Hand tracking - Revision history

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

2025-10-28T00:29:33Z

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

Show changes

Xinreality at 00:28, 28 October 2025

2025-10-28T00:28:24Z

Show changes

Xinreality: /* Optical and AI Pipeline */

2025-10-27T21:20:51Z

Optical and AI Pipeline

← Older revision		Revision as of 21:20, 27 October 2025
Line 112:		Line 112:
	A common approach is using one or more infrared or RGB cameras to visually capture the hands and then employing computer vision algorithms to recognize the hand's pose (the positions of the palm and each finger joint) in 3D space. Advanced [[machine learning]] models are often trained to detect keypoints of the hand (such as knuckle and fingertip positions) from the camera images, reconstructing an articulated hand model that updates as the user moves. A typical pipeline includes:		A common approach is using one or more infrared or RGB cameras to visually capture the hands and then employing computer vision algorithms to recognize the hand's pose (the positions of the palm and each finger joint) in 3D space. Advanced [[machine learning]] models are often trained to detect keypoints of the hand (such as knuckle and fingertip positions) from the camera images, reconstructing an articulated hand model that updates as the user moves. A typical pipeline includes:

	1. '''Detection''': Find hands in the camera frame (often with a palm detector)		#'''Detection''': Find hands in the camera frame (often with a palm detector)
	2. '''Landmark regression''': Predict 2D/3D keypoints for wrist and finger joints (commonly 21 landmarks per hand in widely used models)<ref name="MediaPipeHands" />		#'''Landmark regression''': Predict 2D/3D keypoints for wrist and finger joints (commonly 21 landmarks per hand in widely used models)<ref name="MediaPipeHands" />
	3. '''Pose / mesh estimation''': Fit a kinematic skeleton or hand mesh consistent with human biomechanics for stable interaction and animation		#'''Pose / mesh estimation''': Fit a kinematic skeleton or hand mesh consistent with human biomechanics for stable interaction and animation
	4. '''Temporal smoothing & prediction''': Filter jitter and manage short occlusions for responsive feedback		#'''Temporal smoothing & prediction''': Filter jitter and manage short occlusions for responsive feedback

	This positional data is then provided to the VR/AR system (often through standard interfaces like [[OpenXR]]) so that applications can respond to the user's hand gestures and contacts with virtual objects. Google's MediaPipe Hands, for example, infers 21 3D landmarks per hand from a single RGB frame and runs in real time on mobile-class hardware, illustrating the efficiency of modern approaches.<ref name="MediaPipeHands" />		This positional data is then provided to the VR/AR system (often through standard interfaces like [[OpenXR]]) so that applications can respond to the user's hand gestures and contacts with virtual objects. Google's MediaPipe Hands, for example, infers 21 3D landmarks per hand from a single RGB frame and runs in real time on mobile-class hardware, illustrating the efficiency of modern approaches.<ref name="MediaPipeHands" />

Xinreality: /* 2020s: AI-Driven Refinements and Mainstream Integration */

2025-10-27T21:20:35Z

2020s: AI-Driven Refinements and Mainstream Integration

← Older revision		Revision as of 21:20, 27 October 2025
Line 89:		Line 89:
	\| 1987 \|\| '''[[VPL DataGlove]]''' \|\| First commercial data glove measuring finger bend and hand orientation		\| 1987 \|\| '''[[VPL DataGlove]]''' \|\| First commercial data glove measuring finger bend and hand orientation
	\|-		\|-
	\| 2010 \|\| '''[[Microsoft Kinect''' \|\| Popularized full-body and hand tracking using IR depth camera for gaming		\| 2010 \|\| '''[[Microsoft Kinect]]''' \|\| Popularized full-body and hand tracking using IR depth camera for gaming
	\|-		\|-
	\| 2013 \|\| '''[[Leap Motion Controller]]''' \|\| Small USB peripheral with dual infrared cameras for high-precision hand tracking		\| 2013 \|\| '''[[Leap Motion Controller]]''' \|\| Small USB peripheral with dual infrared cameras for high-precision hand tracking

Xinreality at 21:20, 27 October 2025

2025-10-27T21:20:20Z

Show changes

Xinreality: /* Early Developments (1970s–1990s) */

2025-10-27T21:05:59Z

Early Developments (1970s–1990s)

