LARGE-AREA DEPTH RECOVERY FOR RGB-D CAMERA Conference Paper

abstract

• 2015 IEEE. In this paper, a large-area depth recovery method for RGB-D camera is proposed. Considering that pixels along edges between different regions usually share similar depth values, we first select reliable pixels along edges of large-area depth missing regions and project them into the world coordinate system. Then, by examining the distribution of these pixels, we apply a weighted least squares method to approximate the surface function. With the help of the surface function, missing depth values can be recovered correctly. To the best of our knowledge, this is the first recovery method focusing on large areas of missing depth information. Qualitative evaluation demonstrates the effectiveness of the proposed method.

name of conference

• 2015 IEEE International Conference on Image Processing (ICIP)

authors

• Xiong, Zixiang

published proceedings

• 2015 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)

author list (cited authors)

• Yan, Z., Yu, L. i., & Xiong, Z.

citation count

• 0

complete list of authors

• Yan, Zengqiang||Yu, Li||Xiong, Zixiang

publication date

• January 2015

publisher

• Institute of Electrical and Electronics Engineers (IEEE)  Publisher

published in

• Proceedings / ICIP ... International Conference on Image Processing  Journal

keywords

• Depth Recovery
• Point Cloud Processing
• Rgb-d Camera
• Surface Approximation

Digital Object Identifier (DOI)

• 10.1109/icip.2015.7351032

International Standard Book Number (ISBN) 13

• 9781479983391

start page

• 1409

end page

• 1413

volume

• 2015-December

URL

• http://dx.doi.org/10.1109/icip.2015.7351032