Markerless outside-in tracking - Revision history

Xinreality: Text replacement - "e.g.," to "for example"

2025-05-07T21:30:24Z

Text replacement - "e.g.," to "for example"

← Older revision		Revision as of 21:30, 7 May 2025
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 (~~e.g.,~~ the Randomised Decision Forest used in the original Kinect).<ref name="Shotton2011" />		* '''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 (~~e.g.,~~ [[OpenNI]]/NITE, the [[Microsoft Kinect]] SDK) expose joint-stream APIs for developers.<ref name="OpenNI2013" />		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==

Xinreality at 09:15, 3 May 2025

2025-05-03T09:15:49Z

← Older revision		Revision as of 09:15, 3 May 2025
Line 53:		Line 53:

	==References==		==References==
	<ref name="Shotton2011">Shotton, ~~Jamie~~; Fitzgibbon, ~~Andrew~~; Cook, ~~Mat~~; Sharp, ~~Toby~~; Finocchio, ~~Mark~~; Moore, ~~Bob~~; Kipman, ~~Alex~~; Blake, ~~Andrew (2011)~~. ~~Real-Time~~ Human Pose Recognition in Parts from a Single Depth Image. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) ~~2011~~		<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>
	~~microsoft~~.~~com~~		<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">~~Zeng, Wenjun;~~ Zhang, ~~Zhengyou (2012)~~. ~~Microsoft~~ Kinect Sensor and Its Effect. ~~IEEE MultiMedia~~, 19(2)~~:4–10~~		<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>
	~~microsoft.com~~		<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">~~OpenNI Foundation (2010)~~. OpenNI 1.5.2 User Guide. ~~“OpenNI is an open source API that is publicly available~~ at www.~~OpenNI~~.~~org~~.~~”:contentReference[oaicite:2]{index=2}~~.</ref>		<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, ~~Andreas~~; West, ~~Niels~~; ~~et al. (2022)~~. ~~Applications~~ and ~~limitations~~ of ~~current markerless motion capture methods~~ for ~~clinical gait biomechanics~~. Journal of Biomechanics, ~~129~~:110844. “While markerless temporospatial measures generally appear equivalent to marker-based systems, joint center locations and joint angles are not yet sufficiently accurate for clinical applications.”		<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>
	~~pmc~~.ncbi.nlm.nih.gov
	.</ref>
	<ref name="Pham2004">Pham, ~~Alex (2004-01-18)~~. ~~EyeToy~~ Springs From One Man’s Vision. ~~Los Angeles Times~~. ~~“the $50 EyeToy, a tiny camera that enables video game players to control the action by jumping around and waving their arms…”~~
	latimes.com
	.</ref>
	<ref name="Microsoft2010">Microsoft News Center ~~(2010-11-04)~~. ~~The~~ Future of Entertainment Starts Today as Kinect for ~~Xbox 360~~ Leaps and Lands at Retailers Nationwide. ~~“Kinect for Xbox 360 lets you use your body and voice to play your favorite games~~.~~.. No buttons. No barriers. Just you.”~~
	news.microsoft.com
	.</ref>
	<ref name="Lange2011">Lange, ~~Belinda~~; Rizzo, ~~Skip~~; Chang, ~~Chien~~-~~Yen~~; Suma, ~~Evan A~~.; Bolas, ~~Mark (2011)~~. ~~Markerless~~ Full Body Tracking: ~~Depth-Sensing~~ Technology within Virtual Environments. ~~Proc.~~ I/ITSEC 2011. ~~“FAAST is middleware to facilitate integration of full-body control with virtual reality applications~~... (~~e.g. Microsoft Kinect~~)~~.”~~
	~~illusioneering.cs.umn.edu~~
	.</ref>
	<ref name="Microsoft2017">Good, ~~Owen S~~. ~~(2017-10-25)~~. ~~Kinect is officially dead~~. Really. Officially. It’s ~~dead~~. Polygon. ~~“Microsoft has confirmed it is no longer manufacturing Kinect and none will be sold once retailers run out~~.”
	polygon.com
	.</ref>

Xinreality at 17:45, 30 April 2025

2025-04-30T17:45:31Z

Xinreality: Undo revision 34791 by Xinreality (talk)

2025-04-30T17:37:28Z

Undo revision 34791 by Xinreality (talk)

