Manuel Loaiza - Academia.edu (original) (raw)

Papers by Manuel Loaiza

2018 20th Symposium on Virtual and Augmented Reality (SVR), 2018

Augmented Reality (AR) is expected to be one of the technologies that will have a high impact on ... more Augmented Reality (AR) is expected to be one of the technologies that will have a high impact on different areas such as education, maintenance or game development. One of the main drawbacks of using this technology has been the complexity for users without programming skills to create AR applications. The use of High-Level Content Design Frameworks (HCDF) is proposed as a solution to facilitate the process of developing AR applications. There are different types of HCDF, but it is necessary to classify them so further research would fill gaps in the current literature. To the best of our knowledge, no research has been done focusing on analyzing the articles related to HCDF. As a solution to these problems, we have proposed a systematic method to classify and find current trends in research focused on HCDF.

SBC Journal on Interactive Systems, 2011

This paper describes the Virtual Reality Group of Tecgraf/PUC-Rio and some of its research and de... more This paper describes the Virtual Reality Group of Tecgraf/PUC-Rio and some of its research and development activities in the areas of virtual and augmented reality, 3D user interaction and collaborative systems.

This paper proposes interaction techniques to use Microsoft Kinect in Virtual Reality (VR) applic... more This paper proposes interaction techniques to use Microsoft Kinect in Virtual Reality (VR) applications. Most of the proposed techniques are used in a similar fashion with devices other than Microsoft Kinect, that will allow a user to select objects in a virtual scene and navigate throughout that scene. Kinect was chosen because it is low cost, easily portable and does not require the user to have any equipment attached or held by him, increasing the user's sense of immersion. Techniques are discussed, pointing out advantages and disadvantages of each one, with the intention of creating a knowledge base for the development of practical VR applications.

International Journal of Advanced Computer Science and Applications, 2022

Volumetric reconstruction from one or multiple RGB images has shown significant advances in recen... more Volumetric reconstruction from one or multiple RGB images has shown significant advances in recent years, but the approaches used so far do not take advantage of stereoscopic features such as distance blur, perspective disparity, textures, etc. that are useful to shape the object volumes. Our study is to evaluate a convolutional neural network architecture for reconstruction of 128 3 voxel models from 960 pairs of stereoscopic images. The preliminary results show an 80% of coincidence with the original models in 2 categories using the Intersection over Union metric. These results indicate that good reconstructions can be made from a small dataset. This will reduce the time and memory usage for this task.

Tecgraf/PUC-Rio and some of its research and development activities in the areas of virtual and a... more Tecgraf/PUC-Rio and some of its research and development activities in the areas of virtual and augmented reality, 3D user interaction and collaborative systems. The main projects of the group are related to the oil & gas industry, and include the development of real-time photorealist interaction and visualization tools for virtual environments, which support programs for the representation and inspection of engineering models as well as for the representation of natural models such as terrains and oil reservoirs. Keywords- virtual reality,3D user interaction,augmented reality

Computers & Graphics, 2011

In this paper we present a method for the calibration of multiple cameras based on the extraction... more In this paper we present a method for the calibration of multiple cameras based on the extraction and use of the physical characteristics of a one-dimensional invariant pattern which is defined by four collinear markers. The advantages of this kind of pattern stand out in two key steps of the calibration process. In the initial step of camera calibration methods,

Abstract. In this paper, we describe a novel algorithm to group, label, identify and perform opti... more Abstract. In this paper, we describe a novel algorithm to group, label, identify and perform optical tracking of marker sets, which are grouped into two specific configurations, and whose projective invariant properties will allow obtaining a unique identification for each predefined marker pattern. These configurations are formed by 4 collinear and 5 coplanar markers. This unique identification is used to correctly recognize various and different marker patterns inside the same tracking area, in real time. The algorithm only needs image coordinates of markers to perform the identification of marker patterns. For grouping the dispersed markers that appear in the image, the algorithm uses a “divide and conquer ” strategy to segment the image and give some neighborhood reference among markers.

The emergency of cheaper technologies for immersive environments has considerably increased the i... more The emergency of cheaper technologies for immersive environments has considerably increased the interest in Virtual Reality applications. However, VR frameworks currently available force user applications to be developed specifically for them. This increases the cost of converting an existing application to virtual reality environments. This paper proposes a new framework, the LVRL (Lightweight Virtual Reality Libraries), which allows the creation or conversion of existing applications to VR without changing the application's structure. The LVRL's main objective is to provide a non-intrusive and transparent programming interface allowing the development of VR applications by non-VR developers. This paper describes LVRL's architecture, features, usage and benefits obtained by applications using it.

