Natural Interaction

Due to the rapid increase in video capture technology, more and more tourist videos are captured every day, creating a challenge for organization and association with metadata. In this paper, we present a novel system for annotating and navigating tourist videos. Placing annotations in a video is difficult because of the need to track the movement of the camera. Navigation of a regular video is also challenging due to the sequential nature of the media. To overcome these challenges, we introduce a system for registering videos to geo-referenced 3D models and analyzing the video contents. We also introduce a novel scheduling algorithm for showing annotations in video. We show results in automatically annotated videos and in a map-based application for browsing videos. Our user study indicates the system is very useful.

In this paper we will present the concept of a system that allows for an evolutionary introduction of depth perception into the existing 2D digital TV framework. The work is part of the European Information Society Technologies (IST) project “Advanced Three-Dimensional Television System Technologies”(ATTEST), an activity where industries, research centers and universities have joined forces to design a backwardscompatible, flexible and modular broadcast 3D-TV system, where all parts of the 3D processing chain ...

We describe the goals of the ATTEST project, which started in March 2002 as part of the Information Society Technologies (IST) programme, sponsored by the European Commission. In the 2-year project, several industrial and academic partners cooperate towards a flexible, 2D-compatible and commercially feasible 3D-TV system-for broadcast environments. An entire 3D-video chain will be developed. We discuss the goals for content creation, coding, transmission, display and the central role that human 3D perception ...

We investigate two interactive techniques for registering an image to 3D digital terrain and building models. Registering an image enables a variety of applications, including slideshows with context, automatic annotation, and photo enhancement. To perform the registration, we investigate two modes of interaction. In the overlay interface, an image is displayed over a 3D view and a user manually aligns 3D points to points in the image. In the split interface, the image and the 3D view are displayed side-by-side and the user indicates matching points across the two views. Our user study suggests that the overlay interface is more engaging than split, but is less accurate in registration. We then show several applications that make use of the registration data. Figure 1: A frame from a 3D slideshow. Notice how the landscape smoothly transitions between the digital terrain and the photo.

This paper investigates two methods of improving the user experience of camera-based interaction. First, problems that arise when avatars are designed to mimic a user's physical actions are presented. Second, a solution is proposed: adding a layer of separation between user and avatar while retaining intuitive user control. Two methods are proposed for this separation: spatially and temporally. Implementations of these methods are then presented in the context of a simple game and evaluate their effect on performance and satisfaction. Results of a human subject experiment are presented, showing that reducing the amount of user control can maintain, and even improve, user satisfaction if the design of such a reduction is appropriate. This is followed by a discussion of how the findings inform camera-based game design.

We present an automatic method to recover high-resolution texture over an object by mapping detailed photographs onto its surface. Such high-resolution detail often reveals inaccuracies in geometry and registration, as well as lighting variations and surface reflections. Simple image projection results in visible seams on the surface. We minimize such seams using a global optimization that assigns compatible texture to adjacent triangles. The key idea is to search not only combinatorially over the source images, but also over a set of local image transformations that compensate for geometric misalignment. This broad search space is traversed using a discrete labeling algorithm, aided by a coarse-to-fine strategy. Our approach significantly improves resilience to acquisition errors, thereby allowing simple and easy creation of textured models for use in computer graphics.

Video stabilization is an important video enhancement technology which aims at removing annoying shaky motion from videos. We propose a practical and robust approach of video stabilization that produces full-frame stabilized videos with good visual quality. While most previous methods end up with producing smaller size stabilized videos, our completion method can produce fullframe videos by naturally filling in missing image parts by locally aligning image data of neighboring frames. To achieve this, motion inpainting is proposed to enforce spatial and temporal consistency of the completion in both static and dynamic image areas. In addition, image quality in the stabilized video is enhanced with a new practical deblurring algorithm. Instead of estimating point spread functions, our method transfers and interpolates sharper image pixels of neighboring frames to increase the sharpness of the frame. The proposed video completion and deblurring methods enabled us to develop a complete video stabilizer which can naturally keep the original image quality in the stabilized videos. The effectiveness of our method is confirmed by extensive experiments over a wide variety of videos.

Panoramic mapping multiple imag age. One challenge to are often not stitched troublesome for objec wires, crossing multip power lines, are comm tration due to their sm environments often inc automatic scheme for panoramic images. Ou municipal imagery wh perception of the imag

While onboard navigation systems are gaining in importance, maps are still the medium of choice for laying out a route to a destination and for way finding. However, even with a map, one is almost always more comfortable navigating a route the second time due to the visual memory of the route. To make the first time navigating a route feel more familiar, we present a system that integrates a map with a video automatically constructed from panoramic imagery captured at close intervals along the route. The routing information is used to create a variable speed video depicting the route. During playback of the video, the frame and field of view are dynamically modulated to highlight salient features along the route and connect them back to the map. A user interface is demonstrated to allow exploration of the combined map, video, and textual driving directions. We discuss the construction of the hybrid map and video interface. Finally, we report the results of a study that provides evidence of the effectiveness of such a system for route following.

Augmented reality (AR) takes natural user input (NUI), such as gestures, voice, and eye gaze, and produces digital visual overlays on top of reality seen by a user. Today, multiple shipping AR applications exist, most notably titles for the Microsoft Kinect and smartphone applications such as Layar, Wikitude, and Junaio. Despite this activity, little attention has been paid to operating system support for AR applications. Instead, each AR application today does its own sensing and rendering, with the help of user-level libraries like OpenCV or the Microsoft Kinect SDK.

Augmented reality (AR) applications sense the environment, then render virtual objects on human senses. Examples include smartphone applications that annotate storefronts with reviews and XBox Kinect games that show "avatars" mimicking human movements. No current OS has special support for such applications. As a result, permissions for AR applications are necessarily coarse-grained : applications must ask for access to raw sensor feeds, such as video and audio. These raw feeds expose significant additional information beyond what applications need, including sensitive information such as the user's location, face, or surroundings.

Video stabilization is an important video enhancement technology which aims at removing annoying shaky motion from videos. We propose a practical and robust approach of video stabilization that produces full-frame stabilized videos with good visual quality. While most previous methods end up with producing low resolution stabilized videos, our completion method can produce full-frame videos by naturally filling in missing image parts by locally aligning image data of neighboring frames. To achieve this, motion inpainting is proposed to enforce spatial and temporal consistency of the completion in both static and dynamic image areas. In addition, image quality in the stabilized video is enhanced with a new practical deblurring algorithm. Instead of estimating point spread functions, our method transfers and interpolates sharper image pixels of neighbouring frames to increase the sharpness of the frame. The proposed video completion and deblurring methods enabled us to develop a complete video stabilizer which can naturally keep the original image quality in the stabilized videos. The effectiveness of our method is confirmed by extensive experiments over a wide variety of videos.

This paper describes the design and evaluation of a technique, Direct Pointer, that enables users to interact intuitively with large displays using cameras equipped on handheld devices, such as mobile phones and personal digital assistant (PDA). In contrast to many existing interaction methods that attempt to address the same problem, ours offers direct manipulation of the pointer position with continuous visual feedback. The primary advantage of this technique is that it only requires equipment that is readily available: an electronic display, a handheld digital camera, and a connection between the two. No special visual markers in the display content are needed, nor are fixed cameras pointing at the display. We evaluated the performance of Direct Pointer as an interaction product, showing that it performs as well as comparable techniques that require more sophisticated equipment.