Show changes

Xinreality at 17:36, 30 April 2025

2025-04-30T17:36:44Z

Show changes

Xinreality at 17:31, 30 April 2025

2025-04-30T17:31:23Z

← Older revision		Revision as of 17:31, 30 April 2025
Line 60:		Line 60:
	.</ref>		.</ref>
	<ref name="OpenNI2013">OpenNI Foundation (2010). OpenNI 1.5.2 User Guide. “OpenNI is an open source API that is publicly available at www.OpenNI.org.”:contentReference[oaicite:2]{index=2}.</ref>		<ref name="OpenNI2013">OpenNI Foundation (2010). OpenNI 1.5.2 User Guide. “OpenNI is an open source API that is publicly available at www.OpenNI.org.”:contentReference[oaicite:2]{index=2}.</ref>
	<ref>Pfister, Andreas; West, Niels; et al. (2022). Applications and limitations of current markerless motion capture methods for clinical gait biomechanics. Journal of Biomechanics, 129:110844. “While markerless temporospatial measures generally appear equivalent to marker-based systems, joint center locations and joint angles are not yet sufficiently accurate for clinical applications.”		<ref name="Pfister2022">Pfister, Andreas; West, Niels; et al. (2022). Applications and limitations of current markerless motion capture methods for clinical gait biomechanics. Journal of Biomechanics, 129:110844. “While markerless temporospatial measures generally appear equivalent to marker-based systems, joint center locations and joint angles are not yet sufficiently accurate for clinical applications.”
	pmc.ncbi.nlm.nih.gov		pmc.ncbi.nlm.nih.gov
	.</ref>		.</ref>
	<ref>Pham, Alex (2004-01-18). EyeToy Springs From One Man’s Vision. Los Angeles Times. “the $50 EyeToy, a tiny camera that enables video game players to control the action by jumping around and waving their arms…”		<ref name="Pham2004">Pham, Alex (2004-01-18). EyeToy Springs From One Man’s Vision. Los Angeles Times. “the $50 EyeToy, a tiny camera that enables video game players to control the action by jumping around and waving their arms…”
	latimes.com		latimes.com
	.</ref>		.</ref>
Line 69:		Line 69:
	news.microsoft.com		news.microsoft.com
	.</ref>		.</ref>
	<ref>Lange, Belinda; Rizzo, Skip; Chang, Chien-Yen; Suma, Evan A.; Bolas, Mark (2011). Markerless Full Body Tracking: Depth-Sensing Technology within Virtual Environments. Proc. I/ITSEC 2011. “FAAST is middleware to facilitate integration of full-body control with virtual reality applications... (e.g. Microsoft Kinect).”		<ref name="Lange2011">Lange, Belinda; Rizzo, Skip; Chang, Chien-Yen; Suma, Evan A.; Bolas, Mark (2011). Markerless Full Body Tracking: Depth-Sensing Technology within Virtual Environments. Proc. I/ITSEC 2011. “FAAST is middleware to facilitate integration of full-body control with virtual reality applications... (e.g. Microsoft Kinect).”
	illusioneering.cs.umn.edu		illusioneering.cs.umn.edu
	.</ref>		.</ref>

Xinreality at 17:21, 30 April 2025

2025-04-30T17:21:40Z

Xinreality at 17:20, 30 April 2025

2025-04-30T17:20:26Z

← Older revision		Revision as of 17:20, 30 April 2025
Line 72:		Line 72:
	illusioneering.cs.umn.edu		illusioneering.cs.umn.edu
	.</ref>		.</ref>
	<ref>Good, Owen S. (2017-10-25). Kinect is officially dead. Really. Officially. It’s dead. Polygon. “Microsoft has confirmed it is no longer manufacturing Kinect and none will be sold once retailers run out.”		<ref name="Microsoft2017">Good, Owen S. (2017-10-25). Kinect is officially dead. Really. Officially. It’s dead. Polygon. “Microsoft has confirmed it is no longer manufacturing Kinect and none will be sold once retailers run out.”
	polygon.com		polygon.com
	.</ref>		.</ref>