Spatial augmented reality allows users to create a projected virtual environment on irregular sur... more Spatial augmented reality allows users to create a projected virtual environment on irregular surfaces. This demands an accurate Camera-Projector calibration process in order to produce precise 3D information to match the real object. This paper presents a framework to process data achieved from a calibration of a Kinect-Projector system in visualization applications, allowing the user to create an augmented reality environment without having extensive process of the Camera-Projector calibration, while maintaining a precise calibration to the projection on irregular surfaces. Additionally, different calibration techniques were evaluated in order to demonstrate the better approaches.

Lecture Notes in Computer Science, 2014

Multitouch interfaces allow interacting with a virtual object directly, similar to a real object.... more Multitouch interfaces allow interacting with a virtual object directly, similar to a real object. However, there are several issues to be resolved, such as the accuracy of the manipulation, the occlusion, the separability of the manipulation, etc. Multitouch interfaces allow multiple spatial transformations that can be performed on a virtual object with only a gesture. For example, an object can be rotated, translated and scaled with two fingers with a single gesture. However, some unwanted movements may occur accidentally. Separability techniques appear with the intent to prevent unwanted movements on multitouch surfaces. Occlusion is another problem that occurs in multitouch interfaces. Often the user's hand hides the vision of the object with which he/she interacts; or the user's action on interface hinders the movement when it clicks on a bottom that triggers action. This paper proposes two techniques of separability, aiming to reduce the problems that arise due to excessive freedom of manipulation in multi-touch interfaces, and evaluates the efficiency of these techniques. The techniques developed are not only applicable in simple virtual objects; they are also for WIMP (windows, icons, menus, pointer) objects, aiming to reduce occlusion. A series of tests was performed to evaluate precision, occlusion time for completion of task, and ease of use.

2014 XVI Symposium on Virtual and Augmented Reality, 2014

With the development of VR (Virtual Reality) technologies, several input and output devices have ... more With the development of VR (Virtual Reality) technologies, several input and output devices have been created. There is a category of interaction devices that is becoming important due to the increasing availability of digital cameras. This kind of optical device uses the image captured by a set of digital cameras to track the position of objects and to provide positioning and orientation data for RV systems. This paper presents the development of two low-cost optical tracking devices with six degrees of freedom for desktop applications. The first device uses three webcams mounted on a box and detects the movements of a white marker over its black background. An alternative approach is also presented, using a single camera that, when moved by the user over a mark, works as a 3D mouse. Finally, the use of these devices in VR applications is presented.

This paper presents a six degrees of freedom (6 DoF) optical tracking device for interaction in d... more This paper presents a six degrees of freedom (6 DoF) optical tracking device for interaction in desktop VR applications. The device uses three webcams mounted on a box and uses computer vision techniques to detect the movements of white markers over a black background. We present the process of movements' detection and how this information is adapted to be applied in interaction events and to simulate a 3D mouse device.

The emergence of cheaper technologies for immersive environments has increased considerably the i... more The emergence of cheaper technologies for immersive environments has increased considerably the interest on applications of Virtual Reality (VR). However, currently available VR frameworks force user applications to be developed specifically for them. This increases the cost of converting an existing graphical application to virtual reality environments. This paper proposes a new framework, the LVRL (Lightweight Virtual Reality Libraries), which allows both creation and conversion of existing applications to VR without changing the structure of the application. The LVRL main objective is to provide a minimalist programming interface and non intrusive allowing the development of VR applications by non VR developers. This article describes the architecture of LVRL, its features, usage and the benefits obtained by the applications that use it.

