Detail of Publication
| Text Language | Japanese |
|---|---|
| Authors | Kazuto NOGUCHI, Takayuki HONDO, Masakazu IWAMURA, and Koichi KISE |
| Title | Real-Time Recognition of Objectsby Cascading Approximate Nearest Neighbor Searchers |
| Journal | Proceedings of MIRU 2007 |
| Presentation number | DS-16 |
| Pages | pp.467-468 |
| Reviewed or not | Not reviewed |
| Month & Year | July 2007 |
| Abstract | We demonstrate a system for real-time object recognition which employs PCA-SIFT as local descriptors of images. Object recognition based on PCA-SIFT has posed problems of processing time for both extraction and matching of local descriptors because of their large number. To solve the problem about extraction, the proposed system is equipped with a GPU (Graphical Processing Unit). For the problem about matching, we utilize a cascaded approximate nearest neighbor searchers. These two factors enable us real-time object recognition even with a database of 100,000 objects. |
- Note
<div id="red" class="blink">The best demonstration of MIRU2007</div> - Following file is available.
- Entry for BibTeX
@InCollection{NOGUCHI2007, author = {Kazuto NOGUCHI and Takayuki HONDO and Masakazu IWAMURA and Koichi KISE}, title = {Real-Time Recognition of Objectsby Cascading Approximate Nearest Neighbor Searchers}, booktitle = {Proceedings of MIRU 2007}, year = 2007, month = jul, presenID = {DS-16}, pages = {467--468} }