Xinreality at 17:19, 30 April 2025

2025-04-30T17:19:01Z

← Older revision		Revision as of 17:19, 30 April 2025
Line 56:		Line 56:
	microsoft.com		microsoft.com
	.</ref>		.</ref>
	<ref>Zeng, Wenjun; Zhang, Zhengyou (2012). Microsoft Kinect Sensor and Its Effect. IEEE MultiMedia, 19(2):4–10		<ref name="Zhang2012">Zeng, Wenjun; Zhang, Zhengyou (2012). Microsoft Kinect Sensor and Its Effect. IEEE MultiMedia, 19(2):4–10
	microsoft.com		microsoft.com
	.</ref>		.</ref>
	<ref>OpenNI Foundation (2010). OpenNI 1.5.2 User Guide. “OpenNI is an open source API that is publicly available at www.OpenNI.org.”:contentReference[oaicite:2]{index=2}.</ref>		<ref name="OpenNI2013">OpenNI Foundation (2010). OpenNI 1.5.2 User Guide. “OpenNI is an open source API that is publicly available at www.OpenNI.org.”:contentReference[oaicite:2]{index=2}.</ref>
	<ref>Pfister, Andreas; West, Niels; et al. (2022). Applications and limitations of current markerless motion capture methods for clinical gait biomechanics. Journal of Biomechanics, 129:110844. “While markerless temporospatial measures generally appear equivalent to marker-based systems, joint center locations and joint angles are not yet sufficiently accurate for clinical applications.”		<ref>Pfister, Andreas; West, Niels; et al. (2022). Applications and limitations of current markerless motion capture methods for clinical gait biomechanics. Journal of Biomechanics, 129:110844. “While markerless temporospatial measures generally appear equivalent to marker-based systems, joint center locations and joint angles are not yet sufficiently accurate for clinical applications.”
	pmc.ncbi.nlm.nih.gov		pmc.ncbi.nlm.nih.gov
Line 66:		Line 66:
	latimes.com		latimes.com
	.</ref>		.</ref>
	<ref>Microsoft News Center (2010-11-04). The Future of Entertainment Starts Today as Kinect for Xbox 360 Leaps and Lands at Retailers Nationwide. “Kinect for Xbox 360 lets you use your body and voice to play your favorite games... No buttons. No barriers. Just you.”		<ref name="Microsoft2010">Microsoft News Center (2010-11-04). The Future of Entertainment Starts Today as Kinect for Xbox 360 Leaps and Lands at Retailers Nationwide. “Kinect for Xbox 360 lets you use your body and voice to play your favorite games... No buttons. No barriers. Just you.”
	news.microsoft.com		news.microsoft.com
	.</ref>		.</ref>

Xinreality at 17:17, 30 April 2025

2025-04-30T17:17:16Z

← Older revision		Revision as of 17:17, 30 April 2025
Line 53:		Line 53:

	==References==		==References==
	<ref>Shotton, Jamie; Fitzgibbon, Andrew; Cook, Mat; Sharp, Toby; Finocchio, Mark; Moore, Bob; Kipman, Alex; Blake, Andrew (2011). Real-Time Human Pose Recognition in Parts from a Single Depth Image. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2011		<ref name="Shotton2011">Shotton, Jamie; Fitzgibbon, Andrew; Cook, Mat; Sharp, Toby; Finocchio, Mark; Moore, Bob; Kipman, Alex; Blake, Andrew (2011). Real-Time Human Pose Recognition in Parts from a Single Depth Image. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2011
	microsoft.com		microsoft.com
	.</ref>		.</ref>

← Older revision		Revision as of 17:45, 30 April 2025
Line 3:		Line 3:

	==Introduction==		==Introduction==
	'''[[Markerless outside-in tracking]]''' is a subtype of [[positional tracking]] used in [[virtual reality]] (VR) and [[augmented reality]] (AR). In this approach, external [[camera]]s or other [[depth sensing]] devices positioned in the environment estimate the six-degree-of-freedom pose of a user or object without relying on any [[fiducial marker]]s. Instead, [[computer vision]] algorithms analyse the incoming colour or depth stream to detect and follow natural scene features or the user’s own body, enabling real-time [[motion capture]] and interaction.<ref name="Shotton2011" />		'''[[Markerless outside-in tracking]]''' is a subtype of [[positional tracking]] used in [[virtual reality]] (VR) and [[augmented reality]] (AR). In this approach, external [[camera]]s or other [[depth sensing]] devices positioned in the environment estimate the six-degree-of-freedom ([[6DOF]]) [[pose]] of a user or object without relying on any [[fiducial marker]]s. Instead, [[computer vision]] algorithms analyse the incoming colour or depth stream to detect and follow natural scene features or the user’s own body, enabling real-time [[motion capture]] and interaction.<ref name="Shotton2011" />

	==Underlying technology==		==Underlying technology==
	A typical markerless outside-in pipeline combines specialised hardware with software-based human-pose estimation:		A typical markerless outside-in pipeline combines specialised hardware with software-based human-pose estimation:

