Experiences in Building a Real-World Eating Recogniser
Experiences in Building a Real-World Eating Recogniser
复制标题
构建真实世界饮食识别器的经验
DOI：
--
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
Youngki Lee
中科院分区：
文献类型：
--
作者：
Sougata Sen;Vigneshwaran Subbaraju;Archan Misra;R. Balan;Youngki Lee
在本文中，我们描述了一个自动化的食品日志系统- Annapurna的手势识别模块的渐进式设计。Annapurna在智能手表上运行，利用惯性传感器的数据首先识别进食姿势，然后捕捉食物图像，以食物日志的形式呈现给用户。我们详细介绍了我们从多个野外研究中学到的经验教训，并展示了如何改进进食识别器以应对挑战，例如（i）高手势多样性，以及（ii）具有类似手势签名的非进食活动。Annapurna最终是强大的（识别食物内容，饮食方式和环境的广泛多样性）和准确的（假阳性和假阴性率分别为6.5%和3.3%）
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)