**4. Marker-less-based augmented reality**

Marker-less AR is completely different from marker-based AR because it does not depend on the artificial markers in order to reveal outstanding features in the scene. Marker-less AR systems work to integrate virtual objects into a 3D real environment in real-time, promote user's perception of and interaction with the real world [15]. Marker-less AR works by revealing features that are easily available from the natural objects in the scene, as well as, try to create a model or map from the scenery in order to represent the world as it is displayed by the camera.

### **4.1 Camera pose estimation**

There are two main methods to camera pose estimation techniques called relative orientation and planar homography. Relative orientation is an approach that used to calculate the position and orientation of a camera relative to another from correspondences between five or more ray pairs. A ray pair can be defined as the vectors that arise from a fixed and visible point in the scenery to the camera centre positions [16]. Use the aspect of AR process that recruit computer vision algorithms, called feature detection and tracking, and then suggest a method to improve the subsequent process to output a best camera pose estimate [16]. A localised feature descriptor is used for the matching of salient feature points belonging to the present camera frame with those extracted from the reference frames. Camera pose can be estimated relative to it, however, the calculated 3D pose parameters can be used in order to render virtual objects into the real world [17]. Frikha et al. are proposed real-time monocular piece wise planar SLAM method using the planar scene assumption. Planar structures have used for mapping process in order to allow rendering virtual objects in a meaningful way, as well as improving the camera pose resolution in addition to the quality of 3-D reconstruction of the environment by adding restrictions on 3-D points, and settings in the optimisation process [18]. An energy function based on epipolar geometry has been developed in order to estimate intrinsic camera parameters during camera zooming [19]. Intrinsic camera parameters at each zoom value are calibrated, in order to obtain an accurate camera parameter estimation. The intrinsic camera parameters changes depending on the zoom value that are modelled [19].

### **4.2 Outdoor marker-less-based augmented reality**

Augmented reality is the real-time incorporation of the virtual and physical worlds into a new environment, where digital information is registered with

**61**

*Cultural Heritage in Marker-Less Augmented Reality: A Survey*

real-world elements in a coherent method. One of the big challenges when working in outdoor AR is the registration of the virtual elements in the real-world environment, where it is not realistic to prepare every building with visual markers. This issue is certainly much more accurate when dealing with outdoor augmented reality. Most augmented reality applications are taking the benefit of backpack systems with head-worn displays [20] or handheld devices [21] in order to compose realworlds' views with digital information. Sophisticated hardware contains tracking devices, for example, GPS and gyroscope, which can be used to determine the

Bateau Ivre [22] project have presented on the Seine River in order to make a considerable audience conscious of the possible developments of augmented reality through an artistic installation in an outdoor environment. The installation can be seen from a ship by a huge number of audience without specified equipment, through night-time video-projection on the River banks. The augmentation of the physical world is implemented using real-time image processing for live special effects, for example, contouring, particles and non-realistic rendering. The technical objective of the project was to immerge the audience into a non-realistic view of the River banks that would be different from traditional tours that highlight the main features of Paris' classical architecture. The implemented software is used in standard algorithms for particular effects to a live video stream and then re-projected these effects on the

However, Sato et al. [5] have developed a novel marker-less AR system that uses local feature-based image registration and structure from motion (SfM) technology. The proposed system has some advantages, such as it supports free movement, less limitations, less efforts, as well as lower cost for outdoor AR applications. For the verification of the developed system, it has been applied to a renovation design project. One of the main advantages of the system is that it does not require particular equipment, for example, sensors for geometric registration between augmentations and the real world because the system uses sensor-based registration. Furthermore, the system does not need artificial markers, which reduce user's flexibility [5]. The accuracy of system's registration and tracking for this research is not enough for AR. A development of a 3D map oriented handheld AR system has been presented by Chen et al. [24]. The system achieves geometric consistency by using a 3D map in order to obtain position data instead of using GPS, which provides low position information accuracy, especially in urban areas. In addition, the system features a gyroscope sensor to obtain posture data, as well as a video camera that used to capture live video of the present surroundings. All these components are installed in a smartphone and can be used to assess urban landscape. The authors have used the evaluation of registration accuracy in order to simulate an urban landscape from a short- to a long-range scale. The proposed AR system allows users to simulate a landscape from multiple viewpoints in addition to long-distance simultaneously, as well as walking around the viewpoint fields using just a smartphone [24]. The proposed system has the optical integrity

