Details
| Original language | English |
|---|---|
| Title of host publication | IEEE SSCI 2011 - Symposium Series on Computational Intelligence |
| Subtitle of host publication | SDE 2011 IEEE Symposium on Differential Evolution |
| Pages | 104-111 |
| Number of pages | 8 |
| Publication status | Published - 2011 |
| Event | Symposium Series on Computational Intelligence, IEEE SSCI 2011 - 2011 IEEE Symposium on Differential Evolution, SDE 2011 - Paris, France Duration: 11 Apr 2011 → 15 Apr 2011 |
Publication series
| Name | IEEE SSCI 2011 - Symposium Series on Computational Intelligence - SDE 2011: 2011 IEEE Symposium on Differential Evolution |
|---|
Abstract
The accuracy evaluation of image feature detectors is done using the repeatability criterion. Therefore, a well-known data set consisting of image sequences and homography matrices is processed. This data serves as ground truth mapping information for the evaluation and is used in many computer vision papers. An accuracy validation of the benchmarks has not been done so far and is provided in this work. The accuracy is limited and evaluations of feature detectors may result in erroneous conclusions. Using a differential evolution approach for the optimization of a new, feature-independent cost function, the accuracy of the ground truth homographies is increased. The results are validated using comparisons between the repeatability rates before and after the proposed optimization. The new homographies provide better repeatability results for each detector. The repeatability rate is increased by up to 20%.
ASJC Scopus subject areas
- Computer Science(all)
- Computational Theory and Mathematics
- Computer Science(all)
- Computer Science Applications
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
IEEE SSCI 2011 - Symposium Series on Computational Intelligence: SDE 2011 IEEE Symposium on Differential Evolution. 2011. p. 104-111 5952056 (IEEE SSCI 2011 - Symposium Series on Computational Intelligence - SDE 2011: 2011 IEEE Symposium on Differential Evolution).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Increasing the Accuracy of Feature Evaluation Benchmarks Using Differential Evolution
AU - Cordes, Kai
AU - Rosenhahn, Bodo
AU - Ostermann, Jörn
PY - 2011
Y1 - 2011
N2 - The accuracy evaluation of image feature detectors is done using the repeatability criterion. Therefore, a well-known data set consisting of image sequences and homography matrices is processed. This data serves as ground truth mapping information for the evaluation and is used in many computer vision papers. An accuracy validation of the benchmarks has not been done so far and is provided in this work. The accuracy is limited and evaluations of feature detectors may result in erroneous conclusions. Using a differential evolution approach for the optimization of a new, feature-independent cost function, the accuracy of the ground truth homographies is increased. The results are validated using comparisons between the repeatability rates before and after the proposed optimization. The new homographies provide better repeatability results for each detector. The repeatability rate is increased by up to 20%.
AB - The accuracy evaluation of image feature detectors is done using the repeatability criterion. Therefore, a well-known data set consisting of image sequences and homography matrices is processed. This data serves as ground truth mapping information for the evaluation and is used in many computer vision papers. An accuracy validation of the benchmarks has not been done so far and is provided in this work. The accuracy is limited and evaluations of feature detectors may result in erroneous conclusions. Using a differential evolution approach for the optimization of a new, feature-independent cost function, the accuracy of the ground truth homographies is increased. The results are validated using comparisons between the repeatability rates before and after the proposed optimization. The new homographies provide better repeatability results for each detector. The repeatability rate is increased by up to 20%.
UR - http://www.scopus.com/inward/record.url?scp=79961135973&partnerID=8YFLogxK
U2 - 10.1109/SDE.2011.5952056
DO - 10.1109/SDE.2011.5952056
M3 - Conference contribution
AN - SCOPUS:79961135973
SN - 9781612840727
T3 - IEEE SSCI 2011 - Symposium Series on Computational Intelligence - SDE 2011: 2011 IEEE Symposium on Differential Evolution
SP - 104
EP - 111
BT - IEEE SSCI 2011 - Symposium Series on Computational Intelligence
T2 - Symposium Series on Computational Intelligence, IEEE SSCI 2011 - 2011 IEEE Symposium on Differential Evolution, SDE 2011
Y2 - 11 April 2011 through 15 April 2011
ER -