Search

We present a new human navigation system on smartphones for indoor environments. The conventional systems have required specific positioning infrastructures installed in buildings. In contrast, the proposed system is not to need such requirements because it can determine the position of a user by image matching to process the images from a smartphone camera indoors like a certain corridor. Although a number of personal positioning methods based on image processing have been proposed, it has been difficult in processing cost to apply them just like that to the proposed system. From this point of view, we have focused on the view-based navigation which has been developed as an indoor positioning method for robots due to its simple algorithm by only one monocular camera. By devising the techniques for applying this view-based navigation to a smartphone, we can visually provide the user having a smartphone the positional and directional information to a destination. This paper describes the algorithm of the view-based navigation speeded up for smartphones and shows experimental results for human navigation performed with usually walking in an indoor corridor. [ABSTRACT FROM PUBLISHER]

We propose a learning support system with a robot for asynchronous learning. The proposed system consists of a teacher, a user, a robot, a personal computer, an educational material, and a web camera. In asynchronous learning, the timing to provide the supports such as hints and answers in learning is one of important factors. Here, we endowed a robot with this roll on the timing estimated by extracting the features of usual facial expressions or behaviors of a user in an image captured by a web camera. Thus, we can expect that the robot may give a user learning supports in real time. In fact, we developed the base system that a robot provides hints in the timing estimated by extracting the human general feature tilting own head when we don't understand something. We attempted to evaluate the usefulness for the base system through the experiments of English words learning and some questionnaires for college students. In these experiments, we used a communication robot, PaPeRo, for confirming the counteraction and effect of users. This paper is discussed on the experimental results of the questionnaires and the possibility that user's motivation can be improved by the affinity of the robot in the system. [ABSTRACT FROM PUBLISHER]

This paper describes an improved template matching for a distance measurement system based on image sensors using a target. Authors have developed the distance measurement system that consists of two movable image sensors for automatic berthing of ships. The measurement system measures a distance by detecting and tracking the target. We aim at applying the distance measurement system for automatic relative positioning system between a ship and a FPSO. In this application, the shape of the target captured in images is deformed by their relative positions and attitudes and then measurements error is increased due to the target deformation. For solving the deformation, we propose an improved template matching robust to target deformation. Improved template matching is able to detect the deformed target with template database which is created by image conversion with perspective projection of a reference template. By using improved template matching, the distance measurement error is decreased. From the experimental results performed in miniature and indoor environments, we confirmed that the measurement error of the relative distance is decreased by using the database. [ABSTRACT FROM PUBLISHER]