Real-Time Object Recognition Based on Cortical Multi-scale Keypoints

Terzic, Kasim; Rodrigues, J. M. F.; du Buf, J. M. H.

http://hdl.handle.net/10400.1/3374

Use this identifier to reference this record.

Name:	Description:	Size:	Format:
ibpria2013b.pdf		329.65 KB	Adobe PDF	Download

Send Feedback

Authors

Terzic, Kasim

Rodrigues, J. M. F.

du Buf, J. M. H.

Abstract(s)

In recent years, a large number of impressive object categorisation algorithms have surfaced, both computational and biologically motivated. While results on standardised benchmarks are impressive, very few of the best-performing algorithms took run-time performance into account, rendering most of them useless for real-time active vision scenarios such as cognitive robots. In this paper, we combine cortical keypoints based on primate area V1 with a state-of-the-art nearest neighbour classifier, and show that such a system can approach state-of-the-art categorisation performance while meeting the real-time constraint.

Keywords

Pattern Recognition Computer imaging Vision Computer Graphics Artificial Intelligence

URI

http://hdl.handle.net/10400.1/3374

Citation

Terzic, Kasim; Rodrigues, Joao M. F.; du Buf, J. M. Hans. Real-Time Object Recognition Based on Cortical Multi-scale Keypoints, In Pattern Recognition and Image Analysis, 314-321, ISBN: 978-3-642-38627-5. Berlin, Heidelberg: Springer Berlin Heidelberg, 2013.

Research Projects

A neuro-dynamic framework for cognitive robotics: scene representations, behavioural sequences, and learning.

Research ProjectShow more

Publisher

Springer Berlin Heidelberg

DOI

http://dx.doi.org/ 10.1007/978-3-642-38628-2_37

Altmetrics

Full item page