Today I read a paper titled “The role of RGB-D benchmark datasets: an overview”
The abstract is:
The advent of the Microsoft Kinect three years ago stimulated not only the computer vision community for new algorithms and setups to tackle well-known problems in the community but also sparked the launch of several new benchmark datasets to which future algorithms can be compared 019 to.
This review of the literature and industry developments concludes that the current RGB-D benchmark datasets can be useful to determine the accuracy of a variety of applications of a single or multiple RGB-D sensors.