A triangle mesh-based corner detection algorithm for catadioptric images

ABSTRACT

As with conventional images corner detection is an important aspect of many computer vision problems involving catadioptric images. However, classical image processing algorithms are no longer appropriate for catadioptric images due to nonuniform resolution and distortions of catadioptric images. In this paper, we propose a novel approach to corner detection for catadioptric images based on triangle mesh. First, we transform catadioptric images to spherical images by combining an improved projection model for central catadioptric cameras with triangle mesh for a unit sphere. Spherical images yield a spatially uniform resolution domain for processing catadioptric images. Then, based on the topology of a triangle mesh, variations of light intensity with respect to directions for each image patch are measured to detect corners. The proposed algorithm addresses problems of catadioptric image processing caused by non-uniform resolution and distortions of these images. Experimental results showed that comparing to widely used methods, the triangle mesh-based corner detection algorithm can achieve higher repeatability rate relative to different imaging condition changes.

KEYWORDS:

• Catadioptric image
• corner detection
• triangle mesh
• Harris algorithm
• non-uniform resolution

Disclosure statement

No potential conflict of interest was reported by the author.

Notes on contributor

Tran Dang Khoa Phan was born in Danang, Vietnam, in 1985. He received the B.E., M.Sc. and Ph.D. degrees in electrical engineering from the Tula State University (TSU), Tula, Russia, in 2008, 2010 and 2015, respectively. In 2015, he joined the Department of Electronic and Telecommunication, University of Science and Technology, The University of Danang, Vietnam. His current research interests include digital image processing, computer vision and machine learning.

Image notes

Image 1(a) was created by the author and 1(b) was taken from the source (a) which was provided by Dr. David Scaramuzza.

Image 4(a) and 8(a) are same, and were taken from the source (b) which was provided by Dr. Christopher Mei.

Image 4(b) and 8(b-d) were reproduced from the original image 4(a) using the proposed algorithm by the author.

Image 7(a) was created by the author using the program Pov-Ray which is also listed in the reference [25].

Image 7(b) and 7(c) were taken from the below datasets which is also listed in the references [26] and [27].

[a] https://sites.google.com/site/scarabotix/ocamcalib-toolbox

[b] http://www.robots.ox.ac.uk/∼cmei/Toolbox.html

Additional information

Funding

This work was supported by The University of Danang – University of Science and Technology.