Object recognition - Revision history

Shadowdawn at 09:39, 22 October 2015

2015-10-22T09:39:27Z

← Older revision		Revision as of 09:39, 22 October 2015
Line 1:		Line 1:
	{{stub}}		{{stub}}
	[[Object recognition]] is an important feature in both [[Augmented reality]] and [[virtual reality]]. [[AR]] uses object recognition to deliver contextually aware information and multimedia. In [[VR]], many systems such as [[Chaperone]] of [[SteamVR]] are designed in such a way that they are aware of their surroundings, which is essential for safe operation. As VR and AR technologies become more mainstream, we will see a dramatic improvement in object ~~detection and~~ recognition. These improvements will have to overcome, among many other things, varying lighting conditions, changes in shape and size, and work fast enough to be usable in everyday situations.		[[Object recognition]], as part of [[computer vision]], is an important feature in both [[Augmented reality]] and [[virtual reality]]. [[AR]] uses object recognition to deliver contextually aware information and multimedia. In [[VR]], many systems such as [[Chaperone]] of [[SteamVR]] are designed in such a way that they are aware of their surroundings, which is essential for safe operation. As VR and AR technologies become more mainstream, we will see a dramatic improvement in object recognition. These improvements will have to overcome, among many other things, varying lighting conditions, changes in shape and size, and work fast enough to be usable in everyday situations.

	==How does object recognition work?==		==How does object recognition work?==

Shadowdawn: /* How does object recognition work? */

2015-10-22T09:22:14Z

How does object recognition work?

← Older revision		Revision as of 09:22, 22 October 2015
Line 3:		Line 3:

	==How does object recognition work?==		==How does object recognition work?==
	There are two main methods to conduct object recognition in AR. Each method contains several different sub-~~methods. These are appearance-based methods and feature-based~~ methods.		There are two main methods to conduct object recognition in AR, appearance-based methods and feature-based methods. Each method contains several different sub-methods.

	===Appearance-based methods===		===Appearance-based methods===

Shadowdawn at 09:16, 22 October 2015

2015-10-22T09:16:52Z

← Older revision		Revision as of 09:16, 22 October 2015
Line 1:		Line 1:
	{{stub}}		{{stub}}
	[[Object recognition]] is an important feature in both [[Augmented reality]] and [[virtual reality]]. [[AR]] uses object recognition to deliver contextually aware information and multimedia. In [[VR]], many systems such as [[Chaperone]] of [[SteamVR]] are designed in such a way that they are aware of their surroundings, which is essential for safe operation.		[[Object recognition]] is an important feature in both [[Augmented reality]] and [[virtual reality]]. [[AR]] uses object recognition to deliver contextually aware information and multimedia. In [[VR]], many systems such as [[Chaperone]] of [[SteamVR]] are designed in such a way that they are aware of their surroundings, which is essential for safe operation. As VR and AR technologies become more mainstream, we will see a dramatic improvement in object detection and recognition. These improvements will have to overcome, among many other things, varying lighting conditions, changes in shape and size, and work fast enough to be usable in everyday situations.

	==How does object recognition work?==		==How does object recognition work?==

Shadowdawn: /* =Feature-based methods */

2015-10-22T09:16:33Z

=Feature-based methods

← Older revision		Revision as of 09:16, 22 October 2015
Line 8:		Line 8:
	As their names may suggest, appearance-based methods consider comparable and detectable features of objects and their similarity to templates or exemplars. The main challenge for this method is the simple fact that any single object may look completely differently depending on lighting conditions, distance or angle from which it is viewed, and even its age. This means that highly effective appearance-based system needs to have a large base of templates to use as a base of its evaluation algorithms, which presents obvious problems with storage space, time, and manpower necessary for accomplishing this task. The most commonly used approaches for appearance-based evaluation are edge matching, divide-and-conquer search, greyscale matching, gradient matching, histograms of receptive field responses, and large model bases.		As their names may suggest, appearance-based methods consider comparable and detectable features of objects and their similarity to templates or exemplars. The main challenge for this method is the simple fact that any single object may look completely differently depending on lighting conditions, distance or angle from which it is viewed, and even its age. This means that highly effective appearance-based system needs to have a large base of templates to use as a base of its evaluation algorithms, which presents obvious problems with storage space, time, and manpower necessary for accomplishing this task. The most commonly used approaches for appearance-based evaluation are edge matching, divide-and-conquer search, greyscale matching, gradient matching, histograms of receptive field responses, and large model bases.