and occlusion problem of the 3D-AR system when simulating urban landscape. In addition, Chen et al. [25] presented tracking natural features in an agricultural scene. The main objective of the system is to perform marker-less AR techniques in order to assist in the visualisation of robotic helicopter-related tasks. By creating a virtual marker under a known initial configuration of the robotic helicopter, camera and the ground plane, the system is able to continuously track the camera pose using the natural features of the image sequence to execute augmentation of virtual objects. A simulation using a mock-up model of an agriculture farm have developed to evaluate the performance of the marker-less AR system. The experiment results showed that there are a number of improvements, which need to be taken in consideration before distributing the system in actual flight. The intermittent movement of the virtual marker vertices must be reduced in order

captured scenes to merge the real world with its modified image [23].

*DOI: http://dx.doi.org/10.5772/intechopen.80975*

position in the physical world.

#### *Cultural Heritage in Marker-Less Augmented Reality: A Survey DOI: http://dx.doi.org/10.5772/intechopen.80975*

*Advanced Methods and New Materials for Cultural Heritage Preservation*

**4. Marker-less-based augmented reality**

**4.1 Camera pose estimation**

**Figure 4.**

*Marker-based AR [14].*

Marker-less AR is completely different from marker-based AR because it does not depend on the artificial markers in order to reveal outstanding features in the scene. Marker-less AR systems work to integrate virtual objects into a 3D real environment in real-time, promote user's perception of and interaction with the real world [15]. Marker-less AR works by revealing features that are easily available from the natural objects in the scene, as well as, try to create a model or map from

There are two main methods to camera pose estimation techniques called relative orientation and planar homography. Relative orientation is an approach that used to calculate the position and orientation of a camera relative to another from correspondences between five or more ray pairs. A ray pair can be defined as the vectors that arise from a fixed and visible point in the scenery to the camera centre positions [16]. Use the aspect of AR process that recruit computer vision algorithms, called feature detection and tracking, and then suggest a method to improve the subsequent process to output a best camera pose estimate [16]. A localised feature descriptor is used for the matching of salient feature points belonging to the present camera frame with those extracted from the reference frames. Camera pose can be estimated relative to it, however, the calculated 3D pose parameters can be used in order to render virtual objects into the real world [17]. Frikha et al. are proposed real-time monocular piece wise planar SLAM method using the planar scene assumption. Planar structures have used for mapping process in order to allow rendering virtual objects in a meaningful way, as well as improving the camera pose resolution in addition to the quality of 3-D reconstruction of the environment by adding restrictions on 3-D points, and settings in the optimisation process [18]. An energy function based on epipolar geometry has been developed in order to estimate intrinsic camera parameters during camera zooming [19]. Intrinsic camera parameters at each zoom value are calibrated, in order to obtain an accurate camera parameter estimation. The intrinsic camera parameters

the scenery in order to represent the world as it is displayed by the camera.

changes depending on the zoom value that are modelled [19].

Augmented reality is the real-time incorporation of the virtual and physical worlds into a new environment, where digital information is registered with

**4.2 Outdoor marker-less-based augmented reality**

**60**

real-world elements in a coherent method. One of the big challenges when working in outdoor AR is the registration of the virtual elements in the real-world environment, where it is not realistic to prepare every building with visual markers. This issue is certainly much more accurate when dealing with outdoor augmented reality. Most augmented reality applications are taking the benefit of backpack systems with head-worn displays [20] or handheld devices [21] in order to compose realworlds' views with digital information. Sophisticated hardware contains tracking devices, for example, GPS and gyroscope, which can be used to determine the position in the physical world.

