Azure Kinect sensor SDK system requirements
This document provides details about the system requirements needed to install the sensor SDK and successfully deploy your Azure Kinect DK.
Supported operating systems and architectures
- Windows 10 April 2018 (Version 1803, OS Build 17134) release (x64) or a later version
- Linux Ubuntu 18.04 (x64), with a GPU driver that uses OpenGLv4.4 or a later version
The Sensor SDK is available for the Windows API (Win32) for native C/C++ Windows applications. The SDK isn't currently available to UWP applications. Azure Kinect DK isn't supported for Windows 10 in S mode.
Development environment requirements
To contribute to sensor SDK development, visit GitHub.
Minimum host PC hardware requirements
The PC host hardware requirement is dependent on application/algorithm/sensor frame rate/resolution executed on host PC. Recommended minimum Sensor SDK configuration for Windows is:
- Seventh Gen IntelĀ® CoreTM i3 Processor (Dual Core 2.4 GHz with HD620 GPU or faster)
- 4 GB Memory
- Dedicated USB3 port
- Graphics driver support for OpenGL 4.4 or DirectX 11.0
Lower end or older CPUs may also work depending on your use-case.
Performance differs also between Windows/Linux operating systems and graphics drivers in use.
Body tracking host PC hardware requirements
The body tracking PC host requirement is more stringent than the general PC host requirement. Recommended minimum Body Tracking SDK configuration for Windows is:
- Seventh Gen IntelĀ® CoreTM i5 Processor (Quad Core 2.4 GHz or faster)
- 4 GB Memory
- NVIDIA GEFORCE GTX 1050 or equivalent
- Dedicated USB3 port
The recommended minimum configuration assumes K4A_DEPTH_MODE_NFOV_UNBINNED depth mode at 30fps tracking 5 people. Lower end or older CPUs and NVIDIA GPUs may also work depending on your use-case.
USB3
There are known compatibility issues with USB Host controllers. You can find more information on Troubleshooting page
Next steps
Feedback
https://aka.ms/ContentUserFeedback.
Coming soon: Throughout 2024 we will be phasing out GitHub Issues as the feedback mechanism for content and replacing it with a new feedback system. For more information see:Submit and view feedback for