Search NASA⌕ Search

DOE OSTI · 1884976

Background-Aware 3-D Point Cloud Segmentation With Dynamic Point Feature Aggregation

Abstract

With the proliferation of LiDAR sensors and 3-D vision cameras, 3-D point cloud analysis has attracted significant attention in recent years. In this article, we propose a novel 3-D point cloud learning network, referred to as dynamic point feature aggregation network (DPFA-Net), by selectively performing the neighborhood feature aggregation (FA) with dynamic pooling and an attention mechanism. DPFA-Net has two variants for semantic segmentation and classification of 3-D point clouds. As the core module of the DPFA-Net, we propose an FA layer, in which features of the dynamic neighborhood of each point are aggregated via a self-attention mechanism. In contrast to other segmentation models, which aggregate features from fixed neighborhoods, our approach can aggregate features from different neighbors in different layers providing a more selective and broader view to the query points and focusing more on the relevant features in a local neighborhood. In addition, to further improve the performance of semantic segmentation, we exploit the background–foreground (BF) information and present two novel approaches, namely, two-stage BF-Net and BF regularization. Experimental results show that the proposed DPFA-Net achieves the state-of-the-art overall accuracy score of 89.22% for semantic segmentation on the Stanford large-scale 3-D Indoor Spaces (S3DIS) dataset and provides consistently satisfactory performance across different tasks of semantic segmentation, part segmentation, and 3-D object classification. Furthermore, our model achieves 93.1% accuracy on the ModelNet40 dataset and provides a mean shape intersection-over-union (IoU) value of 85.5% for part segmentation on the ShapeNet-Part dataset. It is a also computationally more efficient compared to other methods.

Explore related subjects

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Chen, Jiajing, Kakillioglu, Burak, Velipasalar, Senem. 2022-04-18. Background-Aware 3-D Point Cloud Segmentation With Dynamic Point Feature Aggregation. https://doi.org/10.1109/tgrs.2022.3168555. https://searchnasa.com/record/osti%3A1884976/background-aware-3-d-point-cloud-segmentation-with-dynamic-point-feature-aggregation

Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Search NASA by Indiciae: BibTeX · RIS.

KEEP EXPLORING

Related reports

GROVER: Ground-based Robotic Omnidirectional Vehicle for Electric Research

Oak Ridge National Laboratory has developed a living laboratory to accelerate the development of electric vehicles and connected and automated vehicle (CAV) technologies. GROVER is a small autonomous bus that uses pulsed laser sensors to move in any direction, with four wheels operating independently, rotating a full 360 degrees.

3-D↗

A Multilevel in Space and Energy Solver for 3-D Multigroup Diffusion and Coarse-Mesh Finite Difference Eigenvalue Problems

The Multilevel in Space and Energy Diffusion (MSED) method accelerates the iterative convergence of multigroup diffusion eigenvalue problems by performing work on lower-order equations with only one group and/or coarser spatial grids. It consists of two primary components: (1) a grey (one-group) diffusion eigenvalue problem that is solved via Wielandt-shifted power iteration (PI) and (2) a multigrid-in-space linear solver. In previous work, the efficiency of MSED was verified using Fourier analysis and numerical results from a one-dimensional multigroup diffusion code. Since that work, MSED has been implemented as a solver for the coarse-mesh finite difference (CMFD) system in the three-dimensional Michigan Parallel Characteristics Transport (MPACT) code. In this paper, the results from the implementation of MSED in MPACT are introduced, and the changes needed to make MSED more suitable for MPACT are described. For problems without feedback, the conclusions in this paper show that MSED can reduce the CMFD run time by an order of magnitude and the overall run time by a factor of 2 to 3 compared to the default CMFD solver in MPACT [PI with the generalized minimal residual (GMRES) method]. For problems with feedback, the convergence of the outer Picard iteration scheme is worsened by the well-converged CMFD solutions produced by the standard MSED method. To overcome this unintuitive deficiency, MSED may be run with looser convergence criteria (a modified version of the MSED method called MSED-L) to circumvent the issue until the multiphysics iteration in MPACT is improved. Results show that MSED-L can reduce the CMFD run time in MPACT by an order of magnitude, without negatively impacting the outer Picard iteration scheme.

3-D↗

Modeling Host-Pathogen Interactions in the Context of the Microenvironment: Three-Dimensional Cell Culture Comes of Age

Tissues and organs provide the structural and biochemical landscapes upon which microbial pathogens and commensals function to regulate health and disease. While flat two-dimensional (2-D) monolayers composed of a single cell type have provided important insight into understanding host-pathogen interactions and infectious disease mechanisms, these reductionist models lack many essential features present in the native host microenvironment that are known to regulate infection, including three-dimensional (3-D) architecture, multicellular complexity, commensal microbiota, gas exchange and nutrient gradients, and physiologically relevant biomechanical forces (e.g., fluid shear, stretch, compression). Here, a major challenge in tissue engineering for infectious disease research is recreating this dynamic 3-D microenvironment (biological, chemical, and physical/mechanical) to more accurately model the initiation and progression of host-pathogen interactions in the laboratory. Here we review selected 3-D models of human intestinal mucosa, which represent a major portal of entry for infectious pathogens and an important niche for commensal microbiota. We highlight seminal studies that have used these models to interrogate host-pathogen interactions and infectious disease mechanisms, and we present this literature in the appropriate historical context. Models discussed include 3-D organotypic cultures engineered in the rotating wall vessel (RWV) bioreactor, extracellular matrix (ECM)-embedded/organoid models, and organ-on-a-chip (OAC) models. Collectively, these technologies provide a more physiologically relevant and predictive framework for investigating infectious disease mechanisms and antimicrobial therapies at the intersection of the host, microbe, and their local microenvironments.

3-D↗