Fri, Sep 29, 2017 @ 03:00 PM - 04:00 PM
Sonny Astani Department of Civil and Environmental Engineering
Conferences, Lectures, & Seminars
Speaker: Meida Chen and Sasan Tavakkol, Astani CEE Graduate Students
Talk Title: Point Cloud Meshes Segmentation and Information Extraction of Outdoor Scenes for The Creation of Virtual Environments and Simulation andInteractive and Immersive Coastal Hydrodynamic Simulation
Abstract: By Meida Chen
Be able to segment, classify, and recognize different types of objects and identify and extract associated features in a photogrammetric generated meshes is essential for creating realistic virtual simulations. Rendering different objects in a virtual environment differently and assign actual physical properties to each object will not only enhance the visual quality but also allow various user interaction with a terrain model. For instance, consider the case of training soldiers in a virtual environment with 3D meshes representing the scene. The task is to recognize the shortest path from location A to location B with the minimum exposure to enemy fire. With the artificial intelligence AI searching algorithm, such as A, the shortest path could be computed, and penalties cloud be assigned to a route based on the number of obstructions that are blocking the enemies line of sight. However, realistically speaking, line of sight that is blocked by buildings and trees should be assigned with different penalties when considering a route, since some materials are easy to be destroyed and damaged. Though this example is an oversimplification, it emphasizes the point that without segmented semantic data, realistic virtual simulations could not be achieved. Thus, in this study the authors established a mesh segmentation and information extraction framework that combines both supervised and unsupervised machine learning algorithms to analyze meshes point clouds that are generated with photogrammetric technique. The segmentation process will be first performed on the generated 3D point clouds. Following that, the generated meshes will be segmented accordingly. Object information such as individual tree locations, the dimension of a tree, and building footprints are then extracted separately. The proposed information extraction processes are designed to overcome the data quality issues in photogrammetric generated point clouds data tend to be noisy, and in some cases parts of a wall and the trunk of a tree cannot be captured due to dense canopy.
By Sasan Tavakkol
Recent catastrophic events such as the Tsunami in Japan 2011 and Hurricane Harvey storm surge and winds in the US 2017, have raised the global awareness for an urgent need to understand the response of developed coastal regions to tsunamis and wind waves. We discuss our efforts in developing the first interactive coastal wave simulation and visualization software, called Celeris. This software can significantly help scientists better understand nearshore wave dynamics as it allows them to observe wave interactions in real time, modify the boundary conditions and model parameters as the model is running, and see the effect of changes immediately. Celeris is released under a GNU license and is currently in use by hundreds of coastal researchers and engineering firms over the world. This software uses a hybrid finite volume finite difference method to solve the extended Boussinesq equations on the GPU. We also explore the opportunities in immersive visualization of coastal waves through Virtual Reality and Augmented Reality to help engineers work in an interactive, immersive, and collaborative environment.
Audiences: Everyone Is Invited
Posted By: Evangeline Reyes