| Paper: | WP-P4.3 |
| Session: | Image and Video Storage and Retrieval IV |
| Time: | Wednesday, September 19, 14:30 - 17:10 |
| Presentation: |
Poster
|
| Title: |
DUAL-LAYER VISUAL VOCABULARY TREE HYPOTHESES FOR OBJECT RECOGNITION |
| Authors: |
Sandra Ober; Graz University of Technology | | |
| | Martin Winter; Graz University of Technology | | |
| | Clemens Arth; Graz University of Technology | | |
| | Horst Bischof; Graz University of Technology | | |
| Abstract: |
This paper introduces an efficient method to substantially increase the recognition performance of a vocabulary tree based recognition system. We propose to enhance the hypothesis obtained by a standard inverse object voting algorithm with reliable descriptor co-occurrences. The algorithm operates on different layers of a standard k-means tree benefiting from the advantages of different levels of information abstraction. The visual vocabulary tree shows good results when a large number of distinctive descriptors form a large visual vocabulary. Co-occurrences perform well even on a coarse object representation with a small number of visual words. An arbitration strategy with minimal computational effort combines the specific strengths of the particular representations. We demonstrate the achieved performance boost and robustness to occlusions in a challenging object recognition task. |
