Camera-based Input - Revision history

Latha Serevi at 15:47, 26 March 2010

2010-03-26T15:47:38Z

← Older revision		Revision as of 08:47, 26 March 2010
Line 8:		Line 8:
	Quick Summary:		Quick Summary:
	Several replies immediately followed that suggested hardware options beyond a normal webcam. These mainly included 3D cams and remote sensors. The discussion thread continued into details of what to expect from different device drivers. The details ranged from ability to track eye gaze to comments about the device's user-friendliness. Later on in the discussion, several people described needs on the interface, and this discussion quickly went into generic and universal interface design. As the thread quited down, at least a few people seemed to agree that a simple generic interface is a good start point. More specifically, one that can use input from a normal webcam, recognize a few common gestures, and play the related avatar animation much like one now can type /yes or /no and have the head nod. It was also mentioned that the simple interface would not require server changes to implement. Further discussion points out the distinction between SL gestures and human gesture and suggests that basic tracking is the low-hanging fruit rather than a simple interface.		Several replies immediately followed that suggested hardware options beyond a normal webcam. These mainly included 3D cams and remote sensors. The discussion thread continued into details of what to expect from different device drivers. The details ranged from ability to track eye gaze to comments about the device's user-friendliness. Later on in the discussion, several people described needs on the interface, and this discussion quickly went into generic and universal interface design. As the thread quited down, at least a few people seemed to agree that a simple generic interface is a good start point. More specifically, one that can use input from a normal webcam, recognize a few common gestures, and play the related avatar animation much like one now can type /yes or /no and have the head nod. It was also mentioned that the simple interface would not require server changes to implement. Further discussion points out the distinction between SL gestures and human gesture and suggests that basic tracking is the low-hanging fruit rather than a simple interface.



			-----
			I tried hooking up a webcam head tracking system to the joystick input of SL, via the utility faceapi2ppjoy. Worked fine, but my attempt to track the viewport based on my head position made me nauseous. ;-)
			-- Latha Serevi, March 2010
			------

	[[Category:Snowglobe]]		[[Category:Snowglobe]]

Rob Linden: + Category:Snowglobe

2009-05-22T18:26:49Z

+ Category:Snowglobe

← Older revision		Revision as of 11:26, 22 May 2009
Line 8:		Line 8:
	Quick Summary:		Quick Summary:
	Several replies immediately followed that suggested hardware options beyond a normal webcam. These mainly included 3D cams and remote sensors. The discussion thread continued into details of what to expect from different device drivers. The details ranged from ability to track eye gaze to comments about the device's user-friendliness. Later on in the discussion, several people described needs on the interface, and this discussion quickly went into generic and universal interface design. As the thread quited down, at least a few people seemed to agree that a simple generic interface is a good start point. More specifically, one that can use input from a normal webcam, recognize a few common gestures, and play the related avatar animation much like one now can type /yes or /no and have the head nod. It was also mentioned that the simple interface would not require server changes to implement. Further discussion points out the distinction between SL gestures and human gesture and suggests that basic tracking is the low-hanging fruit rather than a simple interface.		Several replies immediately followed that suggested hardware options beyond a normal webcam. These mainly included 3D cams and remote sensors. The discussion thread continued into details of what to expect from different device drivers. The details ranged from ability to track eye gaze to comments about the device's user-friendliness. Later on in the discussion, several people described needs on the interface, and this discussion quickly went into generic and universal interface design. As the thread quited down, at least a few people seemed to agree that a simple generic interface is a good start point. More specifically, one that can use input from a normal webcam, recognize a few common gestures, and play the related avatar animation much like one now can type /yes or /no and have the head nod. It was also mentioned that the simple interface would not require server changes to implement. Further discussion points out the distinction between SL gestures and human gesture and suggests that basic tracking is the low-hanging fruit rather than a simple interface.

			[[Category:Snowglobe]]

Rob Linden: "our"->"Linden Lab's"

2009-05-22T17:36:00Z

"our"->"Linden Lab's"

← Older revision		Revision as of 10:36, 22 May 2009
Line 1:		Line 1:
	On the [[SLDev]] mailing list, [[User:Philip Linden\|Philip Linden]] asked: "''Has anyone here worked with camera-based gesture recognition before? How about OpenCV? Is OpenCV the best package for extracting basic head position/gesture information from a camera image stream? Merov and I are pondering a Snowglobe project to detect head motion from simple cameras and connect it to the SL Viewer.''"		On the [[SLDev]] mailing list, [[User:Philip Linden\|Philip Linden]] asked: "''Has anyone here worked with camera-based gesture recognition before? How about OpenCV? Is OpenCV the best package for extracting basic head position/gesture information from a camera image stream? Merov and I are pondering a Snowglobe project to detect head motion from simple cameras and connect it to the SL Viewer.''"

