This unique book explores the important issues in studying for active visual perception. The book’s eleven chapters draw on recent important work in robot vision over ten years, particularly in the use of new concepts. Implementation examples are provided with theoretical methods for testing in a real robot system. With these optimal sensor planning strategies, this book will give the robot vision system the adaptability needed in many practical applications.

This unique book explores the important issues in studying for active visual perception. The book’s eleven chapters draw on recent important work in robot vision over ten years, particularly in the use of new concepts. Implementation examples are provided with theoretical methods for testing in a real robot system. With these optimal sensor planning strategies, this book will give the robot vision system the adaptability needed in many practical applications.

This book constitutes the thoroughly refereed proceedings of the 14th International Conference on Advanced Concepts for Intelligent Vision Systems, ACIVS 2012, held in Brno, Czech Republic, in September 2012. The 46 revised full papers were carefully selected from 81 submissions and deal with image analysis and computer vision with a focus on detection, recognition, tracking and identification.

This book constitutes the refereed proceedings of the 16th Scandinavian Conference on Image Analysis, SCIA 2011, held in Ystad, Sweden, in May 2011. The 74 revised full papers presented were carefully reviewed and selected from 140 submissions. The papers are organized in topical sections on multiple view geometry; segmentation; image analysis; categorization and classification; structure from motion and SLAM; medical and biomedical applications; 3D shape; medical imaging.

Identifying Emerging Trends in Technological Innovation Doctoral programs in science and engineering are important sources of innovative ideas and techniques that might lead to new products and technological innovation. Certainly most PhD students are not experienced researchers and are in the process of learning how to do research. Nevertheless, a number of empiric studies also show that a high number of technological innovation ideas are produced in the early careers of researchers. The combination of the eagerness to try new approaches and directions of young doctoral students with the experience and broad knowledge of their supervisors is likely to result in an important pool of innovation potential. The DoCEIS doctoral conference on Computing, Electrical and Industrial En- neering aims at creating a space for sharing and discussing ideas and results from doctoral research in these inter-related areas of engineering. Innovative ideas and hypotheses can be better enhanced when presented and discussed in an encouraging and open environment. DoCEIS aims to provide such an environment, releasing PhD students from the pressure of presenting their propositions in more formal contexts.

The two-volume set LNAI 7094 and LNAI 7095 constitutes the refereed proceedings of the 10th Mexican International Conference on Artificial Intelligence, MICAI 2011, held in Puebla, Mexico, in November/December 2011. The 96 revised papers presented were carefully reviewed and selected from numerous submissions. The first volume includes 50 papers representing the current main topics of interest for the AI community and their applications. The papers are organized in the following topical sections: automated reasoning and multi-agent systems; problem solving and machine learning; natural language processing; robotics, planning and scheduling; and medical applications of artificial intelligence.

This book focuses on enabling mobile robots to recognize scenes in indoor environments, in order to allow them to determine which actions are appropriate at which points in time. In concrete terms, future robots will have to solve the classification problem represented by scene recognition sufficiently well for them to act independently in human-centered environments. To achieve accurate yet versatile indoor scene recognition, the book presents a hierarchical data structure for scenes – the Implicit Shape Model trees. Further, it also provides training and recognition algorithms for these trees. In general, entire indoor scenes cannot be perceived from a single point of view. To address this problem the authors introduce Active Scene Recognition (ASR), a concept that embeds canonical scene recognition in a decision-making system that selects camera views for a mobile robot to drive to so that it can find objects not yet localized. The authors formalize the automatic selection of camera views as a Next-Best-View (NBV) problem to which they contribute an algorithmic solution, which focuses on realistic problem modeling while maintaining its computational efficiency. Lastly, the book introduces a method for predicting the poses of objects to be searched, establishing the otherwise missing link between scene recognition and NBV estimation.