Paper Reading #2: LightGuide: Projected Visualizations for Hand Movement Guidance

Intro:

Title: LightGuide: Projected Visualizations for Hand Movement Guidance

Reference Information: Collaboration between Microsoft Research and the University of Illinois

Author bios:

Rajinder Sodhi is a PhD student at the University of Illinois that was an intern with Microsoft Research. He works with sensing and display techniques.

Hrvoje Benko is a researcher at Microsoft; one of his projects is the Touch Mouse (similar to the new Apple mouse). He has also worked with spatial augmented reality, multitouch surfaces, and non-flat touch surfaces.

Andrew D. Wilson is a principal researcher at Microsoft that works with multi-touch and gesture-based interfaces as well as depth cameras and the like.

Summary: The authors created a system that tracks users' hand movements and projects motion "hints" onto their hand. A Kinect camera is used to find the user's arm, and the projector is synced to the depth camera to project the appropriate instructions. For example, an instruction to move left may include a left arrow, an illustration of a hand, or a pair of positive and negative colors. The system tracks the user to determine hand positions in real time and ensue that correct instructions are communicated. 3-dimensional instructions are communicated with images with "shadows" to show the correct movement. Two different timing methods were used: one was system-guided (so the instructions were shown at the machine's pace) and one was self-guided (the instructions were shown as the user progressed in the instructions).

Related Works:

Find your way through unknown halls with Guiding Light - Niall Firth
Guiding Light is a smartphone app that uses magnetic sensors to detect where you are in a building and uses a projector to display arrows telling you where to walk. (guidance by projection)

Augmented reality technologies, systems and applications - Carmigniani, Furht, Anisetti, et. al.
A general overview of augmented reality technologies and developments

Annotating the Real World - Stephen Ashley

Display systems and registration methods for augmented reality applications - Dongdong Weng, Dewen Chang, Yontian Chang
An overview of a few augmented reality projects involving projecting reconstructions of ruins for tourists and tracking of dancers.

Augmented reality needle guidance improves facet joint injection training - Ungi, Yeo, et. al.
A study testing whether an image overlay or laser guidance would help medical trainees in injection training

Virtual Interactive Presence and Augmented Reality (VIPAR) for Remote Surgical Assistance - Mahesh Shenai
A system allowing remote surgeon assistance; a viewpiece for the local surgeon displays an overlay of the remote surgeon's actions for guidance.

Suggestions on the applicability of visual instructions with see-through head mounted displays depending on the task - Miwa Nakanishi
A study investigating for which workers visual instructions would be useful if shown on a see-through head mounted display
 

An accuracy certified augmented reality system for therapy guidance - Stephane Nicolau
Superimposing a liver image on video of a patient to provide therapy accuracy
 

An interactive 3D movement path manipulation method in an augmented reality environment  - Taejin Ha

Using a tangible interface to change the path of a 3D object in augmented reality

According to the related works found, this project is indeed novel; projection guidance is not novel, nor is augmented reality instruction, but this seems like a new implementation and use for the technology.

Evaluation: To evaluate the system, 10 participants were recruited and the accuracy of their movements was measured in 90 trials using both LightGuide and an instructional video. They used a quantitative, objective method to determine accuracy; they measured deviation from the path and the fit to the path using Euclidean distances. Despite slight systemic error (camera location, slight tracking error, etc.), this method delivered fairly accurate results that indicated the effectiveness of the system. They also asked for user feedback, a qualitative subjective evaluation, to determine the users' comfort with the system. The main complaints were not knowing the complete path when following the system. They also preferred self-guidance to system-guidance. Overall, the use of the system slowed down users compared to watching a video and then acting.

Discussion:  This is an extraordinary project that could help many people. The authors suggest its use in therapeutic environments in which no instructor is available. Additionally, it could be used as a learning tool for new skills. For lack of a better term, it's really cool. The evaluation was very appropriate, combining empirical data with user opinions.

Paper Reading #1: picoTrans: An Icon-driven User Interface for Machine Translation on Mobile Devices

Introduction:  

Authors: Wei Song, Kumiko Tanaka-Ishii, Andrew Finch, and Eiichiro Sumita

Reference information: This paper was a collaboration between the University of Tokyo Graduate School of Science and Technology and the NICT Language Translation Group in Japan.

