Skeleton Tracking Accuracy and Precision Evaluation of Kinect V1, Kinect V2, and the Azure Kinect
Source abstract
Abstract
The Azure Kinect, the successor of Kinect v1 and Kinect v2, is a depth sensor. In this paper we evaluate the skeleton tracking abilities of the new sensor, namely accuracy and precision (repeatability). Firstly, we state the technical features of all three sensors, since we want to put the new Azure Kinect in the context of its previous versions. Then, we present the experimental results of general accuracy and precision obtained by measuring a plate mounted to a robotic manipulator end effector which was moved along the depth axis of each sensor and compare them. In the second experiment, we mounted a human-sized figurine to the end effector and placed it in the same positions as the test plate. Positions were located 400 mm from each other. In each position, we measured relative accuracy and precision (repeatability) of the detected figurine body joints. We compared the results and concluded that the Azure Kinect surpasses its discontinued predecessors, both in accuracy and precision. It is a suitable sensor for human–robot interaction, body-motion analysis, and other gesture-based applications. Our analysis serves as a pilot study for future HMI (human–machine interaction) designs and applications using the new Kinect Azure and puts it in the context of its successful predecessors.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Hand Gesture Recognition Systems · Human Pose and Action Recognition · Robot Manipulation and Learning
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Institute of Robotics and Cybernetics, Faculty of Electrical Engineering and Information Technology STU in Bratislava, Ilkovičova 3, 812 19 Bratislava, Slovakia
Funding
Agentúra na Podporu Výskumu a Vývoja
References (32)
Show source-provided references
1. Elaraby, A.F., Hamdy, A., and Rehan, M. (2018, January 1–3). A Kinect-Based 3D Object Detection and Recognition System with Enhanced Depth Estimation Algorithm. Proceedings of the 2018 IEEE 9th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON), Vancouver, BC, Canada.10.1109/IEMCON.2018.8615020 ↗
2. Tanabe, R., Cao, M., Murao, T., and Hashimoto, H. (2012, January 20–23). Vision based object recognition of mobile robot with Kinect 3D sensor in indoor environment. Proceedings of the 2012 Proceedings of SICE Annual Conference (SICE), Akita, Japan.
3. Manap, M.S.A., Sahak, R., Zabidi, A., Yassin, I., and Tahir, N.M. (2015, January 6–8). Object Detection using Depth Information from Kinect Sensor. Proceedings of the 2015 IEEE 11th International Colloquium on Signal Processing & Its Applications (CSPA), Kuala Lumpur, Malaysia.10.1109/CSPA.2015.7225638 ↗
4. Xin, G.X., Zhang, X.T., Wang, X., and Song, J. (2015, January 19–20). A RGBD SLAM algorithm combining ORB with PROSAC for indoor mobile robot. Proceedings of the 2015 4th International Conference on Computer Science and Network Technology (ICCSNT), Harbin, China.10.1109/ICCSNT.2015.7490710 ↗
5. RGB-D mapping: Using Kinect-style depth cameras for dense 3D modeling of indoor environments10.1177/0278364911434148 ↗
6. Ibragimov, I.Z., and Afanasyev, I.M. (2017, January 25–26). Comparison of ROS-based visualslam methods in homogeneous indoor environment. Proceedings of the 2017 14th Workshop on Positioning, Navigation and Communications (WPNC), Bremen, Germany.10.1109/WPNC.2017.8250081 ↗
7. Static and dynamic hand gesture recognition in depthdata using dynamic time warping10.1109/TIM.2015.2498560 ↗
8. Superpixel-based hand gesture recognition withKinect depth camera10.1109/TMM.2014.2374357 ↗
9. Robust part-based hand gesture recognition using kinect sensor10.1109/TMM.2013.2246148 ↗
10. Avalos, J., Cortez, S., Vasquez, K., Murray, V., and Ramos, O.E. (March, January 28). Telepres-ence using the kinect sensor and the nao robot. Proceedings of the 2016 IEEE 7th Latin American Symposium on Circuits & Systems (LASCAS), Florianopolis, Brazil.10.1109/LASCAS.2016.7451070 ↗
11. Berri, R., Wolf, D., and Osório, F.S. (2014, January 18–23). Telepresence Robot with Image-Based Face Tracking and 3D Perception with Human Gesture Interface Using Kinect Sensor. Proceedings of the 2014 Joint Conference on Robotics: SBR-LARS Robotics Symposium and Robocontrol, Sao Carlos, Brazil.10.1109/SBR.LARS.Robocontrol.2014.11 ↗
12. Tao, G., Archambault, P.S., and Levin, M.F. (2013, January 26–29). Evaluation of Kinect skeletal tracking in a virtual reality rehabilitation system for upper limb hemiparesis. Proceedings of the 2013 International Conference on Virtual Rehabilitation (ICVR), Philadelphia, PA, USA.10.1109/ICVR.2013.6662084 ↗