This paper presents an algorithm for using projective invariant patterns in augmented reality app... more This paper presents an algorithm for using projective invariant patterns in augmented reality applications. It is actually an adaptation of a previous algorithm for an optical tracking device, that works with infrared illumination and filtering. The present algorithm removes the necessity of working in a controlled environment, which would be inadequate for augmented reality applications. In order to compensate the excess of image noise caused by the absence of the infrared system, the proposed algorithm includes a fast binary decision tree in the process flow. We show that the algorithm achieves real time rates. 2 Related Work One of the most common solutions for objects identification in AR is the use of ARToolkit-like planar patterns [2]. In addition to the identification of objects,

2018 20th Symposium on Virtual and Augmented Reality (SVR), 2018

Augmented Reality (AR) is expected to be one of the technologies that will have a high impact on ... more Augmented Reality (AR) is expected to be one of the technologies that will have a high impact on different areas such as education, maintenance or game development. One of the main drawbacks of using this technology has been the complexity for users without programming skills to create AR applications. The use of High-Level Content Design Frameworks (HCDF) is proposed as a solution to facilitate the process of developing AR applications. There are different types of HCDF, but it is necessary to classify them so further research would fill gaps in the current literature. To the best of our knowledge, no research has been done focusing on analyzing the articles related to HCDF. As a solution to these problems, we have proposed a systematic method to classify and find current trends in research focused on HCDF.

SBC Journal on Interactive Systems, 2011

This paper describes the Virtual Reality Group of Tecgraf/PUC-Rio and some of its research and de... more This paper describes the Virtual Reality Group of Tecgraf/PUC-Rio and some of its research and development activities in the areas of virtual and augmented reality, 3D user interaction and collaborative systems.

This paper proposes interaction techniques to use Microsoft Kinect in Virtual Reality (VR) applic... more This paper proposes interaction techniques to use Microsoft Kinect in Virtual Reality (VR) applications. Most of the proposed techniques are used in a similar fashion with devices other than Microsoft Kinect, that will allow a user to select objects in a virtual scene and navigate throughout that scene. Kinect was chosen because it is low cost, easily portable and does not require the user to have any equipment attached or held by him, increasing the user's sense of immersion. Techniques are discussed, pointing out advantages and disadvantages of each one, with the intention of creating a knowledge base for the development of practical VR applications.

International Journal of Advanced Computer Science and Applications, 2022

Volumetric reconstruction from one or multiple RGB images has shown significant advances in recen... more Volumetric reconstruction from one or multiple RGB images has shown significant advances in recent years, but the approaches used so far do not take advantage of stereoscopic features such as distance blur, perspective disparity, textures, etc. that are useful to shape the object volumes. Our study is to evaluate a convolutional neural network architecture for reconstruction of 128 3 voxel models from 960 pairs of stereoscopic images. The preliminary results show an 80% of coincidence with the original models in 2 categories using the Intersection over Union metric. These results indicate that good reconstructions can be made from a small dataset. This will reduce the time and memory usage for this task.

Tecgraf/PUC-Rio and some of its research and development activities in the areas of virtual and a... more Tecgraf/PUC-Rio and some of its research and development activities in the areas of virtual and augmented reality, 3D user interaction and collaborative systems. The main projects of the group are related to the oil & gas industry, and include the development of real-time photorealist interaction and visualization tools for virtual environments, which support programs for the representation and inspection of engineering models as well as for the representation of natural models such as terrains and oil reservoirs. Keywords- virtual reality,3D user interaction,augmented reality

Computers & Graphics, 2011

In this paper we present a method for the calibration of multiple cameras based on the extraction... more In this paper we present a method for the calibration of multiple cameras based on the extraction and use of the physical characteristics of a one-dimensional invariant pattern which is defined by four collinear markers. The advantages of this kind of pattern stand out in two key steps of the calibration process. In the initial step of camera calibration methods,

Abstract. In this paper, we describe a novel algorithm to group, label, identify and perform opti... more Abstract. In this paper, we describe a novel algorithm to group, label, identify and perform optical tracking of marker sets, which are grouped into two specific configurations, and whose projective invariant properties will allow obtaining a unique identification for each predefined marker pattern. These configurations are formed by 4 collinear and 5 coplanar markers. This unique identification is used to correctly recognize various and different marker patterns inside the same tracking area, in real time. The algorithm only needs image coordinates of markers to perform the identification of marker patterns. For grouping the dispersed markers that appear in the image, the algorithm uses a “divide and conquer ” strategy to segment the image and give some neighborhood reference among markers.

The emergency of cheaper technologies for immersive environments has considerably increased the i... more The emergency of cheaper technologies for immersive environments has considerably increased the interest in Virtual Reality applications. However, VR frameworks currently available force user applications to be developed specifically for them. This increases the cost of converting an existing application to virtual reality environments. This paper proposes a new framework, the LVRL (Lightweight Virtual Reality Libraries), which allows the creation or conversion of existing applications to VR without changing the application's structure. The LVRL's main objective is to provide a non-intrusive and transparent programming interface allowing the development of VR applications by non-VR developers. This paper describes LVRL's architecture, features, usage and benefits obtained by applications using it.

