Article

Innovations to create a Digital India-Distinguishing reality from virtuality

Authors:
To read the full-text of this research, you can request a copy directly from the author.

Abstract

Mixed reality (MR) also referred as hybrid reality, is the combination of real and virtual worlds in order to produce some new environments and visualizations where physical objects and digital objects synchronize in real time. In this paper, our focus is on virtual reality related technologies that collate the real and virtual worlds i.e. mixed reality. Even though the term mixed reality is now defined with a related term augmented reality. Augmented reality refers to any case in which an otherwise real environment is "augmented" by means of virtual (computer graphic) objects. This paper focuses on mixed / augmented reality visual display i.e. the Windows Holographic System called Project HoloLens that is developed and manufactured by Microsoft.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the author.

... Classification using the 3D point cloud data has gained considerable attention across several research domains e.g. autonomous navigation [21,24], virtual and augmented reality creation [10,23] and urban [13,34]-forest monitoring [19] tasks. Amongst the state-of-the-art classification techniques, CNN based models offer a reliable and cost-effective solution to process 3D point cloud datasets that are massive and unstructured in nature. ...
Preprint
Scene understanding of full-scale 3D models of an urban area remains a challenging task. While advanced computer vision techniques offer cost-effective approaches to analyse 3D urban elements, a precise and densely labelled dataset is quintessential. The paper presents the first-ever labelled dataset for a highly dense Aerial Laser Scanning (ALS) point cloud at city-scale. This work introduces a novel benchmark dataset that includes a manually annotated point cloud for over 260 million laser scanning points into 100'000 (approx.) assets from Dublin LiDAR point cloud [12] in 2015. Objects are labelled into 13 classes using hierarchical levels of detail from large (i.e., building, vegetation and ground) to refined (i.e., window, door and tree) elements. To validate the performance of our dataset, two different applications are showcased. Firstly, the labelled point cloud is employed for training Convolutional Neural Networks (CNNs) to classify urban elements. The dataset is tested on the well-known state-of-the-art CNNs (i.e., PointNet, PointNet++ and So-Net). Secondly, the complete ALS dataset is applied as detailed ground truth for city-scale image-based 3D reconstruction.
... Classification using the 3D point cloud data has gained considerable attention across several research domains e.g. autonomous navigation [21,24], virtual and augmented reality creation [10,23] and urban [13,34]-forest monitoring [19] tasks. Amongst the state-of-the-art classification techniques, CNN based models offer a reliable and cost-effective solution to process 3D point cloud datasets that are massive and unstructured in nature. ...
Conference Paper
Full-text available
Scene understanding of full-scale 3D models of an urban area remains a challenging task. While advanced computer vision techniques offer cost-effective approaches to analyse 3D urban elements, a precise and densely labelled dataset is quintessential. The paper presents the first-ever labelled dataset for a highly dense Aerial Laser Scanning (ALS) point cloud at city-scale. This work introduces a novel benchmark dataset that includes a manually annotated point cloud for over 260 million laser scanning points into 100'000 (approx.) assets from Dublin LiDAR point cloud (Laefer, et al) in 2015. Objects are labelled into 13 classes using hierarchical levels of detail from large (i.e. building, vegetation and ground) to refined (i.e. window, door and tree) elements. To validate the performance of our dataset, two different applications are showcased. Firstly, the labelled point cloud is employed for training Convolutional Neural Networks (CNNs) to classify urban elements. The dataset is tested on the well-known state-of-the-art CNNs (i.e. PointNet, PointNet++ and So-Net). Secondly, the complete ALS dataset is applied as detailed ground truth for city-scale image-based 3D reconstruction.
Microsoft HoloLens Launch Games, Apps Detailed
  • John Gaudiosi
Gaudiosi, John (28 February 2016). "Microsoft HoloLens Launch Games, Apps Detailed". Fortune. Retrieved 7 March 2016.