Japanese / English

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.
Back to list