Lifelogging is the process of passively capturing personal daily events using wearable devices. This practice has grown rapidly thanks to the availability of low-cost and power-efficient wearable sensors and mobile devices recording multi-modal data including GPS, photos (egocentric photos), and biometrics data
These devices can create visual diaries encoding every aspect of one’s life with the aim of future sharing, recollecting or analysis. This DCU research collaboration has produced LifeSeeker, a lifelog image retrieval system. The objective is to support users to seek specific life moments using a combination of textual descriptions, spatial relationships, location information, and image similarities. We also tested the efficacy of the system when used by non-experts.
The team has worked on the project for three years as part of the Lifelog Search Challenge, an annual international research challenge. In that time the team has developed the search engine into one of the top performing programs in the challenge