A High Quality Depth Map Upsampling Method Robust to Misalignment of Depth and Color Boundaries

• Published in: Journal of signal processing systems Vol. 75; no. 1; pp. 23 - 37
• Main Authors: Kim, Jaekwang, Lee, Jaeho, Han, Seung-Ryong, Kim, Dowan, Min, Jongsul, Kim, Changick
• Format: Journal Article
• Language: English
• Published: Boston Springer US 01.04.2014
• Subjects: Algorithms; Boundaries; Circuits and Systems; Color; Computer Imaging; Electrical Engineering; Engineering; Image Processing and Computer Vision; Kernels; Mathematical analysis; Pattern Recognition; Pattern Recognition and Graphics; Regression; Signal,Image and Speech Processing; Vectors (mathematics); Vision; TOF depth sensor; Trilateral filter; Depth map upsampling; Fusion camera system
• ISSN: 1939-8018; 1939-8115
• DOI: 10.1007/s11265-013-0783-x

In recent years, fusion camera systems that consist of color cameras and Time-of-Flight (TOF) depth sensors have been popularly used due to its depth sensing capability at real-time frame rates. However, captured depth maps are limited in low resolution compared to the corresponding color images due to physical limitation of the TOF depth sensor. Most approaches to enhancing the resolution of captured depth maps depend on the implicit assumption that when neighboring pixels in the color image have similar values, they are also similar in depth. Although many algorithms have been proposed, they still yield erroneous results, especially when region boundaries in the depth map and the color image are not aligned. We therefore propose a novel kernel regression framework to generate the high quality depth map. Our proposed filter is based on the vector pointing similar pixels that represents the unit vector toward similar neighbors in the local region. The vectors are used to detect misaligned regions between color edges and depth edges. Unlike conventional kernel regression methods, our method properly handles misaligned regions by introducing the numerical analysis of the local structure into the kernel regression framework. Experimental comparisons with other data fusion techniques prove the superiority of the proposed algorithm.