This book focuses on video-based, corneal-reflection eye trackers - the most widely available and affordable type of system, and takes a look at a number of interesting and challenging applications in human factors, collaborative systems, virtual reality, marketing and advertising. The third edition has been extensively revised and extended, and includes new chapters on calibration accuracy, precision and correction; advanced eye movement analysis; binocular eye movement analysis; practical gaze analytics; design; GIS. Opening with useful background information, including an introduction to the human visual system and key issues in visual perception and eye movement, the author then surveys eye-tracking devices and provides a detailed introduction to the technical requirements necessary for installing a system and developing an application program.
Sensor Data Fusion is the process of combining incomplete and imperfect pieces of mutually complementary sensor information in such a way that a better understanding of an underlying real-world phenomenon is achieved. Typically, this insight is either unobtainable otherwise or a fusion result exceeds what can be produced from a single sensor output in accuracy, reliability, or cost. This book provides an introduction Sensor Data Fusion, as an information technology as well as a branch of engineering science and informatics. Part I presents a coherent methodological framework, thus providing the prerequisites for discussing selected applications in Part II of the book. The presentation mirrors the author´s views on the subject and emphasizes his own contributions to the development of particular aspects. With some delay, Sensor Data Fusion is likely to develop along lines similar to the evolution of another modern key technology whose origin is in the military domain, the Internet. It is the author´s firm conviction that until now, scientists and engineers have only scratched the surface of the vast range of opportunities for research, engineering, and product development that still waits to be explored: the Internet of the Sensors.
An aerial robot is a system capable of sustained flight with no direct human control and able to perform a specific task. A lighter than air robot is an aerial robot that relies on the static lift to balance its own weight. It can also be defined as a lighter than air unmanned aerial vehicle or an unmanned airship with sufficient autonomy. Lighter than air systems are particularly appealing since the energy to keep them airborne is small. They are increasingly considered for various tasks such as monitoring, surveillance, advertising, freight carrier, transportation. This book familiarizes readers with a hierarchical decoupled planning and control strategy that has been proven efficient through research. It is made up of a hierarchy of modules with well defined functions operating at a variety of rates, linked together from top to bottom. The outer loop, closed periodically, consists of a discrete search that produces a set of waypoints leading to the goal while avoiding obstacles and weighed regions. The second level smoothes this set so that the generated paths are feasible given the vehicle´s velocity and accelerations limits. The third level generates flyable, timed trajectories and the last one is the tracking controller that attempts to minimize the error between the robot measured trajectory and the reference trajectory. This hierarchy is reflected in the structure and content of the book. Topics treated are: Modelling, Flight Planning, Trajectory Design and Control. Finally, some actual projects are described in the appendix. This volume will prove useful for researchers and practitioners working in Robotics and Automation, Aerospace Technology, Control and Artificial Intelligence.