As a local invariant feature of videos, the spatiotemporal interest point (STIP) has been widely used in computer vision and pattern recognition. However, existing STIP detectors are generally extended from detection algorithms constructed for local invariant features of two-dimensional images, which does not explicitly exploit the motion information inherent in the temporal domain of videos, thus weakening the performance of existing STIP detectors in a video context. To remedy this, we aim to develop an STIP detector that uniformly captures appearance and motion information for video, thus yielding substantial performance improvement. Specifically, under the framework of geometric algebra, we first develop a spatiotemporal unified model of appearance and motion-variation information (UMAMV), and then a UMAMV-based scale space of the spatiotemporal domain is proposed to synthetically analyze appearance information and motion information in a video. Based on this model, we propose an STIP feature of UMAMV-SIFT that embraces both appearance and motion variation information of the videos. Three datasets with different sizes are utilized to evaluate the proposed model and the STIP detector. We present experimental results to show that the UMAMV-SIFT achieves state-of-the-art performance and is particularly effective when dataset is small.
An intelligent image-indexing algorithm is proposed in this paper. It based on knowledge extracted from some simple single low-level image features. Two independent large image databases are built with more than 12000 images for training and test, and the experimental results show it work efficiently for high dimension database indexing. The running time is shorter than other algorithms proposed for the same purpose, and the algorithm performs even better for some certain semantic image classifications.
In this correspondence, a new block sum pyramid algorithm (NBPSA) to motion estimation is presented. Compared with BSPA, NBSPA estimate the vector of the minimum mean absolute difference ( MADmin ) In the mean time, instead of update the value level by level, we update the estimation of MAD row by row, up to down. Experimental results showed that, with the search result ofthe algorithm identical to the search result ofthe exhaustive search and BSPA, NBSPA reduced the computation complexity greatly.
Proceedings Volume Editor (2)
This will count as one of your downloads.
You will have access to both the presentation and article (if available).
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.