Unsupervised Routine Discovery in Egocentric Photo-Streams

Estefanía Talavera*, Nicolai Petkov, Petia Radeva

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

4 Citations (Scopus)
21 Downloads (Pure)


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.
Original languageEnglish
Title of host publicationComputer Analysis of Images and Patterns
Subtitle of host publication18th International Conference, CAIP 2019, Salerno, Italy, September 3–5, 2019, Proceedings
EditorsMario Vento, Gennaro Percannella
Place of PublicationCham
VolumePart I
ISBN (Electronic)978-3-030-29888-3
ISBN (Print)978-3-030-29887-6
Publication statusPublished - 2019
Externally publishedYes
Event18th International Conference on Computer Analysis of Images and Patterns, CAIP 2019 - Salerno, Italy
Duration: 3 Sept 20195 Sept 2019
Conference number: 18

Publication series

NameLecture Notes in Computer Science
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


Conference18th International Conference on Computer Analysis of Images and Patterns, CAIP 2019
Abbreviated titleCAIP 2019


  • Routine discovery
  • Lifestyle
  • Egocentric vision
  • Behaviour analysis


Dive into the research topics of 'Unsupervised Routine Discovery in Egocentric Photo-Streams'. Together they form a unique fingerprint.

Cite this