Maintaining a food journal can allow an individual to monitor eating habits, including unhealthy eating sessions, food items causing severe reactions, or portion size related information. However, manually maintaining a food journal can be burdensome. In this paper, we explore the vision of a pervasive, automated, completely unobtrusive, food journaling system using a commodity smartwatch. We present a prototype system — Annapurna— which is composed of three key components: (a) a smartwatch-based gesture recognizer that can robustly identify eating-specific gestures occurring anywhere, (b) a smartwatch-based image captor that obtains a small set of relevant images (containing views of the food being consumed) with a low energy overhead, and (c) a server-based image filtering engine that removes irrelevant uploaded images. Through lessons learnt from multiple user studies, we refine Annapurna progressively and show that our vision is indeed achievable: Annapurna can identify eating episodes and capture food images (involving a very wide diversity in food content, eating styles and environments) in over 95% of all free-living eating episodes.

维护食品日记可以使个人监控饮食习惯，包括不健康的饮食习惯，引起严重反应的食品或与份量相关的信息。但是，手动维护食品日记会很麻烦。在本文中，我们探索了使用商品智能手表普及，自动化，完全不干扰食品日记系统的愿景。我们提出一个原型系统-Annapurna—由三个关键组件组成：（a）基于智能手表的手势识别器，可以可靠地识别发生在任何地方的饮食特定手势，（b）基于智能手表的图像捕获器，可获取少量相关图像（包含（消耗的食物）和较低的能源开销；以及（c）基于服务器的图像过滤引擎，可删除无关的上传图像。通过从多个用户研究中汲取的经验教训，我们 逐步完善了Annapurna，并表明我们的愿景确实可以实现：Annapurna 可以识别95％以上的饮食事件并捕获食物图像（涉及食物含量，饮食风格和环境的差异非常大）所有自由饮食活动。