Dear Colleagues, I started this discussion to collect data on the use of the Azure Kinect camera in research and industry. It is my intention to collect data about libraries, SDKs, scripts and links, which may be useful to make life easier for users and developers using this sensor.
Notes on installing on various operating systems and platforms (Windows, Linux, Jetson, ROS)
- Azure Kinect camera setup (automated scripts for Linux). https://github.com/juancarlosmiranda/azure_kinect_notes
- Azure Kinect ROS Driver. https://github.com/microsoft/Azure_Kinect_ROS_Driver
SDKs for programming
- Microsoft SDK C/C++. https://learn.microsoft.com/en-us/azure/kinect-dk/sensor-sdk-download
- Azure Kinect Body Tracking SDK. https://learn.microsoft.com/en-us/azure/kinect-dk/body-sdk-download
- Github Azure Kinect SDK. https://github.com/microsoft/Azure-Kinect-Sensor-SDK
- KinZ an Azure Kinect toolkit for Python and Matlab.
Article KinZ an Azure Kinect toolkit for Python and Matlab
- pyk4a - a simple and pythonic wrapper in Python 3 for the Azure-Kinect-Sensor-SDK. https://github.com/etiennedub/pyk4a
Tools for recording and data extraction (update 10/08/2023)
- Azure Kinect DK recorder. https://learn.microsoft.com/en-us/azure/kinect-dk/azure-kinect-recorder
- Azure Kinect Viewer. https://learn.microsoft.com/en-us/azure/kinect-dk/azure-kinect-viewer
- AK_SM_RECORDER. A simple GUI recorder based on Python to manage Azure Kinect camera devices in a standalone mode. (https://pypi.org/project/ak-sm-recorder/)
- AK_ACQS is a software solution for data acquisition in fruit orchards using a sensor system boarded on a terrestrial vehicle. It allows the coordination of computers and sensors through the sending of remote commands via a GUI. At the same time, it adds an abstraction layer on library stack of each sensor, facilitating its integration. This software solution is supported by a local area network (LAN), which connects computers and sensors from different manufacturers ( cameras of different technologies, GNSS receiver) for in-field fruit yield testing. (https://github.com/GRAP-UdL-AT/ak_acquisition_system)
- AK_FRAEX is a desktop tool created for post-processing tasks after field acquisition. It enables the extraction of information from videos recorded in MKV format with the Azure Kinect camera. Through a GUI, the user can configure initial parameters to extract frames and automatically create the necessary metadata for a set of images. (https://pypi.org/project/ak-frame-extractor/)
Tools for fruit sizing and yield prediction (update 19/09/2023)
- AK_SW_BENCHMARKER. Python based GUI tool for fruit size estimation and weight prediction. (https://pypi.org/project/ak-sw-benchmarker/)
- AK_VIDEO_ANALYSER. Python based GUI tool for fruit size estimation and weight prediction from videos recorded with the Azure Kinect DK sensor camera in Matroska format. It receives as input a set of videos to analyse and gives as result reports in CSV datasheet format with measures and weight predictions of each detected fruit. (https://pypi.org/project/ak-video-analyser/).
Demo videos to test the software (update 10/08/2023)
- AK_FRAEX - Azure Kinect Frame Extractor demo videos. https://doi.org/10.5281/zenodo.6968103
- AK_FRAEX - Azure Kinect Frame Extractor demo videos (updated with BGRA32 videos for 3d point cloud extration). https://doi.org/10.5281/zenodo.8232445
Papers, articles (update 24/10/2023)
- Experimental Procedure for the Metrological Characterization of Time-of-Flight Cameras for Human Body 3D Measurements. [
Article Experimental Procedure for the Metrological Characterization...
]. - AKFruitData: A dual software application for Azure Kinect cameras to acquire and extract informative data in yield tests performed in fruit orchard environments. [https://www.sciencedirect.com/science/article/pii/S2352711022001492]
- AKFruitYield: Modular benchmarking and video analysis software for Azure Kinect cameras for fruit size and fruit yield estimation in apple orchards. [https://www.sciencedirect.com/science/article/pii/S2352711023002443]
- Assessing automatic data processing algorithms for RGB-D cameras to predict fruit size and weight in apples. [https://www.sciencedirect.com/science/article/pii/S0168169923006907]
Hi Juan Carlos,
we are using Azure Kinect for non-invasive motion analysis applications. To this end, we use the body tracking SDK available at this link: https://learn.microsoft.com/it-it/azure/kinect-dk/body-sdk-download
visit this link its very useful for projection
https://github.com/microsoft/Azure_Kinect_ROS_Driver
If it can be useful to your work, I recently published a paper about the metrological characterization of Azure Kinect (procedure, results).
Article Experimental Procedure for the Metrological Characterization...
Thank you very much Cristina, I added a new section with your suggestions.
- Badges
- Science topic
- Similar topics
- Computer Science and Engineering
- Programming Languages
- Python