An Adaptive FAST Corner Detector based on High Contrast Grid Image

DOI

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.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

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  - Proceedings of the 2nd International Conference on Mechatronics Engineering and Information Technology (ICMEIT 2017)
PB  - Atlantis Press
SP  - 705
EP  - 711
SN  - 2352-538X
UR  - https://doi.org/10.2991/icmeit-17.2017.128
DO  - 10.2991/icmeit-17.2017.128
ID  - Wu2017/05
ER  -