Bateau Ivre [22] project have presented on the Seine River in order to make a considerable audience conscious of the possible developments of augmented reality through an artistic installation in an outdoor environment. The installation can be seen from a ship by a huge number of audience without specified equipment, through night-time video-projection on the River banks. The augmentation of the physical world is implemented using real-time image processing for live special effects, for example, contouring, particles and non-realistic rendering. The technical objective of the project was to immerge the audience into a non-realistic view of the River banks that would be different from traditional tours that highlight the main features of Paris' classical architecture. The implemented software is used in standard algorithms for particular effects to a live video stream and then re-projected these effects on the captured scenes to merge the real world with its modified image [23].

However, Sato et al. [5] have developed a novel marker-less AR system that uses local feature-based image registration and structure from motion (SfM) technology. The proposed system has some advantages, such as it supports free movement, less limitations, less efforts, as well as lower cost for outdoor AR applications. For the verification of the developed system, it has been applied to a renovation design project. One of the main advantages of the system is that it does not require particular equipment, for example, sensors for geometric registration between augmentations and the real world because the system uses sensor-based registration. Furthermore, the system does not need artificial markers, which reduce user's flexibility [5]. The accuracy of system's registration and tracking for this research is not enough for AR.

A development of a 3D map oriented handheld AR system has been presented by Chen et al. [24]. The system achieves geometric consistency by using a 3D map in order to obtain position data instead of using GPS, which provides low position information accuracy, especially in urban areas. In addition, the system features a gyroscope sensor to obtain posture data, as well as a video camera that used to capture live video of the present surroundings. All these components are installed in a smartphone and can be used to assess urban landscape. The authors have used the evaluation of registration accuracy in order to simulate an urban landscape from a short- to a long-range scale. The proposed AR system allows users to simulate a landscape from multiple viewpoints in addition to long-distance simultaneously, as well as walking around the viewpoint fields using just a smartphone [24]. The proposed system has the optical integrity and occlusion problem of the 3D-AR system when simulating urban landscape.

In addition, Chen et al. [25] presented tracking natural features in an agricultural scene. The main objective of the system is to perform marker-less AR techniques in order to assist in the visualisation of robotic helicopter-related tasks. By creating a virtual marker under a known initial configuration of the robotic helicopter, camera and the ground plane, the system is able to continuously track the camera pose using the natural features of the image sequence to execute augmentation of virtual objects. A simulation using a mock-up model of an agriculture farm have developed to evaluate the performance of the marker-less AR system. The experiment results showed that there are a number of improvements, which need to be taken in consideration before distributing the system in actual flight. The intermittent movement of the virtual marker vertices must be reduced in order to obtain better camera pose estimation. A feature recovery algorithm is one of the most important techniques for scaling the marker-less AR system to operate outdoors on the robotic helicopter [25]. This technique is trembling in the virtual marker vertices. Therefore, camera pose estimation accuracy is low.