Author bios:  
Wei Song is a doctoral candidate in the Graduate School of Information Science and Technology at the University of Tokyo; his bachelor's degree is from the Beijing University of Aeronautics and Astronautics, and his master's is from the University of Tokyo.
Kumiko Tanaka-Ishii was a professor at the University of Tokyo that moved to Kyushu University in April 2012. She specializes in language processing, mathematical modeling of language, language software, and computational semiotics. She previously worked at the National Institute of Advanced Industrial Science and Technology in Japan.
Andrew Finch and Eiichiro Sumita have worked on several translation programs and systems.

Finding related works is difficult due to the specificity of the interface; fwe

Summary: The authors of this paper created an interface based on a picture book method of communication. With this interface, the user taps appropriate icons to create sentences; once the icons are selected, a sentence is created in the user's language. If the sentence is not what the user intended, they are able to alter it until it's correct. The sentence is then translated to the target language. To double-check translation correctness, users can back-translate the sentence in the target language. In this research, only icons about traveling were used (e.g. "I want to go" and "the restaurant").

Related work: 
A Picture Language Translator - Hiroshi Migiyama, Taiichiro Hayashi, Nikolay Mirenkov
A Translation Method from Natural Language Specifications into Formal Specifications Using Contextual Dependencies - Yasunoria Ishihara, Hiroyuki Seki, Tadao Kasami

Portable computer based language translation - Davis, S.

Study and Correlation Analysis of Linguistic, Perceptual, and Automatic Machine Translation Evaluations - Mireia Farrus, Marta R. Costa-jussa, Maja Popovic

An Advanced Review of Hybrid Machine Translation - H.W. Xuan, W. Li, G.Y. Tang

The language translation interface: A perspective from the users - Dominique Estival

Icon Design Study in Computer Interface - Rushan Yan

The difficulty in finding relevant works demonstrates the novelty of the project. Few people have used an icon interface with machine translation, apparently.

Evaluation: To evaluate the usefulness of the project, the creators found 100 sentences involving travel and determined whether equivalent sentences could be created. This resulted in a quantitative, unbiased evaluation (e.g. "For 49 of the 74 sentences that we were able to cover with our system (66% of them), the system proposed the correct source sentence to the user..."). They also analyzed the number of key press actions between this method and typing out sentences; this system was found to use 57% of the number of key presses as the text-entry method. This was a systemic evaluation, showing that the entire system works. However, the authors do state that this prototypical system is incomplete and that further development could make it more accurate.

Discussion:  I feel as though this system is useful, but only for specific people in specific circumstances. Translation of spoken words seems more useful and much quicker than using icons, and typing out the sentences seems more efficient as far as time goes. The fewer key presses would give a translation tool to people unaccustomed to or unskilled in using typical interfaces. The work is novel, combining two previously used translation interfaces ("picture books" and straight text translation). The evaluation seemed incomplete; while the number of key presses is one measure of efficiency, I feel like time taken while constructing sentences should have been investigated.

Blog Post Zero: Introduction

Hi! I'm Kate. Here's a not-so-great picture of me:

Email: k8wells@tamu.edu

Class standing: 4th year senior (graduating in May!)

Taking this class because: I think CHI is important in every branch of computer science/computer engineering.

My experience: I've done research in the Multirobot Lab (map-based planning and task assignment for multiple robots), and I worked on a 3D scanner in CSCE 462. I also worked in IT for 2.5 years.

My professional life goals: I want to work in defense, especially in reconnaissance and intelligence acquisition. I'd particularly like to work for the NSA or a Dallas-based defense contractor. I hope I can help innocent people that way...

Personal life goals: I'd like to have a family and a smallish, cute house that I renovated myself. I'd also like to become an awesome ice skater (we'll see about that. I can go forward and turn left really well)

After I graduate: I'd love to get a job to start working towards my professional life goals...

What I expect to be doing in 10 years: do we ever have any idea?

Biggest technological advancement: machines that REALLY learn. Sure, we have some with specific learning sets, but if a computer can learn a large variety of things like humans can, that would be huge.

If I could travel back in time: I have no idea who I'd meet--too many influential people to even count. My mind goes blank every time I try to pick.

My favorite shoes: are brown leather boots with small wedge heels. I can walk in them really well and they make me feel awesome.

I'd love to be fluent in: Chinese. It seems practical and I would feel less ignorant about the world in general.

An interesting fact about me: After a near-death experience when I was 13, I got a pacemaker/defibrillator.