Catálogo de publicaciones - libros

Visual attention plays a critical role in game playing. A better understanding of the allocation of visual attention can benefit the design of game scenarios. In this paper we propose to design games in different difficulty levels based on the estimation of attention. We use eye movement information in an analysis of attention. Eye fixation and pursuit conditions are considered separately.We find that the image complexity at eye fixation points and the relative position between pursuit direction and disturbance during pursuit eye movements are significant for attention allocation. This result is applied to the design of an interactive 2D game having two difficulty levels. Player response speeds and scores are compared for each difficulty level of the game.

This paper describes the DEEP project (Dialogs taking into account Experience, Emotions and Personality, adapted to computer games), which started in June 2006. The aim of the project is to provide generic solutions for the integration of autonomous Non Player Characters (NPCs) in next-generation adventure games. DEEP NPCs, equipped with a personality and a believable emotional engine, will use context-based information from the game environment and the player behavior to provide entertaining, rich and relevant dialogs.

We developed an interface system called “Marching Bear,” where the robot controller’s motions were reflected in the motions of certain characters appearing on a computer display. We then conducted a simple experiment to investigate the effectiveness of this interface system to see whether users felt that this interface system was enjoyable. We used a questionnaire and conducted an observation to determine whether users could direct the robot’s arms in such a way as to make the character walk. We also investigated the effectiveness of our interface system with two displays, one large, the other small. The results were that most participants felt this system was enjoyable and that they could direct the robot’s arms in the way needed to make the character walk. The larger display had a significantly stronger effect on the participants’ emotional aspects; they felt that the character had some emotions and that they could communicate with the character well. Therefore, the interface system, Marching Bear, was not only enjoyable for users because of the robot controls, but also this type of interface system may become a users’ companion or be perceived as an independent character.

A video game application was developed using SmartSkin, a body shape sensing device. The video game uses a table-sized SmartSkin that can recognize players’ arms on the tabletop. Sensor values are translated to a virtual potential field and the system calculates dynamics of game characters on the field.

At most four players can play the game, and the players control many independent game characters displayed on the table using their arms simultaneously.

Recently various types of robots are being studied and developed, which can be classified into two groups: humanoid type and animal types. Since each group has its own merits and demerits, a new type of robot is expected to emerge with greater strengths and fewer weaknesses. In this paper we propose a new type of robot called the “Centaur Robot” by merging the concepts of these two types of robots. This robot has a human-like upper body and a four-legged animal-like lower body. Due to this basic architecture, the robot has several merits, including human-like behaviors. It can also walk smoothly and stably even on non-smooth ground. We describe the basic concept of our centaur robot and then explain its hardware and software architectures as well as its merits.

Face recognition is important for many applications, including security check-up, judicial administration, visual monitoring and intelligent interaction. Current commercial and research systems use software implementation and require a dedicated computer for the image-processing task–a large, expensive, and complicated-to-use solution. In order to make face recognition ubiquitous, the system complexity, size, and price must be substantially reduced. This paper presents an ARM-based embedded system for face recognition. The float image-pretreatment algorithm was redesigned to enable highly image-pretreatment implementation for ARM9 microprocessor. The system uses a CMOS digital imaging sensor OV7640, a S3C2410A processor and the Linux Operation System for the image processing. A face recognition algorithm based on the HMM is presented. The software can be run in intelligent mobile telephone or PDA directly. This new design is suitable for face detection and recognition, thus making an important step towards low-cost and portable systems.

This paper presents a neuro-fuzzy classifer for activity recognition using one triaxial accelerometer and feature reduction approaches. We use a triaxial accelerometer to acquire subjects’ acceleration data and train the neuro-fuzzy classifier to distinguish different activities/movements. To construct the neuro-fuzzy classifier, a modified mapping-constrained agglomerative clustering algorithm is devised to reveal a compact data configuration from the acceleration data. In addition, we investigate two different feature reduction methods, a feature subset selection and linear discriminate analysis. These two methods are used to determine the significant feature subsets and retain the characteristics of the data distribution in the feature space for training the neuro-fuzzy classifier. Experimental results have successfully validated the effectiveness of the proposed classifier.

In this paper we present GFE – the Graphical FSM (Finite State Machine) Editor based on the Grafcet SFC (Sequential Function Chart) model. The GFE takes advantage of automated code generation and provides strong tools for complex control. At the same time it gives a high-level overview of the entire robotic control architecture. A complex control system may be designed, tested and deployed using visual approach. This is particularly useful for education where the students do not have to start always from scratch, or for young robot builders who are not as experienced in low-level programming. Once a control library is implemented for a particular robot, it may be reused and the robot may be programmed using solely graphical approach, because the most complicated part of controller design - the state machine - is automatically generated. This avoids typing errors and allows fast and simple redesign.

“Media Me” is a media interactive art work which comments on the bidirectional relationship between people and the media through the use of a realtime video mosaic. The elements of the video mosaic could be personal, cultural, historical, and educational. This research can be considered as a combination of creativity, art, and digital entertainment as well as an extension of personal media broadcasting. It comments on the growing trend of personal broadcasting and social media.

Background Subtraction methods are wildly used to detect moving object from static cameras. It has many applications such as traffic monitoring, human motion capture and recognition, and video surveillance. It is hard to propose a background model which works well under all different situations. Actually, there is no need to propose a pervasive model; it is a good model as long as it works well under a special situation. In this paper, a new method combining Gaussian Average and Frame Difference is proposed. Shadow suppression is not specifically dealt with, because it is considered to be part of the background, and can be subtracted by using an appropriate threshold. At last, a new method is raised to fill small gaps that the detected foreground or the moving objects may contain.