### **5. Cultural heritage in augmented reality**

Virtual heritage in AR can be defined as an interactive computer-based technology, which can be used to achieve visual reconstruction, assist scholars and educators of traditional entities, for example, buildings, artefacts and culture [26]. This technology is used to maintain delicate historical buildings from natural disasters and sabotage [27]. In order to create a virtual heritage, there are seven main design principles, which must be taken into account such as high geometric accuracy, high level of automation capture for all details, low cost, photorealism, flexibility, portability and model size efficiency [28]. Cultural heritage layers are proposed to visualise historic media such as drawings, paintings and photographs of buildings and historic scenes seamlessly superimposed on real environment through video see through using X3D [29]. The registration of the virtual objects in the video images is done by using a robust 6DOF tracking framework depending on two technologies that work simultaneously: randomised trees are used for initialization step and a frame-to-frame tracking phase based on KLT. This technique achieved simple, cheap and sustainable development augmented reality applications in the area of the cultural heritage depending on industry standards [30]. The main idea of this research is to use current historic media from archives and superimpose them seamlessly on reality at the suitable place. These local layers are context sensitively telling the location's history and give the impression of a virtual time trip. The results of the application showed in the area of cultural heritage, where the system runs on an Ultra Mobile PC (Sony Vaio UX) with 15 frames/sec. Only the reality filters and the 2D overlays can be selected by the application developer or online by the user [29]. This application is very simple and presented just 2D overlays, as well as the detection of the filter is done manually. Augmented reality for historical tourism using mobile devices has been proposed by Bres et al. [30]. The core of the proposed system is related to a marker-less outdoor augmented reality solution. This technique is based on scale invariant feature transform (SIFT) features for localisation and integration of 3D models into video. These features are used to project a digital model of the building facades of the square in order to get 3D coordinates for each feature point. The algorithms executed are responsible to calculate the camera pose for frame of a video from 3D-2D point correspondences among features that extracted from the current video frame and points in the reference dataset. The algorithms were successfully evaluated on video films of city squares. Despite they do not yet work in real-time, they are able to correct pose estimation and projection of artificial data into the scene. The algorithms automatically recover any loss of track. The research showed that the possibility of SIFT features are purely used for image-based marker-less outdoor augmented reality applications [30]. This research presented a simple mobile application that used to augment a small 3D image. HeladivaAR [31] proposed to reconstruct the historical and cultural heritage of Sri Lanka. HeladivaAR is a mobile phone application that used to show a reconstructed 3D model of these ancient ruins as they were in their initial state. In addition to use of AR technology, the application has used the mobile phone camera to determine and track the remaining ruins of the historical place and reconstructs the 3D model on it and then displays on the application interface. This application used different aspects to reconstruct the cultural heritage building such as image

**63**

of outdoor illumination [23].

**6.1 Registration**

*Cultural Heritage in Marker-Less Augmented Reality: A Survey*

processing, 3D modelling, tracker identification using Android platform, historical books and reconstruct ruined sites. By using of AR, the real scene is enhanced by interactive multimedia information in order to increase the experience of the user, who can recover this information by a user-easy interface through their mobile phone. In education field, virtual heritage becomes a platform of learning, motivating and understanding of particular events and historical elements for students and researchers. This research provides a better understanding of Sri Lankan cultural heritage and allows users to gain interactive knowledge on archaeological facts of ancient kingdoms [31]. However, this research has several limitations. The first one is the application can apply only to android-based augmented reality devices; it cannot apply for the ISO-based operating system devices. The second limitation is the quality of the application that is based on the mobile device because it is not a desktop application. The last limitation is the application developed for Android 3.0 or above. The versions below may encounter rendering problems when running. Indrawan developed marker-less augmented reality utilising gyroscope in order to demonstrate the position of Dewata Nawa Sanga [32]. This application is designed to learn, understand and recognise the properties of Dewata Nao Sanga by using a gyroscope. The sensor works to achieve the object of the deities in the coordinates to be identified, as well as, it is worked to provide information about Dewata Nawa Sanga along alongside and informative 3D animation. This research evaluates the usefulness, functionality of the application, in addition to the impact of the AR Dewata Nawa Sanga application that can motivate its users. The result of usability and satisfaction questionnaire value showed that the percentage average is 84.8%. It illustrates that the application is very useful for the participants to have

knowledge about Dewata Nawa Sanga as well as very satisfied to use [32].

**6. Issues with virtual heritage in augmented reality issues**

There are four main issues related to the virtual heritage in augmented reality. These issues are registration, reconstruction orientation, tracking and location.

