Spatio-thermal depth correction of RGB-D sensors based on Gaussian Processes in real-time
This work addresses a critical issue for computer vision and robotics applications by improving depth sensor accuracy, though it is incremental as it builds on existing calibration techniques with a focus on real-time performance.
The paper tackles the problem of erratic depth readings in commodity RGB-D sensors caused by coarse calibration, aging, and thermal effects, proposing a novel method based on Gaussian Process Regression in a four-dimensional Cartesian and thermal domain to achieve accurate depth calibration in real-time.
Commodity RGB-D sensors capture color images along with dense pixel-wise depth information in real-time. Typical RGB-D sensors are provided with a factory calibration and exhibit erratic depth readings due to coarse calibration values, ageing and thermal influence effects. This limits their applicability in computer vision and robotics. We propose a novel method to accurately calibrate depth considering spatial and thermal influences jointly. Our work is based on Gaussian Process Regression in a four dimensional Cartesian and thermal domain. We propose to leverage modern GPUs for dense depth map correction in real-time. For reproducibility we make our dataset and source code publicly available.