← Older revision		Revision as of 21:05, 27 October 2025
Line 23:		Line 23:

	=== Early Developments (1970s–1990s) ===		=== Early Developments (1970s–1990s) ===
	The foundational milestone occurred in 1977 with the invention of the '''Sayre Glove''', a wired data glove developed by electronic visualization pioneer Daniel Sandin and computer graphics researcher Thomas DeFanti at the University of Illinois at Chicago's Electronic Visualization Laboratory (EVL). Inspired by an idea from colleague Rich Sayre, the glove used optical flex sensors—light emitters paired with photocells embedded in the fingers—to measure joint angles and finger bends. Light intensity variations were converted into electrical signals, enabling basic gesture recognition and hand posture tracking for early VR simulations.<ref name="SayreGlove" /><ref name="SenseGlove" /> This device, considered the first data glove, established the principle of measuring finger flexion for computer input.		The foundational milestone occurred in 1977 with the invention of the '''[[Sayre Glove]]''', a wired data glove developed by electronic visualization pioneer Daniel Sandin and computer graphics researcher Thomas DeFanti at the University of Illinois at Chicago's Electronic Visualization Laboratory (EVL). Inspired by an idea from colleague Rich Sayre, the glove used optical flex sensors—light emitters paired with photocells embedded in the fingers—to measure joint angles and finger bends. Light intensity variations were converted into electrical signals, enabling basic gesture recognition and hand posture tracking for early VR simulations.<ref name="SayreGlove" /><ref name="SenseGlove" /> This device, considered the first data glove, established the principle of measuring finger flexion for computer input.

	In 1983, Gary Grimes of Bell Labs developed the '''Digital Data Entry Glove''', a more sophisticated system patented as an alternative to keyboard input. This device integrated flex sensors, touch sensors, and tilt sensors to recognize unique hand positions corresponding to alphanumeric characters, specifically gestures from the American Sign Language manual alphabet.<ref name="BellGlove" />		In 1983, Gary Grimes of Bell Labs developed the '''[[Digital Data Entry Glove]]''', a more sophisticated system patented as an alternative to keyboard input. This device integrated flex sensors, touch sensors, and tilt sensors to recognize unique hand positions corresponding to alphanumeric characters, specifically gestures from the American Sign Language manual alphabet.<ref name="BellGlove" />

	The 1980s saw the emergence of the first commercially viable data gloves, largely driven by the work of Thomas Zimmerman and [[Jaron Lanier]]. Zimmerman patented an optical flex sensor in 1982 and later co-founded VPL Research with Lanier in 1985. VPL Research became the first company to sell VR hardware, including the iconic '''DataGlove''', which was released commercially in 1987.<ref name="VPL" /><ref name="VirtualSpeech" /> The DataGlove used fiber optic cables to measure finger bends and was typically paired with a [[Polhemus]] magnetic tracking system for positional data. This became an iconic symbol of early VR technology.		The 1980s saw the emergence of the first commercially viable data gloves, largely driven by the work of Thomas Zimmerman and [[Jaron Lanier]]. Zimmerman patented an optical flex sensor in 1982 and later co-founded VPL Research with Lanier in 1985. VPL Research became the first company to sell VR hardware, including the iconic '''[[DataGlove]]''', which was released commercially in 1987.<ref name="VPL" /><ref name="VirtualSpeech" /> The DataGlove used fiber optic cables to measure finger bends and was typically paired with a [[Polhemus]] magnetic tracking system for positional data. This became an iconic symbol of early VR technology.

	In 1989, Mattel released the '''~~Nintendo~~ [[Power Glove]]''', a low-cost consumer version licensed from VPL Research, which used resistive ink flex sensors and ultrasonic emitters for positional tracking. This was the first affordable, mass-market data glove for consumers, popularizing the concept of gestural control in gaming.<ref name="PowerGlove" />		In 1989, Mattel released the '''[[Nintendo Power Glove]]''', a low-cost consumer version licensed from VPL Research, which used resistive ink flex sensors and ultrasonic emitters for positional tracking. This was the first affordable, mass-market data glove for consumers, popularizing the concept of gestural control in gaming.<ref name="PowerGlove" />

