Markerless outside-in tracking: Difference between revisions
Xinreality (talk | contribs) No edit summary |
Xinreality (talk | contribs) m Text replacement - "e.g.," to "for example" Tags: Mobile edit Mobile web edit |
||
| (One intermediate revision by the same user not shown) | |||
| Line 10: | Line 10: | ||
* '''Sensing layer''' – One or more fixed [[RGB-D]] or [[infrared]] depth cameras acquire per-frame point clouds. Commodity devices such as the Microsoft Kinect project a [[structured light]] pattern or use [[time-of-flight]] methods to compute depth maps.<ref name="Zhang2012" /> | * '''Sensing layer''' – One or more fixed [[RGB-D]] or [[infrared]] depth cameras acquire per-frame point clouds. Commodity devices such as the Microsoft Kinect project a [[structured light]] pattern or use [[time-of-flight]] methods to compute depth maps.<ref name="Zhang2012" /> | ||
* '''Segmentation''' – Foreground extraction or person segmentation isolates user pixels from the static background. | * '''Segmentation''' – Foreground extraction or person segmentation isolates user pixels from the static background. | ||
* '''Per-pixel body-part classification''' – A machine-learning model labels each pixel as “head”, “hand”, “torso”, and so on ( | * '''Per-pixel body-part classification''' – A machine-learning model labels each pixel as “head”, “hand”, “torso”, and so on (for example the Randomised Decision Forest used in the original Kinect).<ref name="Shotton2011" /> | ||
* '''Skeletal reconstruction and filtering''' – The system fits a kinematic skeleton to the classified pixels and applies temporal filtering to reduce jitter, producing smooth head- and hand-pose data that can drive VR/AR applications. | * '''Skeletal reconstruction and filtering''' – The system fits a kinematic skeleton to the classified pixels and applies temporal filtering to reduce jitter, producing smooth head- and hand-pose data that can drive VR/AR applications. | ||
Although a single camera can suffice, multi-camera rigs extend coverage and mitigate occlusion problems. Open source and proprietary middleware ( | Although a single camera can suffice, multi-camera rigs extend coverage and mitigate occlusion problems. Open source and proprietary middleware (for example [[OpenNI]]/NITE, the [[Microsoft Kinect]] SDK) expose joint-stream APIs for developers.<ref name="OpenNI2013" /> | ||
==Markerless vs. marker-based tracking== | ==Markerless vs. marker-based tracking== | ||
| Line 53: | Line 53: | ||
==References== | ==References== | ||
<ref name="Shotton2011">Shotton, | <ref name="Shotton2011">Shotton, J.; Fitzgibbon, A.; Cook, M.; Sharp, T.; Finocchio, M.; Moore, R.; Kipman, A.; Blake, A. “Real‑Time Human Pose Recognition in Parts from a Single Depth Image.” *Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)*, 2011, pp. 1297–1304. DOI: 10.1109/CVPR.2011.5995316. Available at: https://ieeexplore.ieee.org/document/5995316 (accessed 3 May 2025).</ref> | ||
<ref name="Zhang2012">Zhang, Z. “Microsoft Kinect Sensor and Its Effect.” *IEEE MultiMedia*, vol. 19, no. 2, 2012, pp. 4–10. DOI: 10.1109/MMUL.2012.24. Available at: https://dl.acm.org/doi/10.1109/MMUL.2012.24 (accessed 3 May 2025).</ref> | |||
.</ref> | <ref name="OpenNI2013">OpenNI Foundation. *OpenNI 1.5.2 User Guide*, 2010. PDF. Available at: https://www.cs.rochester.edu/courses/577/fall2011/kinect/openni-user-guide.pdf (accessed 3 May 2025).</ref> | ||
<ref name="Zhang2012"> | <ref name="Pfister2022">Pfister, A.; West, N.; et al. “Applications and Limitations of Current Markerless Motion Capture Methods for Clinical Gait Biomechanics.” *Journal of Biomechanics*, vol. 129, 2022, Article 110844. DOI: 10.1016/j.jbiomech.2021.110844. Available at: https://pubmed.ncbi.nlm.nih.gov/35237469/ (accessed 3 May 2025).</ref> | ||
<ref name="Pham2004">Pham, A. “EyeToy Springs From One Man’s Vision.” *Los Angeles Times*, 18 Jan 2004. Available at: https://www.latimes.com/archives/la-xpm-2004-jan-18-fi-eyetoy18-story.html (accessed 3 May 2025).</ref> | |||
.</ref> | <ref name="Microsoft2010">Microsoft News Center. “The Future of Entertainment Starts Today as Kinect for Xbox 360 Leaps and Lands at Retailers Nationwide.” Press release, 4 Nov 2010. Available at: https://news.microsoft.com/2010/11/04/the-future-of-entertainment-starts-today-as-kinect-for-xbox-360-leaps-and-lands-at-retailers-nationwide/ (accessed 3 May 2025).</ref> | ||
<ref name="OpenNI2013"> | <ref name="Lange2011">Lange, B.; Rizzo, A.; Chang, C.-Y.; Suma, E. A.; Bolas, M. “Markerless Full Body Tracking: Depth‑Sensing Technology within Virtual Environments.” *Interservice/Industry Training, Simulation and Education Conference (I/ITSEC)*, 2011. PDF. Available at: http://ict.usc.edu/pubs/Markerless%20Full%20Body%20Tracking-%20Depth-Sensing%20Technology%20within%20Virtual%20Environments.pdf (accessed 3 May 2025).</ref> | ||
<ref name="Pfister2022">Pfister, | <ref name="Microsoft2017">Good, O. S. “Kinect Is Officially Dead. Really. Officially. It’s Dead.” *Polygon*, 25 Oct 2017. Available at: https://www.polygon.com/2017/10/25/16543192/kinect-discontinued-microsoft-announcement (accessed 3 May 2025).</ref> | ||
.</ref> | |||
<ref name="Pham2004">Pham, | |||
latimes.com | |||
.</ref> | |||
<ref name="Microsoft2010">Microsoft News Center | |||
news.microsoft.com | |||
.</ref> | |||
<ref name="Lange2011">Lange, | |||
.</ref> | |||
<ref name="Microsoft2017">Good, | |||
polygon.com | |||
.</ref> | |||