Aiden Doherty’s Thesis: Providing effective memory retrieval cues through automatic structuring and augmentation of a lifelog of images

Aiden did fantastic work on managing the enormous corpus you build up when lifelogging. For example, someone wearing a SenseCam could easily collect more than half a million images each year. He investigates techniques that:

1. Identify distinct events within a full day of lifelog images (which typically consists of 2,000 images) e.g. breakfast, working on PC, meeting, etc. 2. Find similar events to a given event in a person’s lifelog e.g. “show me other events where I was in the park” 3. Determine those events that are more important or unusual to the user and also select a relevant keyframe image for visual display of an event e.g. a “meeting” is more interesting to review than “working on PC” 4. Augment the images from a wearable camera with higher quality images from external “Web 2.0” sources e.g. find me pictures taken by others of the U2 concert in Croke Park

You can get the complete abstract and download the thesis.


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s