Registration is one of the most significant issues in virtual heritage AR systems and currently subtracts some restrictions to different AR applications. Registration indicates the accurate compatibility of augmented objects with

Kolivand and El Rhalibi presented a new technique to augment a realistic virtual building in real environments to be observed live through an AR camera [23]. There are some outdoor components when augmented a realistic building, for example, the sun position, shadows, sky illumination and virtual traditional animated characters. It is augmented in real environments at the place of real historical buildings, or desirable locations, at different times of the day and different days of the year [2]. The authors have presented some new ideas in the case of virtual heritage. First of all is modelling the 3D model of Portuguese Malacca. A structured real-time system is provided to trace the sun position, by using Julian dating, and Perez sky model is used for modelling sky colour, have presented in order to create outdoor illumination. A semi-soft shadow algorithm has been implemented to support the realism of outdoor augmented reality systems. A simple camera setup system has used to present Marker-less AR. The final system can be installed on head mounted display (HMD) or in the proposed device called ReVitAge to show the realistic reconstructed virtual heritage buildings, taking into account the main components

*DOI: http://dx.doi.org/10.5772/intechopen.80975*

#### *Cultural Heritage in Marker-Less Augmented Reality: A Survey DOI: http://dx.doi.org/10.5772/intechopen.80975*

*Advanced Methods and New Materials for Cultural Heritage Preservation*

marker vertices. Therefore, camera pose estimation accuracy is low.

**5. Cultural heritage in augmented reality**

to obtain better camera pose estimation. A feature recovery algorithm is one of the most important techniques for scaling the marker-less AR system to operate outdoors on the robotic helicopter [25]. This technique is trembling in the virtual

Virtual heritage in AR can be defined as an interactive computer-based technology, which can be used to achieve visual reconstruction, assist scholars and educators of traditional entities, for example, buildings, artefacts and culture [26]. This technology is used to maintain delicate historical buildings from natural disasters and sabotage [27]. In order to create a virtual heritage, there are seven main design principles, which must be taken into account such as high geometric accuracy, high level of automation capture for all details, low cost, photorealism, flexibility, portability and model size efficiency [28]. Cultural heritage layers are proposed to visualise historic media such as drawings, paintings and photographs of buildings and historic scenes seamlessly superimposed on real environment through video see through using X3D [29]. The registration of the virtual objects in the video images is done by using a robust 6DOF tracking framework depending on two technologies that work simultaneously: randomised trees are used for initialization step and a frame-to-frame tracking phase based on KLT. This technique achieved simple, cheap and sustainable development augmented reality applications in the area of the cultural heritage depending on industry standards [30]. The main idea of this research is to use current historic media from archives and superimpose them seamlessly on reality at the suitable place. These local layers are context sensitively telling the location's history and give the impression of a virtual time trip. The results of the application showed in the area of cultural heritage, where the system runs on an Ultra Mobile PC (Sony Vaio UX) with 15 frames/sec. Only the reality filters and the 2D overlays can be selected by the application developer or online by the user [29]. This application is very simple and presented just 2D overlays, as well as the detection of the filter is done manually. Augmented reality for historical tourism using mobile devices has been proposed by Bres et al. [30]. The core of the proposed system is related to a marker-less outdoor augmented reality solution. This technique is based on scale invariant feature transform (SIFT) features for localisation and integration of 3D models into video. These features are used to project a digital model of the building facades of the square in order to get 3D coordinates for each feature point. The algorithms executed are responsible to calculate the camera pose for frame of a video from 3D-2D point correspondences among features that extracted from the current video frame and points in the reference dataset. The algorithms were successfully evaluated on video films of city squares. Despite they do not yet work in real-time, they are able to correct pose estimation and projection of artificial data into the scene. The algorithms automatically recover any loss of track. The research showed that the possibility of SIFT features are purely used for image-based marker-less outdoor augmented reality applications [30]. This research presented a simple mobile application that used to augment a small 3D image. HeladivaAR [31] proposed to reconstruct the historical and cultural heritage of Sri Lanka. HeladivaAR is a mobile phone application that used to show a reconstructed 3D model of these ancient ruins as they were in their initial state. In addition to use of AR technology, the application has used the mobile phone camera to determine and track the remaining ruins of the historical place and reconstructs the 3D model on it and then displays on the application interface. This application used different aspects to reconstruct the cultural heritage building such as image