	===Feature-based methods==		===Feature-based methods===
	Feature-based methods look for similar features in an imagined or ideal object and a real image. When we consider, for example, a face recognition, it is possible to program a set of features that are associated with the human face. Using these features, a software algorithm can generate a model that will be placed over the captured image. If some features of this object match the image we have a positive match. Common feature-based detection methods include interpretation trees, hypothesize and test method, pose consistency, pose clustering, invariance, geometric hashing, scale-invariant feature transform method, and speeded up robust features (SURF).		Feature-based methods look for similar features in an imagined or ideal object and a real image. When we consider, for example, a face recognition, it is possible to program a set of features that are associated with the human face. Using these features, a software algorithm can generate a model that will be placed over the captured image. If some features of this object match the image we have a positive match. Common feature-based detection methods include interpretation trees, hypothesize and test method, pose consistency, pose clustering, invariance, geometric hashing, scale-invariant feature transform method, and speeded up robust features (SURF).

Shadowdawn: /* How does object recognition work? */

2015-10-22T09:16:25Z

How does object recognition work?

← Older revision		Revision as of 09:16, 22 October 2015
Line 3:		Line 3:

	==How does object recognition work?==		==How does object recognition work?==
	~~The~~ object recognition in ~~augmented reality faces various challenges that~~ are ~~no problem for humans, who easily recognize objects of different sizes, shapes,~~ and ~~colors even when they happen to be partially obscured from view~~.		There are two main methods to conduct object recognition in AR. Each method contains several different sub-methods. These are appearance-based methods and feature-based methods.

	~~Basically, there are two main methods, each containing several different sub-methods. These are appearance-based methods and feature~~-based methods. As their names may suggest, appearance-based methods consider comparable and detectable features of objects and their similarity to templates or exemplars. The main challenge for this method is the simple fact that any single object may look completely differently depending on lighting conditions, distance or angle from which it is viewed, and even its age. This means that highly effective appearance-based system needs to have a large base of templates to use as a base of its evaluation algorithms, which presents obvious problems with storage space, time, and manpower necessary for accomplishing this task. The most commonly used approaches for appearance-based evaluation are edge matching, divide-and-conquer search, greyscale matching, gradient matching, histograms of receptive field responses, and large model bases.		===Appearance-based methods===
			As their names may suggest, appearance-based methods consider comparable and detectable features of objects and their similarity to templates or exemplars. The main challenge for this method is the simple fact that any single object may look completely differently depending on lighting conditions, distance or angle from which it is viewed, and even its age. This means that highly effective appearance-based system needs to have a large base of templates to use as a base of its evaluation algorithms, which presents obvious problems with storage space, time, and manpower necessary for accomplishing this task. The most commonly used approaches for appearance-based evaluation are edge matching, divide-and-conquer search, greyscale matching, gradient matching, histograms of receptive field responses, and large model bases.

	Feature-based methods look for similar features in an imagined or ideal object and a real image. When we consider, for example, a face recognition, it is possible to program a set of features that are associated with the human face. Using these features, a software algorithm can generate a model that will be placed over the captured image. If some features of this object match the image we have a positive match. Common feature-based detection methods include interpretation trees, hypothesize and test method, pose consistency, pose clustering, invariance, geometric hashing, scale-invariant feature transform method, and speeded up robust features (SURF).		===Feature-based methods==
			Feature-based methods look for similar features in an imagined or ideal object and a real image. When we consider, for example, a face recognition, it is possible to program a set of features that are associated with the human face. Using these features, a software algorithm can generate a model that will be placed over the captured image. If some features of this object match the image we have a positive match. Common feature-based detection methods include interpretation trees, hypothesize and test method, pose consistency, pose clustering, invariance, geometric hashing, scale-invariant feature transform method, and speeded up robust features (SURF).
	As VR and AR technologies become more mainstream, we will see a dramatic improvement in object detection and recognition. These improvements will have to overcome, among many other things, varying lighting conditions, changes in shape and size, and work fast enough to be usable in everyday situations.

