, study II and III between February 2009 to March 2010 and study IV December 2009 to January 2013. The results in study I showed that most falls in five hospital wards occurred at night and those most affected had an established visual impairment. Almost half the population in study II and III fell at least once. Perceived vision when performing daily life activities showed a positive association between visual impairment and falls in men but not in women (II). No associations were found between performance-based measured visual ability and falls (III). Visually impaired elderly did not consider risk of falling as a problem (􀀪􀀷). Their main concern is to remain themselves as who they used to be which is managed by self- preservation while maintaining their residual selves and resisting self decay. Maintaining residual self is done by living in the past mostly driven by inertia while resisting self decay is a proactive and purposeful driven strategy. It is a complex issue to do fall risk assessments and planning fall preventive action where the individual’s entire life situation has to be taken into consideration.

No description available.

Neural networks have become increasingly adopted in society over the last few years. As neural networks consume a lot of energy to train, reducing the energy consumption of these networks is desirable from an environmental perspective. Spiking neural network is a type of neural network inspired by the human brain which is significantly more energy efficient than traditional neural networks. However, there is little research about how the hyper parameters of these networks affect the relationship between accuracy and energy. The aim of this report is therefore to analyse this relationship. To do this, we measure the energy usage of training several different spiking network models. The results of this study shows that the choice of hyper-parameters in a neural network does affect the efficiency of the network. While correlation between any individual factors and energy consumption is inconclusive, this work could be used as a springboard for further research in this area. / Under de senaste åren har neuronnät blivit allt vanligare i samhället. Eftersom neuronnät förbrukar mycket energi för att träna dem är det önskvärt ur miljösynpunkt att minska energiförbrukningen för dessa nätverk. Spikande neuronnät är en typ av neuronnät inspirerade av den mänskliga hjärnan som är betydligt mer energieffektivt än traditionella neuronnät. Det finns dock lite forskning om hur hyperparametrarna i dessa nätverk påverkar sambandet mellan noggrannhet och energi. Syftet med denna rapport är därför att analysera detta samband. För att göra detta mäter vi energiförbrukningen vid träning av flera olika modeller av spikande neuronnät-modeller. Resultaten av denna studie visar att valet av hyperparametrar i ett neuronnät påverkar nätverkets effektivitet. Även om korrelationen mellan enskilda faktorer och energiförbrukning inte är entydig kan detta arbete användas som en startpunkt för ytterligare forskning inom detta område.

Traditional workflow systems have several drawbacks, e.g. in their inabilities to rapidly react to changes, to construct workflow automatically (or with user involvement) and to improve performance autonomously (or with user involvement) in an incremental manner according to specified goals. Overcoming these limitations would be highly beneficial for complex domains where such adversities are exhibited. Video processing is one such domain that increasingly requires attention as larger amounts of images and videos are becoming available to persons who are not technically adept in modelling the processes that are involved in constructing complex video processing workflows. Conventional video and image processing systems, on the other hand, are developed by programmers possessing image processing expertise. These systems are tailored to produce highly specialised hand-crafted solutions for very specific tasks, making them rigid and non-modular. The knowledge-based vision community have attempted to produce more modular solutions by incorporating ontologies. However, they have not been maximally utilised to encompass aspects such as application context descriptions (e.g. lighting and clearness effects) and qualitative measures. This thesis aims to tackle some of the research gaps yet to be addressed by the workflow and knowledge-based image processing communities by proposing a novel workflow composition and execution approach within an integrated framework. This framework distinguishes three levels of abstraction via the design, workflow and processing layers. The core technologies that drive the workflow composition mechanism are ontologies and planning. Video processing problems provide a fitting domain for investigating the effectiveness of this integratedmethod as tackling such problems have not been fully explored by the workflow, planning and ontological communities despite their combined beneficial traits to confront this known hard problem. In addition, the pervasiveness of video data has proliferated the need for more automated assistance for image processing-naive users, but no adequate support has been provided as of yet. A video and image processing ontology that comprises three sub-ontologies was constructed to capture the goals, video descriptions and capabilities (video and image processing tools). The sub-ontologies are used for representation and inference. In particular, they are used in conjunction with an enhanced Hierarchical Task Network (HTN) domain independent planner to help with performance-based selection of solution steps based on preconditions, effects and postconditions. The planner, in turn, makes use of process models contained in a process library when deliberating on the steps and then consults the capability ontology to retrieve a suitable tool at each step. Two key features of the planner are the ability to support workflow execution (interleaves planning with execution) and can perform in automatic or semi-automatic (interactive) mode. The first feature is highly desirable for video processing problems because execution of image processing steps yield visual results that are intuitive and verifiable by the human user, as automatic validation is non trivial. In the semiautomaticmode, the planner is interactive and prompts the user tomake a tool selection when there is more than one tool available to perform a task. The user makes the tool selection based on the recommended descriptions provided by the workflow system. Once planning is complete, the result of applying the tool of their choice is presented to the user textually and visually for verification. This plays a pivotal role in providing the user with control and the ability to make informed decisions. Hence, the planner extends the capabilities of typical planners by guiding the user to construct more optimal solutions. Video processing problems can also be solved in more modular, reusable and adaptable ways as compared to conventional image processing systems. The integrated approach was evaluated on a test set consisting of videos originating from open sea environment of varying quality. Experiments to evaluate the efficiency, adaptability to user’s changing needs and user learnability of this approach were conducted on users who did not possess image processing expertise. The findings indicate that using this integrated workflow composition and execution method: 1) provides a speed up of over 90% in execution time for video classification tasks using full automatic processing compared to manual methods without loss of accuracy; 2) is more flexible and adaptable in response to changes in user requests (be it in the task, constraints to the task or descriptions of the video) than modifying existing image processing programs when the domain descriptions are altered; 3) assists the user in selecting optimal solutions by providing recommended descriptions.