13. Satyavolu, S., Bruder, G., Willemsen, P., and Steinicke, F. (2012, January 4–8). Analysis of IR-based virtual reality tracking using multiple Kinects. Proceedings of the 2012 IEEE Virtual Reality (VR), Costa Mesa, CA, USA.10.1109/VR.2012.6180925 ↗
14. Gotsis, M., Tasse, A., Swider, M., Lympouridis, V., Poulos, I.C., Thin, A.G., Turpin, D., Tucker, D., and Jordan-Marsh, M. (2012, January 4–8). Mixed realitygame prototypes for upper body exercise and rehabilitation. Proceedings of the 2012 IEEE Virtual Reality Workshops (VRW), Costa Mesa, CA, USA.10.1109/VR.2012.6180940 ↗
15. Heimann-Steinert, A., Sattler, I., Otte, K., Röhling, H.M., Mansow-Model, S., and Müller-Werdan, U. (2019). Using New Camera-Based Technologies for Gait Analysis in Older Adults in Comparison to the Established GAITRite System. Sensors, 20.10.3390/s20010125 ↗
16. Volák, J., Koniar, D., Hargas, L., Jablončík, F., Sekel’Ova, N., and Durdík, P. (2018, January 21–23). RGB-D imaging used for OSAS diagnostics. Proceedings of the 2018 ELEKTRO, Mikulov, Czech Republic.10.1109/ELEKTRO.2018.8398326 ↗
17. Zhu, H., and Pun, C. (2013, January 26–28). Human action recognition with skeletal information from depth camera. Proceedings of the 2013 IEEE International Conference on Information and Automation (ICIA), Yinchuan, China.10.1109/ICInfA.2013.6720456 ↗
18. Wei, T., Lee, B., Qiao, Y., Kitsikidis, A., Dimitropoulos, K., and Grammalidis, N. (2015, January 8–10). Experimental study of skeleton tracking abilities from microsoft kinect non-frontal views. Proceedings of the 2015 3DTV-Conference: The True Vision—Capture, Transmission and Display of 3D Video (3DTV-CON), Lisbon, Portugal.10.1109/3DTV.2015.7169367 ↗
19. Chen, N., Chang, Y., Liu, H., Huang, L., and Zhang, H. (2018, January 25–27). Human Pose Recognition Based on Skeleton Fusion from Multiple Kinects. Proceedings of the 2018 37th Chinese Control Conference (CCC), Wuhan, China.10.23919/ChiCC.2018.8483016 ↗
20. Gündüz, A.F., Şen, M.O., Karci, A., and Yeroğlu, C. (2017, January 16–17). Artificial immune system optimization based duplex kinect skeleton fusion. Proceedings of the 2017 International Artificial Intelligence and Data Processing Symposium (IDAP), Malatya, Turkey.10.1109/IDAP.2017.8090248 ↗
21. Cao, M., and Hashimoto, H. (2013, January 10–13). Specific person recognition and tracking of mobile robot with Kinect 3D sensor. Proceedings of the IECON 2013–39th Annual Conference of the IEEE Industrial Electronics Society, Vienna, Austria.10.1109/IECON.2013.6700527 ↗
22. Chen, J., Wu, X., and Guo, T. (2014, January 4–7). 3-D real-time image matching based on kinect skeleton. Proceedings of the 2014 IEEE 27th Canadian Conference on Electrical and Computer Engineering (CCECE), Toronto, ON, Canada.
23. Fachri, M., Hudhajanto, R.P., and Mulyadi, I.H. (2019, January 2–3). Wayang Kulit Movement Control System Using Kinect Sensor. Proceedings of the 2019 2nd International Conference on Applied Engineering (ICAE), Batam, Indonesia.10.1109/ICAE47758.2019.9221840 ↗
24. Albert, J.A., Owolabi, V., Gebel, A., Brahms, C.M., Granacher, U., and Arnrich, B. (2020). Evaluation of the Pose Tracking Performance of the Azure Kinect and Kinect v2 for Gait Analysis in Comparison with a Gold Standard: A Pilot Study. Sensors, 20.10.3390/s20185104 ↗
25. Lee, C., Kim, J., Cho, S., Kim, J., Yoo, J., and Kwon, S. (2020). Development of Real-Time Hand Gesture Recognition for Tabletop Holographic Display Interaction Using Azure Kinect. Sensors, 20.10.3390/s20164566 ↗
26. Manghisi, V.M., Fiorentino, M., Boccaccio, A., Gattullo, M., Cascella, G.L., Toschi, N., Pietroiusti, A., and Uva, A.E. (2020). A Body Tracking-Based Low-Cost Solution for Monitoring Workers’ Hygiene Best Practices during Pandemics. Sensors, 20.10.3390/s20216149 ↗
27. Lee, S.-H., Yoo, J., Park, M., Kim, J., and Kwon, S. (2021). Robust Extrinsic Calibration of Multiple RGB-D Cameras with Body Tracking and Feature Matching. Sensors, 21.10.3390/s21031013 ↗
28. Foundations of Visual Linear Human–Robot Interaction via Pointing Gesture Navigation10.1007/s12369-017-0408-9 ↗
29. Tölgyessy, M., Dekan, M., Chovanec, Ľ., and Hubinský, P. (2021). Evaluation of the Azure Kinect and Its Comparison to Kinect V1 and Kinect V2. Sensors, 21.10.3390/s21020413 ↗
30. Efficient human pose estimation from single depth images10.1109/TPAMI.2012.241 ↗
31. Kinect range sensing: Structured-light versus Time-of-Flight Kinect10.1016/j.cviu.2015.05.006 ↗
32. Bamji, C.S., Mehta, S., Thompson, B., Elkhatib, T., Wurster, S., Akkaya, O., Payne, A., Godbaz, J., Fenton, M., and Rajasekaran, V. (2018, January 11–15). IMpixel 65nm BSI 320MHz demodulated TOF Image sensor with 3μm global shutter pixels and analog binning. Proceedings of the 2018 IEEE International Solid-State Circuits Conference-(ISSCC), San Francisco, CA, USA.10.1109/ISSCC.2018.8310200 ↗