**62**

processing, 3D modelling, tracker identification using Android platform, historical books and reconstruct ruined sites. By using of AR, the real scene is enhanced by interactive multimedia information in order to increase the experience of the user, who can recover this information by a user-easy interface through their mobile phone. In education field, virtual heritage becomes a platform of learning, motivating and understanding of particular events and historical elements for students and researchers. This research provides a better understanding of Sri Lankan cultural heritage and allows users to gain interactive knowledge on archaeological facts of ancient kingdoms [31]. However, this research has several limitations. The first one is the application can apply only to android-based augmented reality devices; it cannot apply for the ISO-based operating system devices. The second limitation is the quality of the application that is based on the mobile device because it is not a desktop application. The last limitation is the application developed for Android 3.0 or above. The versions below may encounter rendering problems when running.

Indrawan developed marker-less augmented reality utilising gyroscope in order to demonstrate the position of Dewata Nawa Sanga [32]. This application is designed to learn, understand and recognise the properties of Dewata Nao Sanga by using a gyroscope. The sensor works to achieve the object of the deities in the coordinates to be identified, as well as, it is worked to provide information about Dewata Nawa Sanga along alongside and informative 3D animation. This research evaluates the usefulness, functionality of the application, in addition to the impact of the AR Dewata Nawa Sanga application that can motivate its users. The result of usability and satisfaction questionnaire value showed that the percentage average is 84.8%. It illustrates that the application is very useful for the participants to have knowledge about Dewata Nawa Sanga as well as very satisfied to use [32].

Kolivand and El Rhalibi presented a new technique to augment a realistic virtual building in real environments to be observed live through an AR camera [23]. There are some outdoor components when augmented a realistic building, for example, the sun position, shadows, sky illumination and virtual traditional animated characters. It is augmented in real environments at the place of real historical buildings, or desirable locations, at different times of the day and different days of the year [2]. The authors have presented some new ideas in the case of virtual heritage. First of all is modelling the 3D model of Portuguese Malacca. A structured real-time system is provided to trace the sun position, by using Julian dating, and Perez sky model is used for modelling sky colour, have presented in order to create outdoor illumination. A semi-soft shadow algorithm has been implemented to support the realism of outdoor augmented reality systems. A simple camera setup system has used to present Marker-less AR. The final system can be installed on head mounted display (HMD) or in the proposed device called ReVitAge to show the realistic reconstructed virtual heritage buildings, taking into account the main components of outdoor illumination [23].

### **6. Issues with virtual heritage in augmented reality issues**

There are four main issues related to the virtual heritage in augmented reality. These issues are registration, reconstruction orientation, tracking and location.

#### **6.1 Registration**

Registration is one of the most significant issues in virtual heritage AR systems and currently subtracts some restrictions to different AR applications. Registration indicates the accurate compatibility of augmented objects with

real environments [23]. Any AR system without an accurate registration leads to unsuccessful mixed environments because of the results of the defect wrong. The registration process is the overlay of virtual objects onto a real scene by using information that have extracted from the scene. Especially, this information is the feature points that extracted from the real scene using some tracking techniques. There are two categories of registration techniques, sensor-based and computer vision-based techniques. In sensor-based technique, there is a need to calibrate the external sensors, but the available sensors equipment's are either huge or expensive, or lack satisfactory levels of accuracy. Computer vision-based methods techniques work to avert calibration of external sensors, as well as offer the possibility for accurate tracking without huge and costly equipment. It can be categorised as two main types depending on camera calibration requirements [33]. The first kind does not require any calibration of camera parameters in advance, which includes the use of a known 3D calibration object. However, the second type is assuming that the intrinsic camera parameters are pre-calibrated. This is a common assumption in most of the existing AR systems.

There are several researches that work to develop the registration of the virtual elements in the real-world environments. These researches will be explained in the following section.