Made available in DSpace on 2016-08-02T21:42:57Z (GMT). No. of bitstreams: 1 Claudia Santos Rezende.pdf: 1260219 bytes, checksum: c41d4540b825bd81735751d1dbe1d96d (MD5) Previous issue date: 2009-11-23 / This study seeks to discover which factors can explain the performance of companies in the airline industry, as well as the possible causes for differential performance in enterprises of this sector, since it is based the theory of resource-based view (RBV) and institutional theory , these theories related to the field of business strategy. To achieve this goal, we draw a history of commercial aviation in Brazil since its origin up to the year 2007 we will conduct a review of literature on the RBV, Institutional theory, competitive advantage and organizational performance. We work with secondary data supplied by ANAC, to period 1995 a 2007, which must be examined through a multilevel analysis, considering the factor analysis firm.(AU) / O presente trabalho busca descobrir quais fatores são capazes de explicar o desempenho das empresas do setor aéreo, bem como as possíveis causas para a diferenciação de desempenho nas empresas deste setor, tendo por fundamento a teoria da visão baseada em recursos (RBV) e a teoria Institucional, teorias estas relacionadas ao campo da estratégia empresarial. Para atingir esse objetivo, vamos traçar um histórico do setor de aviação comercial brasileira desde os seus primórdios até o ano de 2007, realizaremos uma revisão de literatura sobre a RBV, teoria Institucional, vantagem competitiva e desempenho organizacional. Trabalhamos com dados secundários fornecidos pela ANAC, referentes ao período de 1995 a 2007, os quais devem ser analisados à luz de uma análise multinível, considerando o fator firma na análise.(AU)

Event-based vision offers high dynamic range, time resolution and lower latency than conventional frame-based vision sensors. These attributes are useful in varying light condition and fast motion. However, there are no neural network models and training protocols optimized for object detection with event data, and conventional artificial neural networks for frame-based data are not directly suitable for that task. Spiking neural networks are natural candidates but further work is required to develop an efficient object detection architecture and end-to-end training protocol. For example, object detection in varying light conditions is identified as a challenging problem for the automation of construction equipment such as earth-moving machines, aiming to increase the safety of operators and make repetitive processes less tedious. This work focuses on the development and evaluation of a neural network for object detection with data from an event-based sensor. Furthermore, the strengths and weaknesses of an event-based vision solution are discussed in relation to the known challenges described in former works on automation of earth-moving machines. A solution for object detection with event data is implemented as a modified YOLOv3 network with spiking convolutional layers trained with a backpropagation algorithm adapted for spiking neural networks. The performance is evaluated on the N-Caltech101 dataset with classes for airplanes and motorbikes, resulting in a mAP of 95.8% for the combined network and 98.8% for the original YOLOv3 network with the same architecture. The solution is investigated as a proof of concept and suggestions for further work is described based on a recurrent spiking neural network.

<div>Event-Based cameras, also known as neuromophic cameras or dynamic vision sensors, are an imaging modality that attempt to mimic human eyes by asynchronously measuring contrast over time. If the contrast changes sufficiently then a 1-bit event is output, indicating whether the contrast has gone up or down. This stream of events is sparse, and its asynchronous nature allows the pixels to have a high dynamic range and high temporal resolution. However, these events do not encode the intensity of the scene, resulting in an inverse problem to estimate intensity images from the event stream. Hybrid event-based cameras, such as the DAVIS camera, provide a reference intensity image that can be leveraged when estimating the intensity at each pixel during an event. Normally, inverse problems are solved by formulating a forward and prior model and minimizing the associated cost, however, for this problem, the Plug and Play (P&P) algorithm is used to solve the inverse problem. In this case, P&P replaces the prior model subproblem with a denoiser, making the algorithm modular, easier to implement. We propose an idealized forward model that assumes the contrast steps measured by the DAVIS camera are uniform in size to simplify the problem. We show that the algorithm can swiftly reconstruct the scene intensity at a user-specified frame rate, depending on the chosen denoiser’s computational complexity and the selected frame rate.</div>