	Philip added a specific project proposal for first phase [[Gesture Recognition]]. ~~Our~~ goal is to have an intern work this summer to achieve a first step of simply using a regular camera (no markers or other hardware) to enhance the visual commmunication of the avatar by triggering gestures and head movement in response to what the camera sees. Community help with this project is welcome!		Philip added a specific project proposal for first phase [[Gesture Recognition]]. Linden Lab's goal is to have an intern work this summer to achieve a first step of simply using a regular camera (no markers or other hardware) to enhance the visual commmunication of the avatar by triggering gestures and head movement in response to what the camera sees. Community help with this project is welcome!

	A very long thread followed:		A very long thread followed:

Rob Linden: Camera-based gesture recognition moved to Camera-based Input: Conversation is broader than gesture recognition

2009-05-22T17:35:11Z

Camera-based gesture recognition moved to Camera-based Input: Conversation is broader than gesture recognition

← Older revision	Revision as of 10:35, 22 May 2009
(No difference)

Dzonatas Sol: update

2009-05-22T17:23:31Z

update

← Older revision		Revision as of 10:23, 22 May 2009
Line 7:		Line 7:

	Quick Summary:		Quick Summary:
	Several replies immediately followed that suggested hardware options beyond a normal webcam. These mainly included 3D cams and remote sensors. The discussion thread continued into details of what to expect from different device drivers. The details ranged from ability to track eye gaze to comments about the device's user-friendliness. Later on in the discussion, several people described needs on the interface, and this discussion quickly went into generic and universal interface design. As the thread quited down, at least a few people seemed to agree that a simple generic interface is a good start point. More specifically, one that can use input from a normal webcam, recognize a few common gestures, and play the related avatar animation much like one now can type /yes or /no and have the head nod. It was also mentioned that the simple interface would not require server changes to implement.		Several replies immediately followed that suggested hardware options beyond a normal webcam. These mainly included 3D cams and remote sensors. The discussion thread continued into details of what to expect from different device drivers. The details ranged from ability to track eye gaze to comments about the device's user-friendliness. Later on in the discussion, several people described needs on the interface, and this discussion quickly went into generic and universal interface design. As the thread quited down, at least a few people seemed to agree that a simple generic interface is a good start point. More specifically, one that can use input from a normal webcam, recognize a few common gestures, and play the related avatar animation much like one now can type /yes or /no and have the head nod. It was also mentioned that the simple interface would not require server changes to implement. Further discussion points out the distinction between SL gestures and human gesture and suggests that basic tracking is the low-hanging fruit rather than a simple interface.

Philip Linden at 17:19, 22 May 2009

2009-05-22T17:19:38Z

← Older revision		Revision as of 10:19, 22 May 2009
Line 1:		Line 1:
	On the [[SLDev]] mailing list, [[User:Philip Linden\|Philip Linden]] asked: "''Has anyone here worked with camera-based gesture recognition before? How about OpenCV? Is OpenCV the best package for extracting basic head position/gesture information from a camera image stream? Merov and I are pondering a Snowglobe project to detect head motion from simple cameras and connect it to the SL Viewer.''"		On the [[SLDev]] mailing list, [[User:Philip Linden\|Philip Linden]] asked: "''Has anyone here worked with camera-based gesture recognition before? How about OpenCV? Is OpenCV the best package for extracting basic head position/gesture information from a camera image stream? Merov and I are pondering a Snowglobe project to detect head motion from simple cameras and connect it to the SL Viewer.''"

	Philip added a specific project proposal for first phase [[Gesture Recognition]]		Philip added a specific project proposal for first phase [[Gesture Recognition]]. Our goal is to have an intern work this summer to achieve a first step of simply using a regular camera (no markers or other hardware) to enhance the visual commmunication of the avatar by triggering gestures and head movement in response to what the camera sees. Community help with this project is welcome!

