Abstract | ||
---|---|---|
In this paper, we describe the progressive design of the gesture recognition module of an automated food journaling system -- Annapurna. Annapurna runs on a smartwatch and utilises data from the inertial sensors to first identify eating gestures, and then captures food images which are presented to the user in the form of a food journal. We detail the lessons we learnt from multiple in-the-wild studies, and show how eating recognizer is refined to tackle challenges such as (i) high gestural diversity, and (ii) non-eating activities with similar gestural signatures. Annapurna is finally robust (identifying eating across a wide diversity in food content, eating styles and environments) and accurate (false-positive and false-negative rates of 6.5% and 3.3% respectively) |
Year | DOI | Venue |
---|---|---|
2017 | 10.1145/3092305.3092306 | WPA@MobiSys |
Field | DocType | ISBN |
Activity recognition,Computer science,Simulation,Gesture,Gesture recognition,Human–computer interaction,Journaling file system,Inertial measurement unit,Smartwatch | Conference | 978-1-4503-4958-1 |
Citations | PageRank | References |
1 | 0.40 | 13 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Sougata Sen | 1 | 21 | 5.69 |
Subbaraju, V. | 2 | 157 | 15.53 |
Archan Misra | 3 | 1688 | 149.25 |
Rajesh Krishna Balan | 4 | 1056 | 80.30 |
Youngki Lee | 5 | 832 | 70.33 |