In this paper, we propose a relocalization method for keyframe-based SLAM that enables real-time and accurate recovery from tracking failures. To realize an AR-based application in a real world situation, not only accurate camera tracking but also fast and accurate relocalization from tracking failure is required. The previous keyframe-based relocalization methods have some drawbacks with regard to speed and accuracy. The proposed relocalization method selects two algorithms adaptively depending on the relative camera pose between a current frame and a target keyframe. In addition, it estimates a degree of false matches to speed up RANSAC-based model estimation. We present effectiveness of our method by an evaluation using public tracking dataset.

Kinect Fusion is able to build a 3D reconstruction in real time and provide a 3D model. Kinect Fusion uses Iterative Closest Point (ICP) algorithm for point cloud alignment from the each camera frame and estimates each camera pose. However, ICP algorithm has its limits and the camera poses lack in accuracy. We propose an alignment method which is not only based on point cloud but also line segments. This method significantly improve the camera pose accuracy obtained from Kinect Fusion and creates better 3D model. In this method, we use line segment matching by Line-based Eight-directional Histogram Feature(LEHF). We also propose an improved version of LEHF for this alignment method. The basic idea is to get a set of 2D-3D line segment correspondences between 2D line segments on camera images and 3D line segments of 3D line segment based models, to solve the PnL problem and to recompute the camera pose. The experimental result that the camera pose estimated by our method is more accurate than the original one obtained from Kinect Fusion.

This demonstration shows novel interaction between mobile devices and their nearby devices using digital images on a mobile display. The interaction needs neither special hardware for communication, nor additional software for existing mobile devices. In the interaction, users of mobile devices can easily interact with nearby devices by three procedures: 1) selecting an image, 2) displaying an image in full-screen mode, or 3) holding the display over a camera connected to the device. The key technology of the interaction is FPcode (Fine Picture code) which is a kind of steganography and can be invisibly embedded in printed images. To enable FPcode to be applied to images on mobile displays, we have developed a camera control method for reducing the influence of moire stripes on the display and variations in display brightness. In the demonstration, we show an application using FPcode on a mobile display.