A personal visual lifelog can be considered to be a human memory augmentation tool and in recent years we have noticed an increased interest in the topic of lifelogging both in academic research and from industry practitioners. In this preliminary work, we explore the concept of event segmentation of visual lifelog data. Lifelog data, by its nature is continual and streams of multimodal data can easy run into thousands of wearable camera images per day, along with a significant number of other sensor sources. In this paper, we present two new approaches to event segmentation and compare them against pre-existing approaches in a user experiment with ten users. We show that our approaches based on visual concepts occurrence and image categorization perform better than the pre-existing approaches. We finalize the paper with a suggestion for next steps for the research community.