Automatic Summarization of Wearable Video - Indexing Subjective Interest
PCM '01 Proceedings of the Second IEEE Pacific Rim Conference on Multimedia: Advances in Multimedia Information Processing
Wearable Computing Meets Ubiquitous Computing: Reaping the Best of Both Worlds
ISWC '99 Proceedings of the 3rd IEEE International Symposium on Wearable Computers
Asymmetries in Collaborative Wearable Interfaces
ISWC '99 Proceedings of the 3rd IEEE International Symposium on Wearable Computers
ISWC '00 Proceedings of the 4th IEEE International Symposium on Wearable Computers
StartleCam: A Cybernetic Wearable Camera
ISWC '98 Proceedings of the 2nd IEEE International Symposium on Wearable Computers
Design and implementation of geo-tagged video search framework
Journal of Visual Communication and Image Representation
Geotagging in multimedia and computer vision--a survey
Multimedia Tools and Applications
| Hi-index | 0.00 |
With the advent of wearable cameras attached with wearable computers, we can record our daily lives as a large amount of video data. As a consequence, automatic creation of indexes on such video data is becoming important to support query retrieval or digest creation on them. This is because it is unrealistic to create indexes on long-sustained video data by hand. To cope with this problem, we propose a method to automatically create index on such video data on the basis of geographic objects. In this scheme, users wear a wearable computer, a GPS receiver, and a wearable video camera with gyroscope to record various kinds of context information as well as video data. The system then makes analysis of those data, and automatically creates indexes of the video data. To this end, we propose two kinds of weighting schemes for geographic objects, namely, distance-and direction-based weights. We introduce some variations of distance-based weighting functions, and a method to adaptively decide reasonable indexing area with respect to the position of the user and geographic objects.