arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1905.04076cs.CV
收藏

自我中心照片流中的无监督例程发现

Unsupervised routine discovery in egocentric photo-streams

University of Groningen(格罗宁根大学);University of Barcelona(巴塞罗那大学)

Estefania Talavera, Nicolai Petkov, Petia Radeva

摘要:

一个人的日常生活是由不同日子的活动定义的,可以直接影响人的健康。在这项工作中,我们解决了日常相关的日子的认识。为此,我们依靠以自我为中心的图像,这些图像由可穿戴相机记录,并允许从第一人称视角监控用户的生活。我们提出了一个无监督的模型,确定日常相关的日子,离群值检测方法。我们在总共72天的时间内以照片流的形式测试了所提出的框架,这些照片流覆盖了5个不同相机佩戴者的大约2周的生活。我们的模型为所有用户实现了平均76%的准确率和68%的加权F分数。因此,我们表明,我们的框架能够识别日常相关的日子,并打开大门,了解人们的行为。

英文摘要:

The routine of a person is defined by the occurrence of activities throughout different days, and can directly affect the person's health. In this work, we address the recognition of routine related days. To do so, we rely on egocentric images, which are recorded by a wearable camera and allow to monitor the life of the user from a first-person view perspective. We propose an unsupervised model that identifies routine related days, following an outlier detection approach. We test the proposed framework over a total of 72 days in the form of photo-streams covering around 2 weeks of the life of 5 different camera wearers. Our model achieves an average of 76% Accuracy and 68% Weighted F-Score for all the users. Thus, we show that our framework is able to recognise routine related days and opens the door to the understanding of the behaviour of people.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