Proceedings of the 2nd International Conference on Mechatronics Engineering and Information Technology (ICMEIT 2017)

An Adaptive FAST Corner Detector based on High Contrast Grid Image

Authors
Teng Wu, Zhili Zhang, Junyang Zhao, Fenggang Liu
Corresponding Author
Teng Wu
Available Online May 2017.
DOI
https://doi.org/10.2991/icmeit-17.2017.128How to use a DOI?
Keywords
image; high contrast enhancement; corner detection; adaptive threshold; entropy
Abstract
In this paper, an improved adaptive threshold algorithm was propose for grid image blocks with preprocessing in order to settle some defects as feature clustering, threshold fixation and noise sensitivity in FAST corner detection algorithms. Firstly, a high contrast enhancement filter algorithm is used to preprocess the image to suppress effects of the noise and enhance target characteristics. Then, based on the statistical analysis of image entropy and variance, a prediction equation for capacity of corner is proposed to adjust the threshold of the image block after the base threshold is determined to overcome the problem of image feature clustering. The experiments show that the adaptive thresholds of the improved algorithm are reasonable and the distribution of corner detection results is uniform, and the effect of noise and fuzzy images on the stability of the algorithm is well solved.
Open Access
This is an open access article distributed under the CC BY-NC license.

Download article (PDF)

Proceedings
2nd International Conference on Mechatronics Engineering and Information Technology (ICMEIT 2017)
Part of series
Advances in Computer Science Research
Publication Date
May 2017
ISBN
978-94-6252-338-8
ISSN
2352-538X
DOI
https://doi.org/10.2991/icmeit-17.2017.128How to use a DOI?
Open Access
This is an open access article distributed under the CC BY-NC license.

Cite this article

TY  - CONF
AU  - Teng Wu
AU  - Zhili Zhang
AU  - Junyang Zhao
AU  - Fenggang Liu
PY  - 2017/05
DA  - 2017/05
TI  - An Adaptive FAST Corner Detector based on High Contrast Grid Image
BT  - 2nd International Conference on Mechatronics Engineering and Information Technology (ICMEIT 2017)
PB  - Atlantis Press
SN  - 2352-538X
UR  - https://doi.org/10.2991/icmeit-17.2017.128
DO  - https://doi.org/10.2991/icmeit-17.2017.128
ID  - Wu2017/05
ER  -