Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
Local invariant feature detectors: a survey
Foundations and Trends® in Computer Graphics and Vision
Minimum explanation complexity for MOD based visual concept detection
Proceedings of the international conference on Multimedia information retrieval
CAIP'07 Proceedings of the 12th international conference on Computer analysis of images and patterns
Handbook of Augmented Reality
AR postcard: the augmented reality system with a postcard
Proceedings of the 10th International Conference on Virtual Reality Continuum and Its Applications in Industry
Hi-index | 0.00 |
Most augmented reality toolkits require special markers to be used. In our system any designated object in the environment can be used instead of special markers. Furthermore, our system was designed to work with low contrast surfaces (such as the wrinkles on the hands of the users). We used a constellation of maximally discriminative salient points derived from the environment to position a 3D rendered entity. These salient features are combined with local texture to give greater detection stability which results in less jitter to the user. We present a real time system which has sufficiently low computational requirements that it works with typical hardware found on modern laptops, tablets, and smartphones.