Marcos Cordeiro d'Ornellas

Automatic Dynamic Task Distribution between CPU and GPU for Real-Time Systems

The increase of computational power of programmable GPU (graphics processing unit) brings new concepts for using these devices for generic processing. Hence, with the use of the CPU and the GPU for data processing come new ideas that deals with distribution of tasks among CPU and GPU, such as automatic distribution. The importance of the automatic distribution of tasks between CPU and GPU lies in three facts. First, automatic task distribution enables the applications to use the best of both processors. Second, the developer does not have to decide which processor will do the work, allowing the automatic task distribution system to choose the best option for the moment. And third, sometimes, the application can be slowed down by other processes if the CPU or GPU is already overloaded. Based on these facts, this paper presents new schemes for efficient automatic task distribution between CPU and GPU. This paper also includes tests and results of implementing those schemes with a test case and with a real-time system.

A Survey of Procedural Content Generation Techniques Suitable to Game Development

The development of a complex game is a time consuming task that requires a significant amount of content generation, including terrains, objects, characters, etc that requires a lot of effort from the a designing team. The quality of such content impacts the project costs and budget. One of the biggest challenges concerning the content is how to improve its details and at the same time lower the creation costs. In this context procedural content generation techniques can help to reduce the costs associated with content creation. This paper presents a survey of classical and modern techniques focused on procedural content generation suitable for game development. They can be used to produce terrains, coastlines, rivers, roads and cities. All techniques are classified as assisted (require human intervention/guidance in order to produce results) or non-assisted (require few or no human intervention/guidance to produce the desired results).

Virtual cinematography director for interactive storytelling

This paper proposes an intelligent cinematography director for plot-based storytelling systems. The role of the director is to select in real-time the camera shots that best fit for the scenes and present the content in an interesting and coherent manner. Directors knowledge is represented with a collection of support vector machines (SVM) trained to solve cinematography problems of shot selection. With this work we introduce the use of support vector machines, applied as an artificial intelligence method, in a storytelling director. This approach also can be extended and applied in games and other digital entertainment applications.

Thoroughly Approach to Upper Limb Rehabilitation Using Serious Games for Intensive Group Physical Therapy or Individual Biofeedback Training

Several studies have shown that game-based rehabilitation is a viable option to improve the treatment of patients with physical disabilities. Even though many games are built focusing on rehabilitation, the majority does not present a broad study about the right approach on the many types of existing conditions and also the physiological and medical implications of this games in the patients treatments. The actual level of integration between Unity and the body-tracking device supported by Microsoft Kinect, has provided a solid tool to build a serious game focusing the rehabilitation paradigm. This work presents the steps and foundation regarding the subject to build a serious game with focus in rehabilitation of the upper limb, more specifically of those patients with hemiplegia or hemiparesis, with the use of biofeedback analysis to evaluate the patients development. It also shows the possibility of the multiplayer perspective into the rehabilitation treatment to help with the learning phase and bring motivation to the gaming experience.

Charack: Tool for Real-Time Generation of Pseudo-Infinite Virtual Worlds for 3D Games

In MMO games the player’s experience is mainly influenced by the size and details of the virtual world. Technically the bigger the world is, the bigger is the time the player takes to explore all the places. This work presents a tool (named Charack) able to generate pseudo-infinite virtual worlds with different types of terrains. Using a combination of algorithms and content management methods, Charack is able to create beaches, islands, bays and coastlines that imitates real world landscapes. The tool clearly distinguish the generation of each type of content. The contribution of the tool is the ability to generate arbitrarily large pieces of land (or landscape) focusing on detailed coastline generation, by means of using procedural algorithms.

Support Vector Machines for Cinematography Real-Time Camera Control in Storytelling Environments

This paper proposes an intelligent cinematography director for camera control in plot-based storytelling systems. The role of the director is to select in real-time the camera shots that best fit for the scenes and present the content in an interesting and coherent manner. Directors knowledge is represented with a collection of support vector machines (SVM) trained to solve cinematography problems of shot selection. With this work we introduce the use of support vector machines, applied as an artificial intelligence method, in a storytelling director. This approach also can be extended and applied in games and other digital entertainment applications.

Applying Digital Rights Management to Complex Content Management Systems

Content rights are considered one of the most imperative elements of complexity in content processes. These processes include the construction of the content, its selection for commercial publication, its production, diffusion, and marketing, as well as its eventual use. In addition, the processes of tracking digital rights and managing access to content based rights information are gradually more necessary. The most powerful technique to control and track such access is to combine forms and meanings to achieve persistent protection. In this paper, after a quick explanation of content management systems and digital rights management, we address some legal and market issues that have led to complex content processes and systems. We also discuss some ways in which retailers of content management systems may incorporate digital rights into their products by means of rights expression languages.

A Deformable Contour Based Approach for Hand Image Segmentation

In this paper we address the issue of hand contour segmentation from digital images using deformable contour models (snakes). We present a novel variation of the traditional snake solution, where additional nodes are inserted and redundant nodes are deleted to better describe the complexity of the extracted line. Candidate locations for node insertion and deletion are based on an analysis of the energy terms in the snake solution. This allows us to use more closely spaced nodes along the high curvature segments of a hand outline. This dynamic manipulation of the node number and spacing within a single snake allows us to better capture the geometry of the hand and accommodate its radiometric behavior. Here we present our approach, and some experimental results demonstrating its performance as a tool for hand contour segmentation in biometrics, medical imaging, and pattern recognition.

Knowledge representation for lung cancer patients' prognosis

The gradual increase of cancer cases worldwide has been posing a need on the use of computing resources to accurately retrieve the information recorded in databases. One can highlight the retrieved information importance from a specialist in order to better evaluate pathological response and predict the cancer patient prognosis. This paper presents a way to represent knowledge of cancer registries with emphasis on prognosis. It makes use data mining techniques to find patterns in data stored for patients lifetime in similar situations. The work is focused on the generation of association rules to find patterns on these registries in order to measure the patient prognosis and drive healthcare experts conclusions. A validation against international oncology organizations and health publications was also made to ensure data and work reliability.