A metrological and application-related comparison of six consumer grade stereo depth cameras for the use in robotics
Michel Heinemann, Jonas Herzfeld, Martin J. Sliwinski, Johannes Hinckeldeyn, Jochen Kreutzfeldt
- Year
- 2022
- Citations
- 6
Abstract
Consumer grade depth cameras are important devices to enable robots and unmanned vehicles to perceive their environments. Three major technologies are relevant for those devices: Time-of-Flight, structured light and stereo vision. Stereo cameras in particular have conquered the market in recent years, with Intel's D-series systems leading the way. Besides stereo cameras from Intel, there are many models from other manufacturers, but it has not yet been investigated how these cameras perform in comparison. This paper proposes and applies methods to measure the performance of depth cameras in a metrological way as well as with a focus on the use in robotics. Six stereo depth cameras are tested and compared. In addition, a real world benchmark test and a qualitative evaluation of the accompanying software and documentation is done. A clear recommendation is given in the end.
Keywords
Related papers
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Fractional Differential Equations
Igor Podlubný
2025
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991