	* 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 (e.g., the Randomised Decision Forest used in the original Kinect).<ref name="Shotton2011" />		* '''Per-pixel body-part classification''' – A machine-learning model labels each pixel as “head”, “hand”, “torso”, and so on (e.g., 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 (e.g., [[OpenNI]]/NITE, the Microsoft Kinect SDK) expose joint-stream APIs for developers.<ref name="OpenNI2013" />		Although a single camera can suffice, multi-camera rigs extend coverage and mitigate occlusion problems. Open source and proprietary middleware (e.g., [[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==
	Marker-based outside-in systems (HTC Vive Lighthouse, PlayStation VR) attach active LEDs or retro-reflective spheres to the headset or controllers; external sensors triangulate these explicit targets, achieving sub-millimetre precision and sub-10 ms latency. Markerless alternatives dispense with physical targets, improving user comfort and reducing setup time, but at the cost of:		[[Outside-in tracking\|Marker-based outside-in systems]] ([[HTC Vive]] [[Lighthouse]], [[PlayStation VR]) attach active LEDs or retro-reflective spheres to the headset or controllers; external sensors triangulate these explicit targets, achieving sub-millimetre precision and sub-10 ms latency. Markerless alternatives dispense with physical targets, improving user comfort and reducing setup time, but at the cost of:

	* Lower positional accuracy and higher latency – Depth-sensor noise and computational overhead introduce millimetre- to centimetre-level error and ~20–30 ms end-to-end latency.		* '''Lower positional accuracy and higher latency''' – Depth-sensor noise and computational overhead introduce millimetre- to centimetre-level error and ~20–30 ms end-to-end latency.
	* Sensitivity to occlusion – If a body part leaves the camera’s line of sight, the model loses track until the part re-enters view.		* '''Sensitivity to occlusion''' – If a body part leaves the camera’s line of sight, the model loses track until the part re-enters view.

	==History and notable systems==		==History and notable systems==
Line 35:		Line 35:

	==Applications==		==Applications==
	* Gaming and Entertainment – Titles like ''Kinect Sports'' mapped whole-body actions directly onto avatars. Enthusiast VR chat platforms still use Kinect skeletons to animate full-body avatars.		* '''Gaming and Entertainment''' – Titles like ''Kinect Sports'' mapped whole-body actions directly onto avatars. Enthusiast VR chat platforms still use Kinect skeletons to animate full-body avatars.
	* Rehabilitation and Exercise – Clinicians employ depth-based pose tracking to monitor range-of-motion exercises without encumbering patients with sensors.		* '''Rehabilitation and Exercise''' – Clinicians employ depth-based pose tracking to monitor range-of-motion exercises without encumbering patients with sensors.
	* Interactive installations – Museums deploy wall-mounted depth cameras to create “magic-mirror” AR exhibits that overlay virtual costumes onto visitors in real time.		* '''Interactive installations''' – Museums deploy wall-mounted depth cameras to create “magic-mirror” AR exhibits that overlay virtual costumes onto visitors in real time.
	* Telepresence – Multi-Kinect arrays stream volumetric representations of remote participants into shared virtual spaces.		* '''Telepresence''' – Multi-Kinect arrays stream volumetric representations of remote participants into shared virtual spaces.

	==Advantages==		==Advantages==

← Older revision		Revision as of 17:21, 30 April 2025
Line 18:		Line 18:
	Marker-based outside-in systems (HTC Vive Lighthouse, PlayStation VR) attach active LEDs or retro-reflective spheres to the headset or controllers; external sensors triangulate these explicit targets, achieving sub-millimetre precision and sub-10 ms latency. Markerless alternatives dispense with physical targets, improving user comfort and reducing setup time, but at the cost of:		Marker-based outside-in systems (HTC Vive Lighthouse, PlayStation VR) attach active LEDs or retro-reflective spheres to the headset or controllers; external sensors triangulate these explicit targets, achieving sub-millimetre precision and sub-10 ms latency. Markerless alternatives dispense with physical targets, improving user comfort and reducing setup time, but at the cost of:

	* Lower positional accuracy and higher latency – Depth-sensor noise and computational overhead introduce millimetre- to centimetre-level error and ~20–30 ms end-to-end latency.~~<ref name="Baker2016" />~~		* Lower positional accuracy and higher latency – Depth-sensor noise and computational overhead introduce millimetre- to centimetre-level error and ~20–30 ms end-to-end latency.
	* Sensitivity to occlusion – If a body part leaves the camera’s line of sight, the model loses track until the part re-enters view.		* Sensitivity to occlusion – If a body part leaves the camera’s line of sight, the model loses track until the part re-enters view.