Gao et al. [6] introduced a new technique to improve the stabilisation and the accuracy of marker-less registration in AR. Based on three-dimensional map information generated by visual simultaneous localisation-SLAM. The proposed technique allows tracking and registration of virtual objects in order to ensure a stable in addition of real-time performance of marker-less AR applications. The stability of the system can be performed by integrating the Hough voting algorithm with the repeated Closest Points (ICP) technique. The proposed technique is faster than the standard methods. In addition, it is able to achieve more accurate registration results when compared with the previous techniques. The experimental results showed that the proposed technique can efficiently repress the virtual object jittering, as well as a higher tracking accuracy with good performance [6]. This technique can identify only one object for each recognition. Kanade-Lucas-Tomasi (KLT) natural feature tracker and the reconstruction technology is presented by Pang et al. [33]. KLT tracker technique is used to track the identical feature points in two control images. The authors presented three key stages in the proposed technique. The first stage is the affine reconstruction. In this stage, two control images from the video sequence are chosen and the KLT tracker is used for the extraction of the natural feature points. After that, the Affine Coordinate System (ACS) is defined by using these natural feature points. The user is responsible to select four planar points for setting the Euclidean WCS in two control images, respectively, and then the affine coordinates of the specific points are reconstructed by using the affine reconstruction method. While, the second stage is re-projection. Compute the corresponding affine reprojection matrix in the live video frame by using the natural feature points that have been tracked by the KLT technique. The image projections of the selected points are predestined in the live video sequence by using the affine re-projection matrix. However, the third stage is the camera extrinsic parameters such as camera pose, which are predestined in terms of the four selected points achieved in the second stage. Eventually, the virtual objects can be rendered on the real scene by using the graphics pipeline techniques such as OpenGL. The experiment results showed some improvement compared to the previous work [33]. The main limitation of this research is that the user has to manually determine the four points in the initialization stage, as well as, the authors do not consider tracking the feature points.

**65**

**Figure 5.**

*Realistic reconstruction of cultural heritage.*

*Cultural Heritage in Marker-Less Augmented Reality: A Survey*

tracking of points normal to the object contours [27].

Reconstruction is one of the basic processes in the AR. It refers to the construction of virtual objects in a similar way to replicate the original building [23]. Many cultural heritage applications require to reconstruct of real-world objects and scenes. Reconstruction process becomes increasingly common to use for modelling purpose of cultural heritage. This is fundamentally because of rapid development in laser-scanning techniques, 3D modelling, image-based modelling techniques, the power of the computer and virtual reality. The default objects appear on an appropriate model that covers the details of accurate enough is essential [23]. Objects must be exactly identical to the original ones which visitors can see clearly at the background of live videos. In addition, interest in objects' shadows is an essential part of the reconstruction process. Real-time shadows are created in relation to the sun position in a specified location, date and time. Eventually, the influence of the sky lighting on the virtual building during the daytime is the last part of creating the realistic virtual heritage in AR systems. Most virtual reconstruction techniques are based mainly on 3D scanning techniques, in order to get the objects faithfully [34]. **Figure 5** shows the reconstruction of the building and place it in the real

Tracking is a substantial subject in a real-time augmented reality context. The key requirements for tracking are the high level of accuracy and low level of latency at a sensible cost. Objects' tracking in the scene is defined as the amount of the pose between the camera and the objects. Virtual objects can be displayed into the scene using the pose. A local moving edges tracker have been used to provide real-time

A new method for conception of vision-based augmented reality systems is presented by considering either 3D model-based tracking techniques or 3D modelfree tracking approaches [1]. The method depends on decreasing the cost function expressed in the image and this decreasing is achieved via a visual serving control law. The main feature of a model-based method is that the information about the scene allows improvement of robustness and system' performance by the ability for predicting hidden movement of the object and acts in order to reduce the effects of outlier data introduced in the tracking process [35]. It is occasionally necessary to achieve the pose computation with minimal constraining information on the viewed scene because 3D information is not readily available in certain circumstances. The algorithm has been tested on different image sequences and for diverse applications, which illustrate a real usability of this approach [1]. This research has

*DOI: http://dx.doi.org/10.5772/intechopen.80975*

**6.2 Reconstruction**

environment.

**6.3 Tracking**
