R3MR: Region Growing Based 3D Mesh Reconstruction for Big Data Platform

Abstract

Visualization is one of the most intuitive and perceptible ways for information representation in the big data era. As an essential part of the visualization, 3D mesh reconstruction is facing great challenges due to its characteristics of quantity, non-structure, and low-accuracy. The traditional 3D mesh reconstruction method has strict theoretical proof and can be used to reconstruct the surface of the complex topological structure for computer rendering and display. However, it is not suitable to handle a large number of point cloud and noise point cloud in a big data platform because the process is inefficient, low-automation and requires massive calculations. To address this issue, we propose a region growing based 3D mesh reconstruction (R3MR) in the big data platform. Firstly, we divide the large data points into three categories: flat point set, high curvature point set, and boundary point set. The errors of topological structure for 3D meshes usually occur in the place with large curvatures and noise points, so the division of high curvature point set is beneficial to solve the low-accuracy problem in 3D mesh reconstruction. Moreover, the flat points can be treated as one kind of point to avoid repetitive calculations because their features are basically the same. Hence, the division of the flat point set is beneficial to solve the problem of quantity and massive calculations. Secondly, our proposal is to start the mesh reconstruction from the flat point set progressively, because it can obtain the outline of the 3D model. In many scenarios, such as autonomous driving, only the overall outline of the model is required. Finally, during the 3D mesh reconstruction, the inner edge adjacency list and optimal selection principle are set to improve the robustness of the whole system. Simulation experiments show that the proposed 3D mesh reconstruction can naturally reflect the detailed features of objects in the big data platform, especially effective for the scattered point cloud.

3D Reconstruction for Super-Resolution CT Images in the Internet of Health Things Using Deep Learning

“…With the high-accuracy and high-security 3D reconstruction results [33], the IoHT can remotely diagnose diseases, which directly integrates all medical resources to serve patients. On the one hand, the IoHT application of diagnosing disease via machine learning and AI is valuable for the patients to get the high-accuracy diagnosis result.…”

“…Fast up-convolution adjusts the up-sampling operation to make it more efficient. The convolution kernel with the original size of 55  is reset to four small sizes: (a) 33  , (b) 32  , (c) 23  , and (d) 22  . By interleaving four feature maps, the image can be magnified 2  .…”

The Impact of Cloud Computing-Based Big Data Platform on IE Education

“…Li et al focused on visualization. As an important part of visualization, they proposed 3D mesh reconstruction (R3MR) based on regional growth in the big data platform [8]. Generally speaking, due to the wide application and many technical points, there are many and very exciting related research projects on big data platforms, and there are also many research projects on cloud computing, but there is still relatively little research on the topic of this article.…”

HUMANNET—A Two-Tiered Deep Neural Network Architecture for Self-Occluding Humanoid Pose Reconstruction

“…While the majority of methods focus on voxel based mesh representation [22][23][24][25][26][27], for object reconstruction due to their representation simplicity, voxels have one major flaw-exponentially increasing requirements to train them with increasing fidelity. Some papers tried to solve this ever-increasing memory requirements using smarter data representation styles like octrees [28,29].…”