Research on Fast Object Detection of CCD Astronomical Image

DOI

10.2991/icmmcce-17.2017.267How to use a DOI?

Keywords

CCD Image; Object Detection; Extracted Matrix

Abstract

As the imaging technology improves the resolution of the astronomical image, how to effectively and efficiently extract objects has become a big challenge. As the dimension of the CCD image matrix is increasing with the increase of the astronomical image resolution, the traditional method which needs to detect objects point-by-point can't satisfy practical usage due to their low detection efficiency. A novel traversal method based on the extraction of the block matrix is proposed in this paper, which overcomes the limitations of traditional traversal methods. The proposed method extracts these data that are larger than the threshold to generate new small matrices by four corners positioning to avoid the traversal of the whole matrix for object detection. Then these small matrices are respectively traversed. The experiments show that the proposed algorithm can greatly improve the computing and searching efficiency.

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  - Ming-Lei Wu
AU  - Jing-Chang Pan
PY  - 2017/09
DA  - 2017/09
TI  - Research on Fast Object Detection of CCD Astronomical Image
BT  - Proceedings of the 2017 5th International Conference on Mechatronics, Materials, Chemistry and Computer Engineering (ICMMCCE 2017)
PB  - Atlantis Press
SP  - 1521
EP  - 1524
SN  - 2352-5401
UR  - https://doi.org/10.2991/icmmcce-17.2017.267
DO  - 10.2991/icmmcce-17.2017.267
ID  - Wu2017/09
ER  -