3D reconstruction using Structure From Motion (SFM) algorithm and Multi View Stereo (MVS) based on computer vision

Kholil, Moch.; Ismanto, I; Fuad, M. Nur

doi:10.1088/1757-899x/1073/1/012066

Cited by 15 publications

(9 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dense clouds are then classified to distinguish points that correspond to land, vegetation, or other structures such as buildings [24], [25]. Classified dense cloud is the key to producing the main product for volcanic eruption impact analysis.…”

Section: Photogrammetric Processingmentioning

confidence: 99%

Aero Mapping Application for Affected Area Detection by the Semeru Volcano Eruption in 2022

Irawan,

Prasetyo,

Yusuf

et al. 2023

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

The development of geospatial technology, especially Unmanned Aerial vehicles (UAV) or drones, has been growing rapidly. One of the uses of UAV is to detect disaster hazards, the extent of the affected area, and the element of risks. The latest UAV technology in the form of Aero Mapping is beneficial for mapping disaster-affected areas, in this case, post-volcanic eruption lava flows. Aero mapping with the rotary wing type is low-cost (<$ 2000/Rp.29.500.000) but a potent tool for collecting spatial data quickly and accurately. This application is applied to detect areas affected by volcanic eruptions. The photo image produced by the UAV can be used to analyze lava flows, lava deposits, changes in landforms, and changes in land cover due to volcanic eruptions. This study aims to detect the area affected by the eruption of Semeru Volcano post-eruption in 2022. In the research study area, there is no detailed scale mapping can detect the direction/path of post-eruptive lahars. This research seeks to detail the description of the affected areas. The results of aerial photographs show that low-cost UAVs are capable of producing high-resolution data of up to 2.86 cm/px (Orthomosaic), 6.94 cm/px (DSM), and 3.94 cm/px (GSD) with a total area of up to 755 Ha. This area is obtained from 34 flight processes at an altitude of 120 meters with 70% front and side overlap. These findings prove that aero mapping is a low-cost technique that can be used to map new lava flows after the 2022 eruption at Semeru Volcano.

show abstract

Section: Photogrammetric Processingmentioning

confidence: 99%

Aero Mapping Application for Affected Area Detection by the Semeru Volcano Eruption in 2022

Irawan,

Prasetyo,

Yusuf

et al. 2023

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

show abstract

“…The determinant value of Hessian matrix is used as the feature detection of SURF, and the integral graph is used to improve the operation efficiency. The descriptor of SURF is based on the response of a 2D discrete wavelet transform and makes efficient use of the integral graph [24], which is more efficient and accurate than SIFT in running speed and brightness change; however, SIFT works better in the case of scale and rotation transformation, so the SIFT feature-extraction results and SURF feature-extraction results are fused to learn from each other and increase the number of matching feature points [20,21].…”

Section: Extraction and Matching Of Image Feature Pointsmentioning

confidence: 99%

“…MVS captures more scene viewpoints to improve robustness and reduce the impact of image noise and surface texture. It is usually divided into voxel-based algorithms, point-cloud diffusion algorithms and depth-map fusion algorithm, according to the representation of scene [21].…”

Section: Introduction To Mvs Theorymentioning

confidence: 99%

Research on Multi-View 3D Reconstruction Technology Based on SFM

Gao

Zhao

Han

et al. 2022

Sensors

View full text Add to dashboard Cite

Multi-view 3D reconstruction technology is used to restore a 3D model of practical value or required objects from a group of images. This paper designs and implements a set of multi-view 3D reconstruction technology, adopts the fusion method of SIFT and SURF feature-point extraction results, increases the number of feature points, adds proportional constraints to improve the robustness of feature-point matching, and uses RANSAC to eliminate false matching. In the sparse reconstruction stage, the traditional incremental SFM algorithm takes a long time, but the accuracy is high; the traditional global SFM algorithm is fast, but its accuracy is low; aiming at the disadvantages of traditional SFM algorithm, this paper proposes a hybrid SFM algorithm, which avoids the problem of the long time consumption of incremental SFM and the problem of the low precision and poor robustness of global SFM; finally, the MVS algorithm of depth-map fusion is used to complete the dense reconstruction of objects, and the related algorithms are used to complete the surface reconstruction, which makes the reconstruction model more realistic.

show abstract

“…The three-dimensional reconstruction technology based on the images is a technology for restoring 2D images to 3D models [28]. SFM is one of the 3D reconstruction methods, of which the principle is to apply a matching algorithm to an acquired sequence of multi-view images in order to obtain the correspondence of the same pixel points of the image and to use the matching constraint relationship in combination with the triangulation principle to obtain the 3D coordinates of the spatial points and then reconstruct a 3D model of the object [29]. The reconstruction process mainly contains the key steps such as feature point extraction and matching, sparse point cloud reconstruction and dense point cloud reconstruction.…”

Section: ) Object 3d Point Cloud Acquisitionmentioning

confidence: 99%

Research on Object Panoramic 3D Point Cloud Reconstruction System Based on Structure From Motion

et al. 2022

View full text Add to dashboard Cite

3D reconstruction is the transformation of real objects into mathematical models. By using 3D models, we can observe the shape and measure the parameters, and help us to analyze the properties of objects. For the problems of incompleteness and inefficiency in the reconstruction of object 3D point clouds, a fast and automated system for panoramic 3D point cloud reconstruction of objects was proposed. First, we designed an automatic platform, which could acquire RGB image sequences of objects in two directions. Then we adopted the Structure From Motion (SFM) algorithm to generate point clouds. For the problem of different scales of point clouds, we obtained the scaling by calculating the length ratio of the axes of the oriented bounding box, and scaled the point clouds to a uniform scale. In addition, markers were placed around the object and used to acquire the rotation matrix of the object point cloud in two directions. Finally, we verified the point cloud models of different objects generated by the system, and found that the relative error didn't exceed 6.67%. According to the results, the system proposed could reconstruct the panoramic 3D point cloud of the object better and provide a reference for related research.

show abstract

3D reconstruction using Structure From Motion (SFM) algorithm and Multi View Stereo (MVS) based on computer vision

Cited by 15 publications

References 8 publications

Aero Mapping Application for Affected Area Detection by the Semeru Volcano Eruption in 2022

Aero Mapping Application for Affected Area Detection by the Semeru Volcano Eruption in 2022

Research on Multi-View 3D Reconstruction Technology Based on SFM

Research on Object Panoramic 3D Point Cloud Reconstruction System Based on Structure From Motion

Contact Info

Product

Resources

About