Spatial augmented reality allows users to create a projected virtual environment on irregular sur... more Spatial augmented reality allows users to create a projected virtual environment on irregular surfaces. This demands an accurate Camera-Projector calibration process in order to produce precise 3D information to match the real object. This paper presents a framework to process data achieved from a calibration of a Kinect-Projector system in visualization applications, allowing the user to create an augmented reality environment without having extensive process of the Camera-Projector calibration, while maintaining a precise calibration to the projection on irregular surfaces. Additionally, different calibration techniques were evaluated in order to demonstrate the better approaches.

Lecture Notes in Computer Science, 2014

Multitouch interfaces allow interacting with a virtual object directly, similar to a real object.... more Multitouch interfaces allow interacting with a virtual object directly, similar to a real object. However, there are several issues to be resolved, such as the accuracy of the manipulation, the occlusion, the separability of the manipulation, etc. Multitouch interfaces allow multiple spatial transformations that can be performed on a virtual object with only a gesture. For example, an object can be rotated, translated and scaled with two fingers with a single gesture. However, some unwanted movements may occur accidentally. Separability techniques appear with the intent to prevent unwanted movements on multitouch surfaces. Occlusion is another problem that occurs in multitouch interfaces. Often the user's hand hides the vision of the object with which he/she interacts; or the user's action on interface hinders the movement when it clicks on a bottom that triggers action. This paper proposes two techniques of separability, aiming to reduce the problems that arise due to excessive freedom of manipulation in multi-touch interfaces, and evaluates the efficiency of these techniques. The techniques developed are not only applicable in simple virtual objects; they are also for WIMP (windows, icons, menus, pointer) objects, aiming to reduce occlusion. A series of tests was performed to evaluate precision, occlusion time for completion of task, and ease of use.

2014 XVI Symposium on Virtual and Augmented Reality, 2014

With the development of VR (Virtual Reality) technologies, several input and output devices have ... more With the development of VR (Virtual Reality) technologies, several input and output devices have been created. There is a category of interaction devices that is becoming important due to the increasing availability of digital cameras. This kind of optical device uses the image captured by a set of digital cameras to track the position of objects and to provide positioning and orientation data for RV systems. This paper presents the development of two low-cost optical tracking devices with six degrees of freedom for desktop applications. The first device uses three webcams mounted on a box and detects the movements of a white marker over its black background. An alternative approach is also presented, using a single camera that, when moved by the user over a mark, works as a 3D mouse. Finally, the use of these devices in VR applications is presented.

This paper presents a six degrees of freedom (6 DoF) optical tracking device for interaction in d... more This paper presents a six degrees of freedom (6 DoF) optical tracking device for interaction in desktop VR applications. The device uses three webcams mounted on a box and uses computer vision techniques to detect the movements of white markers over a black background. We present the process of movements' detection and how this information is adapted to be applied in interaction events and to simulate a 3D mouse device.

The emergence of cheaper technologies for immersive environments has increased considerably the i... more The emergence of cheaper technologies for immersive environments has increased considerably the interest on applications of Virtual Reality (VR). However, currently available VR frameworks force user applications to be developed specifically for them. This increases the cost of converting an existing graphical application to virtual reality environments. This paper proposes a new framework, the LVRL (Lightweight Virtual Reality Libraries), which allows both creation and conversion of existing applications to VR without changing the structure of the application. The LVRL main objective is to provide a minimalist programming interface and non intrusive allowing the development of VR applications by non VR developers. This article describes the architecture of LVRL, its features, usage and the benefits obtained by the applications that use it.

This paper presents an algorithm for using projective invariant patterns in augmented reality app... more This paper presents an algorithm for using projective invariant patterns in augmented reality applications. It is actually an adaptation of a previous algorithm for an optical tracking device, that works with infrared illumination and filtering. The present algorithm removes the necessity of working in a controlled environment, which would be inadequate for augmented reality applications. In order to compensate the excess of image noise caused by the absence of the infrared system, the proposed algorithm includes a fast binary decision tree in the process flow. We show that the algorithm achieves real time rates. 2 Related Work One of the most common solutions for objects identification in AR is the use of ARToolkit-like planar patterns [2]. In addition to the identification of objects,