Parallel Structure from Motion for Sparse Point Cloud Generation in Large-Scale Scenes

Abstract

Scene reconstruction uses images or videos as input to reconstruct a 3D model of a real scene and has important applications in smart cities, surveying and mapping, military, and other fields. Structure from motion (SFM) is a key step in scene reconstruction, which recovers sparse point clouds from image sequences. However, large-scale scenes cannot be reconstructed using a single compute node. Image matching and geometric filtering take up a lot of time in the traditional SFM problem. In this paper, we propose a novel divide-and-conquer framework to solve the distributed SFM problem. First, we use the global navigation satellite system (GNSS) information from images to calculate the GNSS neighborhood. The number of images matched is greatly reduced by matching each image to only valid GNSS neighbors. This way, a robust matching relationship can be obtained. Second, the calculated matching relationship is used as the initial camera graph, which is divided into multiple subgraphs by the clustering algorithm. The local SFM is executed on several computing nodes to register the local cameras. Finally, all of the local camera poses are integrated and optimized to complete the global camera registration. Experiments show that our system can accurately and efficiently solve the structure from motion problem in large-scale scenes.

Automatic Extrinsic Calibration of 3D LIDAR and Multi-Cameras Based on Graph Optimization

“…In recent years, with the increasing demands on perception performance in the fields of mobile robots [ 1 , 2 , 3 ], surveying and mapping [ 4 , 5 , 6 , 7 , 8 ], 3D reconstruction [ 9 , 10 , 11 , 12 ], and autonomous driving [ 13 , 14 ], the application of multi-sensor fusion technology is more and more extensive [ 15 , 16 , 17 ]. Among them, LIDAR and cameras perform particularly well in multi-sensor fusion technology [ 18 , 19 , 20 , 21 ].…”

Comprehensive mPoint: A Method for 3D Point Cloud Generation of Human Bodies Utilizing FMCW MIMO mm-Wave Radar

“…Radar point cloud data not only contains almost all the aforementioned features but also can directly indicate the spatial locations of the targets, and they are receiving more attention. However, most of these research investigations are focused only on feature extraction and recognition after obtaining point clouds without paying much attention to the generation of the point cloud [15,[32][33][34][35][36]. This causes inaccurate results because it is well known that the quality of the generated point cloud has a significant effect on the accuracy and effectiveness of the subsequent data process.…”