Line 25:		Line 25:
	! Year !! System !! Notes		! Year !! System !! Notes
	\|-		\|-
	\| 2003 \|\| [[EyeToy]] (PlayStation 2) \|\| 2-D silhouette tracking with a single RGB camera for casual gesture-based games.~~<ref name="Sony2003" />~~		\| 2003 \|\| [[EyeToy]] (PlayStation 2) \|\| 2-D silhouette tracking with a single RGB camera for casual gesture-based games.
	\|-		\|-
	\| 2010 \|\| [[Kinect]] for Xbox 360 \|\| Consumer launch of a structured-light depth sensor delivering real-time full-body skeletons (up to six users).<ref name="Microsoft2010" />		\| 2010 \|\| [[Kinect]] for Xbox 360 \|\| Consumer launch of a structured-light depth sensor delivering real-time full-body skeletons (up to six users).<ref name="Microsoft2010" />
	\|-		\|-
	\| 2014 – 2016 \|\| Research prototypes \|\| Studies showed Kinect V2 could supply 6-DOF head, hand, and body input to DIY VR HMDs.~~<ref name="KinectVRStudy" />~~		\| 2014 – 2016 \|\| Research prototypes \|\| Studies showed Kinect V2 could supply 6-DOF head, hand, and body input to DIY VR HMDs.
	\|-		\|-
	\| 2017 \|\| Kinect production ends \|\| Microsoft discontinued Kinect hardware as commercial VR shifted toward marker-based and inside-out solutions.<ref name="Microsoft2017" />		\| 2017 \|\| Kinect production ends \|\| Microsoft discontinued Kinect hardware as commercial VR shifted toward marker-based and inside-out solutions.<ref name="Microsoft2017" />
Line 36:		Line 36:
	==Applications==		==Applications==
	* Gaming and Entertainment – Titles like ''Kinect Sports'' mapped whole-body actions directly onto avatars. Enthusiast VR chat platforms still use Kinect skeletons to animate full-body avatars.		* Gaming and Entertainment – Titles like ''Kinect Sports'' mapped whole-body actions directly onto avatars. Enthusiast VR chat platforms still use Kinect skeletons to animate full-body avatars.
	* Rehabilitation and Exercise – Clinicians employ depth-based pose tracking to monitor range-of-motion exercises without encumbering patients with sensors.~~<ref name="Baker2016" />~~		* Rehabilitation and Exercise – Clinicians employ depth-based pose tracking to monitor range-of-motion exercises without encumbering patients with sensors.
	* Interactive installations – Museums deploy wall-mounted depth cameras to create “magic-mirror” AR exhibits that overlay virtual costumes onto visitors in real time.		* Interactive installations – Museums deploy wall-mounted depth cameras to create “magic-mirror” AR exhibits that overlay virtual costumes onto visitors in real time.
	* Telepresence – Multi-Kinect arrays stream volumetric representations of remote participants into shared virtual spaces.		* Telepresence – Multi-Kinect arrays stream volumetric representations of remote participants into shared virtual spaces.
Line 48:		Line 48:
	==Disadvantages==		==Disadvantages==
	* '''Occlusion sensitivity''' – Furniture or other players can block the line of sight, causing intermittent loss of tracking.		* '''Occlusion sensitivity''' – Furniture or other players can block the line of sight, causing intermittent loss of tracking.
	* '''Reduced accuracy and jitter''' – Compared with marker-based solutions, joint estimates exhibit higher positional noise, especially during fast or complex motion.~~<ref name="Baker2016" />~~		* '''Reduced accuracy and jitter''' – Compared with marker-based solutions, joint estimates exhibit higher positional noise, especially during fast or complex motion.
	* '''Environmental constraints''' – Bright sunlight, glossy surfaces, and feature-poor backgrounds degrade depth or feature extraction quality.		* '''Environmental constraints''' – Bright sunlight, glossy surfaces, and feature-poor backgrounds degrade depth or feature extraction quality.
	* '''Limited range and FOV''' – Most consumer depth cameras operate effectively only within 0.8–5 m; beyond that, depth resolution and skeleton stability decrease.		* '''Limited range and FOV''' – Most consumer depth cameras operate effectively only within 0.8–5 m; beyond that, depth resolution and skeleton stability decrease.