Browsing by Author "Welch, Greg"
Now showing 1 - 3 of 3
Results Per Page
Sort Options
Item An Automated Virtual Receptionist for Recognizing Visitors and Assuring Mask Wearing(The Eurographics Association, 2020) Zehtabian, Sharare; Khodadadeh, Siavash; Kim, Kangsoo; Bruder, Gerd; Welch, Greg; Bölöni, Ladislau; Turgut, Damla; Kulik, Alexander and Sra, Misha and Kim, Kangsoo and Seo, Byung-KukIntelligent virtual agents have many societal uses, specifically in situations in which the presence of real humans would be prohibitive. In particular, virtual receptionists can perform a variety of tasks associated with visitor and employee safety, e.g., during the COVID-19 pandemic. In this poster, we present our prototype of a virtual receptionist that employs computer vision and meta-learning techniques to identify and interact with a visitor in a manner similar to that of a real human receptionist. Specifically we employ a meta-learning-based classifier to learn the visitors' faces from the minimal data collected during a first visit, such that the receptionist can recognize the same visitor during follow-up visits. The system also makes use of deep neural network-based computer vision techniques to recognize whether the visitor is wearing a face mask or not.Item A Systematic Literature Review of Embodied Augmented Reality Agents in Head-Mounted Display Environments(The Eurographics Association, 2020) Norouzi, Nahal; Kim, Kangsoo; Bruder, Gerd; Erickson, Austin; Choudhary, Zubin; Li, Yifan; Welch, Greg; Argelaguet, Ferran and McMahan, Ryan and Sugimoto, MakiEmbodied agents, i.e., computer-controlled characters, have proven useful for various applications across a multitude of display setups and modalities. While most traditional work focused on embodied agents presented on a screen or projector, and a growing number of works are focusing on agents in virtual reality, a comparatively small number of publications looked at such agents in augmented reality (AR). Such AR agents, specifically when using see-through head-mounted displays (HMDs) as the display medium, show multiple critical differences to other forms of agents, including their appearances, behaviors, and physical-virtual interactivity. Due to the unique challenges in this specific field, and due to the comparatively limited attention by the research community so far, we believe that it is important to map the field to understand the current trends, challenges, and future research. In this paper, we present a systematic review of the research performed on interactive, embodied AR agents using HMDs. Starting with 1261 broadly related papers, we conducted an in-depth review of 50 directly related papers from 2000 to 2020, focusing on papers that reported on user studies aiming to improve our understanding of interactive agents in AR HMD environments or their utilization in specific applications. We identified common research and application areas of AR agents through a structured iterative process, present research trends, and gaps, and share insights on future directions.Item Towards Interactive Virtual Dogs as a Pervasive Social Companion in Augmented Reality(The Eurographics Association, 2020) Norouzi, Nahal; Kim, Kangsoo; Bruder, Gerd; Welch, Greg; Kulik, Alexander and Sra, Misha and Kim, Kangsoo and Seo, Byung-KukPets and animal-assisted intervention sessions have shown to be beneficial for humans' mental, social, and physical health. However, for specific populations, factors such as hygiene restrictions, allergies, and care and resource limitations reduce interaction opportunities. In parallel, understanding the capabilities of animals' technological representations, such as robotic and digital forms, have received considerable attention and has fueled the utilization of many of these technological representations. Additionally, recent advances in augmented reality technology have allowed for the realization of virtual animals with flexible appearances and behaviors to exist in the real world. In this demo, we present a companion virtual dog in augmented reality that aims to facilitate a range of interactions with populations, such as children and older adults.We discuss the potential benefits and limitations of such a companion and propose future use cases and research directions.