The SenseCam is a small wearable personal device which automatically captures up to 2,500 images per day. This yields a very large personal collection of images, or in a sense a large visual diary of a person's day. Intelligent techniques are necessary for effective structuring, searching and browsing of this image collection for locating important or significant events in a person's life. In this paper we identify three stages in the process of capturing and structuring SenseCam images and then displaying them to an end user to review. These stages are expressed in terms of the canonical process stages to which they correlate.

The SenseCam is a wearable camera that passively captures approximately 3,000 images per day, which equates to almost one million images per year. It is used to create a personal visual recording of the wearer's life and generates information which can be helpful as a human memory aid. For such a large amount of visual information to be of any use, it is accepted that it should be structured into "events", of which there are about 8,000 in a wearer's average year. In automatically segmenting SenseCam images into events, it will then be useful for users to locate other events similar to a given event e.g. "what other times was I walking in the park?", "show me other events when I was in a restaurant". On two datasets of 240k and 1.8M images containing topics with a variety of information needs, we evaluate the fusion of MPEG-7, SIFT, and SURF content-based retrieval techniques to address the event search issue. We have found that our proposed fusion approach of MPEG-7 and SURF offers an improvement on using either of those sources or SIFT individually, and we have also shown how a lifelog event is modeled has a large effect on the retrieval performance.

In this paper we present an overview of a software platform that has been developed within the aceMedia project, termed the aceToolbox, that provides global and local lowlevel feature extraction from audiovisual content. The toolbox is based on the MPEG-7 eXperimental Model (XM), with extensions to provide descriptor extraction from arbitrarily shaped image segments, thereby supporting local descriptors reflecting real image content. We describe the architecture of the toolbox as well as providing an overview of the descriptors supported to date. We also briefly describe the segmentation algorithm provided. We then demonstrate the usefulness of the toolbox in the context of two different content processing scenarios: similarity-based retrieval in large collections and scene-level classification of still images.

Abstract. The SenseCam is a wearable camera that automatically takes photos of the wearer's activities, generating thousands of images per day. Automatically organising these images for efficient search and retrieval is a challenging task, but can be simplified by providing semantic information with each photo, such as the wearer's location during capture time. We propose a method for automatically determining the wearer's location using an annotated image database, described using SURF interest point descriptors. We show that SURF out-performs SIFT in matching SenseCam images and that matching can be done efficiently using hierarchical trees of SURF descriptors. Additionally, by re-ranking the top images using bi-directional SURF matches, location matching performance is improved further.

No abstract