Augmented reality

About: Augmented reality is a research topic. Over the lifetime, 36039 publications have been published within this topic receiving 479617 citations. The topic is also known as: AR.

Technologies for augmented reality systems: realizing ultrasound-guided needle biopsies

Abstract: We present a real-time stereoscopic video-see-through augmented reality (AR) system applied to the medical procedure known as ultrasound-guided needle biopsy of the breast. The AR system was used by a physician during procedures on breast models and during non-invasive examinations of human subjects. The system merges rendered live ultrasound data and geometric elements with stereo images of the patient acquired through head-mounted video cameras and presents these merged images to the physician in a head-mounted display. The physician sees a volume visualization of the ultrasound data directly under the ultrasound probe, properly registered within the patient and with the biopsy needle. Using this system, a physician successfully guided a needle into an artificial tumor within a training phantom of a human breast. We discuss the construction of the AR system and the issues and decisions which led to the system architecture and the design of the video see-through head-mounted display. We designed methods to properly resolve occlusion of the real and synthetic image elements. We developed techniques for realtime volume visualization of timeand position-varying ultrasound data. We devised a hybrid tracking system which achieves improved registration of synthetic and real imagery and we improved on previous techniques for calibration of a magnetic tracker. CR

Cognitive, performance, and systems issues for augmented reality applications in manufacturing and maintenance

Abstract: This paper presents cognitive studies and analyses relating to how augmented reality (AR) interacts with human abilities in order to benefit manufacturing and maintenance tasks A specific set of applications is described in detail, as well as a prototype system and the software library that it is built upon An integrated view of information flow to support AR is also presented, along with a proposal for an AR media language (ARML) that could provide interoperability between various AR implementations

Contextually intelligent communication systems and processes

Abstract: A contextually intelligent communication system and processes acquire and processes data on the current context of a user who is using a connected mobile communication device such as a smart phone or tablet by using various sensors, image recognition or augmented reality residing in the connected device; providing additional data to define the user's current environment; combining the contextual data on the device with the additional data to define the user's complete, relevant context; gathering the user's current context data and updating the device by uploading the data via a wide area mobile network to a contextually intelligent server in the cloud, matching the user's current contextual data with the user's past and historical data and then downloading updated data back to the device, with the updated data including any of a variety of contextually relevant information such as feedback, experiences, recommendations, offers, coupons, advice, tactile feedback, content such as visual and audio representations, augmented reality, and other audio/visual displays to the device of the user that is predictably useful and relevant to the user's current context and future context as the user enters a new context.

Interactive Occlusion and Collision of Real and Virtual Objects in Augmented Reality

Abstract: We present several techniques for interactively performing occlusion and collision detection between static real objects and dynamic virtual objects in augmented reality. Computer vision algorithms are used to acquire data that model aspects of the real world. Either geometric models may be registered to real objects, or a depth map of the real scene may be extracted with computer vision algorithms. The computer vision-derived data are mapped into algorithms that exploit the power of graphics workstations, in order to interactively produce new effects in augmented reality. By combining live video from a calibrated camera with real-time renderings of the real-world data from graphics hardware, dynamic virtual objects occlude and are occluded by static real objects. As a virtual object is interactively manipulated collisions with real objects are detected, and the motion of the virtual object is constrained. Simulated gravity may then be produced by automatically moving the virtual object in the direction of a gravity vector until it encounters a collision with a real object.