Progressive Structure from Motion by Iteratively Prioritizing and Refining Match Pairs

Xiao, Teng; Qingsong, Yan; Ma, Weile; Deng, Fei

doi:10.3390/rs13122340

Cited by 4 publications

(3 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, some objects with mirror symmetry on different sides and planes of a building. These repeated structures will lead to wrong matching relations, and will also establish wrong mutual connection relations in the image connection graph, which will most affect the reconstruction effect [15]. The repeated structure problem is shown in Fig .…”

Section: Repetitive Structure and Short Baseline Problemmentioning

confidence: 99%

Optimize incremental SFM for repetitive structures and short baseline issues

2023

Preprint

View full text Add to dashboard Cite

Structure from Motion has been widely used in 3D reconstruction based on multiview geometry, which is used to construct sparse point clouds and solve camera pose information. However, there are often problematic matching pairs in image sets, which makes it difficult to obtain correct reconstruction results by SFM method. Aiming at the problems of repetitive structure and short baseline, this paper constructs the Minimum Spanning Tree to filter the mismatched image pairs, and reconstructs the connection relationship between images, thus improving the incremental SFM method. In the initialization stage, the edge weights are calculated, and the MST is extracted, and then iterative merging is performed to get the final image connection graph from which the mismatching is filtered, and then it is expanded in an incremental way until the images in the whole data set are traversed. The evaluation results of public data sets and data sets with repeated structures show that the improved incremental SFM method can achieve similar or better reconstruction results.

show abstract

Section: Repetitive Structure and Short Baseline Problemmentioning

confidence: 99%

Optimize incremental SFM for repetitive structures and short baseline issues

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Shen et al (2016) proposed guided feature matching by checking triplet vertices and loop consistency. To address the repetitive structures in ambiguous scenes, Xiao et al (2021) proposed a strategy of iterative prioritisation and refining matched pairs. Cui et al (2021) proposed a view‐graph construction method based on a verified maximum spanning tree.…”

Section: Related Workmentioning

confidence: 99%

View‐graph key‐subset extraction for efficient and robust structure from motion

Gong

Zhou

Liu

et al. 2023

The Photogrammetric Record

View full text Add to dashboard Cite

Structure from motion (SfM) is used to recover camera poses and the sparse structure of real scenes from multiview images. SfM methods construct a view‐graph from the matching relationships of images. Redundancy and incorrect edges are usually observed in it. Redundancy inhibits the efficiency and incorrect edges result in the misalignment of structures. In addition, the uneven distribution of vertices usually affects the global accuracy. To address these problems, we propose a coarse‐to‐fine approach in which the poses of an extracted key‐subset of images are first computed and then all remaining images are oriented. The core of this approach is view‐graph key‐subset extraction, which not only prunes redundant data and incorrect edges but also obtains properly distributed key‐subset vertices. The extraction approach is based on a replaceability score and an iteration‐update strategy. In this way, only vertices with high SfM importance are preserved in the key‐subset. Different public datasets are used to evaluate our approach. Due to the absence of ground‐truth camera poses in large‐scale datasets, we present new datasets with accurate camera poses and point clouds. The results demonstrate that our approach greatly increases the efficiency of SfM. Furthermore, the robustness and accuracy can be improved.

show abstract

“…The edges are weighted according to the number of matched features, and the verification is performed to increase the robustness of reconstruction. Furthermore, the incremental method proposed by Xiao et al [26] selects a pair of camera seeds from the edges of the view-graph, and then, the other cameras are incrementally registered based on the connection of cameras in the view-graph. Although image reduction/selection methods make the large-scale adjustment more manageable, the scene completeness cannot be guaranteed.…”

Section: Related Workmentioning

confidence: 99%

A New Multi-Criteria Tie Point Filtering Approach to Increase the Accuracy of UAV Photogrammetry Models

Mousavi

Varshosaz

Rashidi

et al. 2022

Drones

View full text Add to dashboard Cite

Extracting accurate tie points plays an essential role in the accuracy of image orientation in Unmanned Aerial Vehicle (UAV) photogrammetry. In this study, a Multi-Criteria Decision Making (MCDM) automatic filtering method is presented. Based on the quality features of a photogrammetric model, the proposed method works at the level of sparse point cloud to remove low-quality tie points for refining the orientation results. In the proposed algorithm, different factors that affect the quality of tie points are identified. The quality measures are then aggregated by applying MCDM methods and a competency score for each 3D tie point. These scores are employed in an automatic filtering approach that selects a subset of high-quality points which are then used to repeat the bundle adjustment. To evaluate the proposed algorithm, various internal and external studies were conducted on different datasets. The findings suggest that our method is both effective and reliable. In addition, in comparison to the existing filtering techniques, the proposed strategy increases the accuracy of bundle adjustment and dense point cloud generation by about 40% and 70%, respectively.

show abstract

Progressive Structure from Motion by Iteratively Prioritizing and Refining Match Pairs

Cited by 4 publications

References 39 publications

Optimize incremental SFM for repetitive structures and short baseline issues

Optimize incremental SFM for repetitive structures and short baseline issues

View‐graph key‐subset extraction for efficient and robust structure from motion

A New Multi-Criteria Tie Point Filtering Approach to Increase the Accuracy of UAV Photogrammetry Models

Contact Info

Product

Resources

About