	==Augmented Reality==		==Augmented Reality==

Shadowdawn at 09:12, 22 October 2015

2015-10-22T09:12:26Z

← Older revision		Revision as of 09:12, 22 October 2015
Line 1:		Line 1:
	{{stub}}		{{stub}}
	[[Object recognition]] is an important feature in both [[Augmented reality]] and [[virtual reality]]. [[AR]] uses object recognition to deliver contextually aware information and multimedia. In [[VR]], many systems such as [[Chaperone]] of [[SteamVR]] are designed in such a way that they are aware of their surroundings, which is essential for safe operation.		[[Object recognition]] is an important feature in both [[Augmented reality]] and [[virtual reality]]. [[AR]] uses object recognition to deliver contextually aware information and multimedia. In [[VR]], many systems such as [[Chaperone]] of [[SteamVR]] are designed in such a way that they are aware of their surroundings, which is essential for safe operation.

			==How does object recognition work?==
			The object recognition in augmented reality faces various challenges that are no problem for humans, who easily recognize objects of different sizes, shapes, and colors even when they happen to be partially obscured from view.

			Basically, there are two main methods, each containing several different sub-methods. These are appearance-based methods and feature-based methods. As their names may suggest, appearance-based methods consider comparable and detectable features of objects and their similarity to templates or exemplars. The main challenge for this method is the simple fact that any single object may look completely differently depending on lighting conditions, distance or angle from which it is viewed, and even its age. This means that highly effective appearance-based system needs to have a large base of templates to use as a base of its evaluation algorithms, which presents obvious problems with storage space, time, and manpower necessary for accomplishing this task. The most commonly used approaches for appearance-based evaluation are edge matching, divide-and-conquer search, greyscale matching, gradient matching, histograms of receptive field responses, and large model bases.

			Feature-based methods look for similar features in an imagined or ideal object and a real image. When we consider, for example, a face recognition, it is possible to program a set of features that are associated with the human face. Using these features, a software algorithm can generate a model that will be placed over the captured image. If some features of this object match the image we have a positive match. Common feature-based detection methods include interpretation trees, hypothesize and test method, pose consistency, pose clustering, invariance, geometric hashing, scale-invariant feature transform method, and speeded up robust features (SURF).

			As VR and AR technologies become more mainstream, we will see a dramatic improvement in object detection and recognition. These improvements will have to overcome, among many other things, varying lighting conditions, changes in shape and size, and work fast enough to be usable in everyday situations.

	==Augmented Reality==		==Augmented Reality==

Shadowdawn: /* Augmented Reality */

2015-10-22T09:11:19Z

Augmented Reality

← Older revision		Revision as of 09:11, 22 October 2015
Line 4:		Line 4:
	==Augmented Reality==		==Augmented Reality==
	===Google Glass===		===Google Glass===
	[[Google Glass]] was the first system to demonstrate how object recognition can be used in AR. First released by [[Google]] in February 2013, the system uses a special liquid crystal on silicon (LCoS), [[optical head-mounted display]] with 640x360 pixels [[resolution]] to display information from many existing Google applications, as well as those created by third-party developers. Google Glass is able to recognize an image in a scene, track its position, and augment the display by displaying appropriate information. This may be a map with navigation, price information for shoppers, office and business hours, or nutrition information of food items.		[[Google Glass]] was the first system to demonstrate how object recognition can be used in AR. First released by [[Google]] in February 2013, the system uses a special liquid crystal on silicon (LCoS), [[optical head-mounted display]] with 640x360 pixels [[resolution]] to display information from many existing Google applications, as well as those created by third-party developers. Google Glass is able to recognize an image in a scene, [[positional tracking\|track its position]], and augment the display by displaying appropriate information. This may be a map with navigation, price information for shoppers, office and business hours, or nutrition information of food items.

