Common-sense reasoning for human action recognition

This paper presents a novel method that leverages reasoning capabilities in a computer vision system dedicated to human action recognition. The proposed methodology is decomposed into two stages. First, a machine learning based algorithm - known as bag of words - gives a first estimate of action classification from video sequences, by performing an image feature analysis. Those results are afterward passed to a common-sense reasoning system, which analyses, selects and corrects the initial estimation yielded by the machine learning algorithm. This second stage resorts to the knowledge implicit in the rationality that motivates human behaviour. Experiments are performed in realistic conditions, where poor recognition rates by the machine learning techniques are significantly improved by the second stage in which common-sense knowledge and reasoning capabilities have been leveraged. This demonstrates the value of integrating common-sense capabilities into a computer vision pipeline. © 2012 Elsevier B.V. All rights reserved.

Real-time GPU color-based segmentation of football players

In this paper, we propose a multi-camera application capable of processing high resolution images and extracting features based on colors patterns over graphic processing units (GPU). The goal is to work in real time under the uncontrolled environment of a sport event like a football match. Since football players are composed for diverse and complex color patterns, a Gaussian Mixture Models (GMM) is applied as segmentation paradigm, in order to analyze sport live images and video. Optimization techniques have also been applied over the C++ implementation using profiling tools focused on high performance. Time consuming tasks were implemented over NVIDIA's CUDA platform, and later restructured and enhanced, speeding up the whole process significantly. Our resulting code is around 4-11 times faster on a low cost GPU than a highly optimized C++ version on a central processing unit (CPU) over the same data. Real time has been obtained processing until 64 frames per second. An important conclusion derived from our study is the scalability of the application to the number of cores on the GPU. © 2011 Springer-Verlag.

Examining the presence of Arching-Action in Edge Stiffened Bridge Deck Cantilever Overhangs Subjected to a Wheel Load

Engineers have proposed the idea that there may be some arching action present in bridge deck cantilever overhangs stiffened along their longitudinal free edge, via a traffic barrier, subjected to a wheel load. This paper includes the details of a full-scale corrosion-free bridge deck with cantilever overhangs stiffened along their longitudinal free edge by a traffic barrier wall that has been constructed and tested under static and fatigue wheel loads at the University of Manitoba. It also reviews experimental test results and postulates various discussions that suggest the presence of arching-action in cantilever slab overhangs. Test results indicated static ultimate load capacities significantly greater than the ultimate capacity if the mode of failure and behavior of the cantilever overhang was completely flexural. These early results confirm and indicate the presence of arching-action resulting in a significant break-through in cantilever behavior when subjected to a wheel load. The theory to account for this arching-action is not yet developed and further research should be conducted.

Mean shift based gradient vector flow for image segmentation

In recent years, gradient vector flow (GVF) based algorithms have been successfully used to segment a variety of 2-D and 3-D imagery. However, due to the compromise of internal and external energy forces within the resulting partial differential equations, these methods may lead to biased segmentation results. In this paper, we propose MSGVF, a mean shift based GVF segmentation algorithm that can successfully locate the correct borders. MSGVF is developed so that when the contour reaches equilibrium, the various forces resulting from the different energy terms are balanced. In addition, the smoothness constraint of image pixels is kept so that over- or under-segmentation can be reduced. Experimental results on publicly accessible datasets of dermoscopic and optic disc images demonstrate that the proposed method effectively detects the borders of the objects of interest.

A service evaluation of the role of complementary therapies for patients with cancer - By Action Cancer

Advances in the diagnosis and treatment of cancer has resulted in longer survival, meaning that cancer patients are now living with what may be termed a chronic type condition. As a result of this the needs of patients living with a cancer diagnosis has changed, placing a greater emphasis on survivorship which in turn has an effect on quality of life and sleep patterns. Evidence suggests that counselling and complementary therapies have a positive impact not only on the cancer patient’s quality of life but also on family members and friends.

The aim of this study was to determine if there is an improvement in client’s quality of life and sleep patterns after availing of counselling and complementary therapy services as offered by a local cancer charity.

All clients availing of the counselling or complementary therapies offered by the charity were invited to participate in a Service Evaluation. The regulations relating to research involving human participants as outlined by the “Research Governance Framework” at a local university were also adhered to. A seven piece questionnaire was used for evaluation of services.

Access to anonymous data from the cancer patients, their families and carers was granted by the Research and Development Officer within Action Cancer.
A total of 507 participants completed the initial questionnaires immediately before therapy and 255 participants completed the questionnaires immediately after therapy, the total matched sample is 230. When considering counselling and complementary therapies together (therapeutic services) there were statistically significant results indicating improved quality of life and sleep patterns between the two sets of data. However this was not the trend when considering counselling and complementary therapies alone.

While some of the findings closely reflect the literature and on the whole supports the use of therapeutic services in having a positive effect on cancer patient’s quality of life and sleep patterns.

Marie Sallé and the development of the ballet en action

Sallé's ballets en action are evaluated in terms of Enlightenment dramaturgical principles, and her role in shaping this aesthetic is mooted.

Arching action strength enhancement in laterally-restrained slab strips

The behaviour and ultimate load capacity of laterally-restrained reinforced concrete slabs can be considerably enhanced by the development of arching or compressive membrane action. This paper presents a simple method for predicting the enhanced ultimate load capacity of laterally-restrained slab strips. The method is based on deformation theory and utilizes an elastic-plastic stress-strain criterion for concrete. The loads carried by bending and arching action are calculated separately and then added to give the total ultimate load capacity. A simple equivalent strip approach, based on a three-hinged arch analogy, allows for the degree of lateral restraint. The method of prediction has been validated by correlation with a wide range of test results from various sources.