	A very long thread followed:		A very long thread followed:

Philip Linden at 17:16, 22 May 2009

2009-05-22T17:16:03Z

← Older revision		Revision as of 10:16, 22 May 2009
Line 1:		Line 1:
	On the [[SLDev]] mailing list, [[User:Philip Linden\|Philip Linden]] asked: "''Has anyone here worked with camera-based gesture recognition before? How about OpenCV? Is OpenCV the best package for extracting basic head position/gesture information from a camera image stream? Merov and I are pondering a Snowglobe project to detect head motion from simple cameras and connect it to the SL Viewer.''"		On the [[SLDev]] mailing list, [[User:Philip Linden\|Philip Linden]] asked: "''Has anyone here worked with camera-based gesture recognition before? How about OpenCV? Is OpenCV the best package for extracting basic head position/gesture information from a camera image stream? Merov and I are pondering a Snowglobe project to detect head motion from simple cameras and connect it to the SL Viewer.''"

			Philip added a specific project proposal for first phase [[Gesture Recognition]]

	A very long thread followed:		A very long thread followed:

Dzonatas Sol at 08:45, 22 May 2009

2009-05-22T08:45:36Z

← Older revision		Revision as of 01:45, 22 May 2009
Line 5:		Line 5:

	Quick Summary:		Quick Summary:
	Several replies immediately ~~follow~~ that suggested hardware options beyond a normal webcam. These mainly included 3D cams and remote sensors. The discussion thread continued into details of what to expect from different device drivers. The details ranged from ability to track eye gaze to comments about the device's user-friendliness. Later on in the discussion, several people described needs on the interface, and this discussion quickly went into generic and universal interface design. As the thread quited down, at least a few people seemed to agree that a simple generic interface is a good start point. More specifically, one that can use input from a normal webcam, recognize a few common gestures, and play the related avatar animation much like one now can type /yes or /no and have the head nod. It was also mentioned that the simple interface would not require server changes to implement.		Several replies immediately followed that suggested hardware options beyond a normal webcam. These mainly included 3D cams and remote sensors. The discussion thread continued into details of what to expect from different device drivers. The details ranged from ability to track eye gaze to comments about the device's user-friendliness. Later on in the discussion, several people described needs on the interface, and this discussion quickly went into generic and universal interface design. As the thread quited down, at least a few people seemed to agree that a simple generic interface is a good start point. More specifically, one that can use input from a normal webcam, recognize a few common gestures, and play the related avatar animation much like one now can type /yes or /no and have the head nod. It was also mentioned that the simple interface would not require server changes to implement.

Dzonatas Sol: quick summary

2009-05-22T08:45:02Z

quick summary

← Older revision		Revision as of 01:45, 22 May 2009
Line 3:		Line 3:
	A very long thread followed:		A very long thread followed:
	[https://lists.secondlife.com/pipermail/sldev/2009-May/thread.html#13973 sldev thread about camera-based gesture recognition]		[https://lists.secondlife.com/pipermail/sldev/2009-May/thread.html#13973 sldev thread about camera-based gesture recognition]

			Quick Summary:
			Several replies immediately follow that suggested hardware options beyond a normal webcam. These mainly included 3D cams and remote sensors. The discussion thread continued into details of what to expect from different device drivers. The details ranged from ability to track eye gaze to comments about the device's user-friendliness. Later on in the discussion, several people described needs on the interface, and this discussion quickly went into generic and universal interface design. As the thread quited down, at least a few people seemed to agree that a simple generic interface is a good start point. More specifically, one that can use input from a normal webcam, recognize a few common gestures, and play the related avatar animation much like one now can type /yes or /no and have the head nod. It was also mentioned that the simple interface would not require server changes to implement.

Rob Linden: Stub page...hoping someone can summarize the thread here

2009-05-22T03:29:49Z

Stub page...hoping someone can summarize the thread here

New page

On the [[SLDev]] mailing list, [[User:Philip Linden|Philip Linden]] asked: "''Has anyone here worked with camera-based gesture recognition before? How about OpenCV? Is OpenCV the best package for extracting basic head position/gesture information from a camera image stream? Merov and I are pondering a Snowglobe project to detect head motion from simple cameras and connect it to the SL Viewer.''"

A very long thread followed:
[https://lists.secondlife.com/pipermail/sldev/2009-May/thread.html#13973 sldev thread about camera-based gesture recognition]