	Development of augmented reality apps for Google Glass is made very accessible thanks to several SDKs that are currently available with [[Wikitude]] SDK being the most popular. The SDK enables developers to take advantage of built-in image recognition and tracking technology, position-aware services with geo-referenced data, embed videos from [[YouTube]] or Vimeo, and more. It ~~is a very quick way how~~ anybody who is interested in augmented reality and object recognition ~~can~~ develop a new ~~practical~~ application and showcase just how this technology could be integrated with our daily lives. Other solutions include, for example, [[CraftAR]], which is a suite of tools created for agencies, publishers, and companies that would like to leverage technological possibilities of AR and IR to create ads, magazines, and catalogs. The technology works on all major mobile operating systems and supports the most popular programming languages and 3D engines.		Development of augmented reality apps for Google Glass is made very accessible thanks to several SDKs that are currently available with [[Wikitude]] SDK being the most popular. The SDK enables developers to take advantage of built-in image recognition and tracking technology, position-aware services with geo-referenced data, embed videos from [[YouTube]] or Vimeo, and more. It allows anybody who is interested in augmented reality and object recognition to quickly develop a new application and showcase just how this technology could be integrated with our daily lives. Other solutions include, for example, [[CraftAR]], which is a suite of tools created for agencies, publishers, and companies that would like to leverage technological possibilities of AR and IR to create ads, magazines, and catalogs. The technology works on all major mobile operating systems and supports the most popular programming languages and 3D engines.

	==Virtual Reality==		==Virtual Reality==

Shadowdawn at 09:07, 22 October 2015

2015-10-22T09:07:45Z

← Older revision		Revision as of 09:07, 22 October 2015
Line 1:		Line 1:
	{{stub}}		{{stub}}
	[[Object recognition]] is an important feature in both [[Augmented reality]] and [[virtual reality]]. [[AR]] uses object recognition to deliver contextually aware information and multimedia. In [[VR]], many systems such as [[Chaperone]] of [[SteamVR]] are designed in such a way so that they are aware of their surroundings, which is essential for safe operation.		[[Object recognition]] is an important feature in both [[Augmented reality]] and [[virtual reality]]. [[AR]] uses object recognition to deliver contextually aware information and multimedia. In [[VR]], many systems such as [[Chaperone]] of [[SteamVR]] are designed in such a way that they are aware of their surroundings, which is essential for safe operation.

	==Augmented Reality==		==Augmented Reality==

Shadowdawn at 09:07, 22 October 2015

2015-10-22T09:07:25Z

← Older revision		Revision as of 09:07, 22 October 2015
Line 1:		Line 1:
	{{stub}}		{{stub}}
	[[Object recognition]] is an important feature in both [[Augmented reality]] and [[virtual reality]]. [[AR]] uses object recognition to deliver contextually aware information and multimedia. In [[VR]], many systems are designed in such a way so that they are aware of their surroundings, which is ~~in some cases~~ essential for safe operation.		[[Object recognition]] is an important feature in both [[Augmented reality]] and [[virtual reality]]. [[AR]] uses object recognition to deliver contextually aware information and multimedia. In [[VR]], many systems such as [[Chaperone]] of [[SteamVR]] are designed in such a way so that they are aware of their surroundings, which is essential for safe operation.

	==Augmented Reality==		==Augmented Reality==

Shadowdawn at 09:05, 22 October 2015

2015-10-22T09:05:18Z

← Older revision		Revision as of 09:05, 22 October 2015
Line 1:		Line 1:
	{{stub}}		{{stub}}
	[[Object recognition]] is an important feature in both [[Augmented reality]] and [[virtual reality]]. [[AR]] uses object recognition to deliver contextually aware information and multimedia. In [[VR]], many systems are designed in such a way so that they are aware of their surroundings, which is in some cases essential for safe operation.		[[Object recognition]] is an important feature in both [[Augmented reality]] and [[virtual reality]]. [[AR]] uses object recognition to deliver contextually aware information and multimedia. In [[VR]], many systems are designed in such a way so that they are aware of their surroundings, which is in some cases essential for safe operation.

	==Augmented Reality==		==Augmented Reality==