	Throughout the 1990s, hand tracking advanced with the integration of more sophisticated sensors into VR systems. Researchers at MIT's Media Lab built on the Sayre Glove, incorporating electromagnetic and inertial measurement unit (IMU) sensors for improved positional tracking. These systems, often tethered to workstations, supported rudimentary interactions but were limited by wiring and low resolution. The '''CyberGlove''' (early 1990s) by Virtual Technologies used thin foil strain gauges sewn into fabric to measure up to 22 joint angles, becoming a high-precision glove used in research and professional applications.<ref name="AvatarAcademy" />		Throughout the 1990s, hand tracking advanced with the integration of more sophisticated sensors into VR systems. Researchers at MIT's Media Lab built on the Sayre Glove, incorporating electromagnetic and inertial measurement unit (IMU) sensors for improved positional tracking. These systems, often tethered to workstations, supported rudimentary interactions but were limited by wiring and low resolution. The '''[[CyberGlove]]''' (early 1990s) by Virtual Technologies used thin foil strain gauges sewn into fabric to measure up to 22 joint angles, becoming a high-precision glove used in research and professional applications.<ref name="AvatarAcademy" />

	{\| class="wikitable sortable"		{\| class="wikitable sortable"

Xinreality at 21:04, 27 October 2025

2025-10-27T21:04:46Z

← Older revision		Revision as of 21:04, 27 October 2025
Line 10:		Line 10:
	\| applications = Gaming, training, healthcare, productivity, accessibility, social VR		\| applications = Gaming, training, healthcare, productivity, accessibility, social VR
	}}		}}

			[[File:hand tracking1.jpg\|300px\|right]]

	'''Hand tracking''' is a [[computer vision]]-based technology used in [[virtual reality]] (VR), [[augmented reality]] (AR), and [[mixed reality]] (MR) systems to detect, track, and interpret the position, orientation, and movements of a user's hands and fingers in real time. Unlike traditional input methods such as [[motion controller\|controllers]] or gloves, hand tracking enables controller-free, natural interactions by leveraging cameras, sensors, and artificial intelligence (AI) algorithms to map hand poses into virtual environments.<ref name="Frontiers2021" /> This technology enhances immersion, presence, and usability in [[extended reality]] (XR) applications by allowing users to perform gestures like pointing, grabbing, pinching, and swiping directly with their bare hands.		'''Hand tracking''' is a [[computer vision]]-based technology used in [[virtual reality]] (VR), [[augmented reality]] (AR), and [[mixed reality]] (MR) systems to detect, track, and interpret the position, orientation, and movements of a user's hands and fingers in real time. Unlike traditional input methods such as [[motion controller\|controllers]] or gloves, hand tracking enables controller-free, natural interactions by leveraging cameras, sensors, and artificial intelligence (AI) algorithms to map hand poses into virtual environments.<ref name="Frontiers2021" /> This technology enhances immersion, presence, and usability in [[extended reality]] (XR) applications by allowing users to perform gestures like pointing, grabbing, pinching, and swiping directly with their bare hands.

Xinreality at 14:27, 26 October 2025

2025-10-26T14:27:30Z

← Older revision		Revision as of 14:27, 26 October 2025
Line 327:		Line 327:
	</references>		</references>

	[[Category:~~Virtual reality]]~~		[[Category:Terms]]
	~~[[Category:Augmented reality~~]]
	[[Category:Computer vision]]		[[Category:Computer vision]]
	[[Category:Human-computer interaction]]		[[Category:Human-computer interaction]]

Xinreality at 14:26, 26 October 2025

2025-10-26T14:26:30Z

Show changes

Xinreality: Created page with "{{Infobox technology | name = Hand tracking | image = | caption = A user interacting with a virtual interface using optical hand tracking | type = Computer vision / Gesture recognition / Natural user interface technology | invention_date = 1977 (Sayre Glove) | inventor = Daniel Sandin, Thomas DeFanti, Richard Sayre | fields = Virtual reality, Augmented reality, Mixed reality | related = Gesture recognitio..."

2025-10-26T14:20:09Z

Created page with "{{Infobox technology | name = Hand tracking | image =  | caption = A user interacting with a virtual interface using optical hand tracking | type = Computer vision / Gesture recognition / Natural user interface technology | invention_date = 1977 (Sayre Glove) | inventor = Daniel Sandin, Thomas DeFanti, Richard Sayre | fields = Virtual reality, Augmented reality, Mixed reality | related = Gesture recognitio..."

Show changes