Hierarchical motion consistency constraint for efficient geometrical verification in UAV stereo image matching

Jiang, San; Jiang, Wanshou

doi:10.1016/j.isprsjprs.2018.06.009

Cited by 21 publications

(16 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Image matching is one of the fundamental technologies in photogrammetry and computer vision, which is widely used in image registration, image stitching, 3D reconstruction, etc. [67][68][69]. It is a long-standing and challenging task, especially for UAV images, due to the strong geometric deformations (e.g.…”

Section: Low-altitude Uav Image Matchingmentioning

confidence: 99%

Mini-Unmanned Aerial Vehicle-Based Remote Sensing: Techniques, applications, and prospects

Xiang

Xia

Zhang

2019

IEEE Geosci. Remote Sens. Mag.

148

View full text Add to dashboard Cite

The past few decades have witnessed the great progress of unmanned aircraft vehicles (UAVs) in civilian fields, especially in photogrammetry and remote sensing. In contrast with the platforms of manned aircraft and satellite, the UAV platform holds many promising characteristics: flexibility, efficiency, highspatial/temporal resolution, low cost, easy operation, etc., which make it an effective complement to other remote-sensing platforms and a cost-effective means for remote sensing. Considering the popularity and expansion of UAV-based remote sensing in recent years, this paper provides a systematic survey on the recent advances and future prospectives of UAVs in the remote-sensing community. Specifically, the main challenges and key technologies of remote-sensing data processing based on UAVs are discussed and summarized firstly. Then, we provide an overview of the widespread applications of UAVs in remote sensing. Finally, some prospects for future work are discussed. We hope this paper will provide remotesensing researchers an overall picture of recent UAV-based remote sensing developments and help guide the further research on this topic.

show abstract

Section: Low-altitude Uav Image Matchingmentioning

confidence: 99%

Mini-Unmanned Aerial Vehicle-Based Remote Sensing: Techniques, applications, and prospects

Xiang

Xia

Zhang

2019

IEEE Geosci. Remote Sens. Mag.

148

View full text Add to dashboard Cite

show abstract

“…Thus, the efficiency of the GC-RANSAC is very sensitive to the number of initial matches. Second, compared with the results documented in Jiang et al [31], the speedup ratios between the HMCC-RANSAC and the LO-RANSAC is not obvious due to the influence of match pair selection and the tiling strategy for feature matching. On the one hand, MST-Expansion can noticeably reduce the number of image pairs captured from varying viewing directions; on the other hand, the tiling strategy can decrease the ratio of false matches.…”

Section: Performance Evaluation Of Individual Stepsmentioning

confidence: 63%

“…For the three issues in the SfM reconstruction of oblique UAV images, namely match pair selection, feature extraction and matching, and geometrical verification, this paper summarizes the corresponding solutions based on our previous research [12,17,31] and then proposes the overall workflow to achieve an efficient SfM solution, as presented in Figure 1. The processing pipeline consists of three parts: (1) match pair selection based on the analysis of topology connection network;…”

Section: Methodsmentioning

confidence: 99%

“…For photogrammetric images, the rough geo-referencing characteristics have been exploited for outlier removal, which is based on the assumption that two images have been coarsely aligned, and the geometrical transformation of initial matches can be simplified as two-dimensional transformation [29,30]. Similarly, the same idea can also be introduced to achieve efficient geometrical verification for oblique UAV images, as reported in Jiang et al [31], where a hierarchical motion consistency constraint (HMCC) algorithm was designed to filter obvious outliers prior to the use of the RANSAC. Experimental results demonstrated their promising performance for geometrical verification of oblique UAV images.…”

Section: Introductionmentioning

confidence: 99%

“…This paper proposes an integrated SfM solution based on previous studies [12,17,31]. First, the operation for match pair selection is conducted to remove unessential image pairs.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Efficient SfM for Oblique UAV Images: From Match Pair Selection to Geometrical Verification

Jiang

2018

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Accurate orientation is required for the applications of UAV (Unmanned Aerial Vehicle) images. In this study, an integrated Structure from Motion (SfM) solution is proposed, which aims to address three issues to ensure the efficient and reliable orientation of oblique UAV images, including match pair selection for large-volume images with large overlap degree, reliable feature matching of images captured from varying directions, and efficient geometrical verification of initial matches. By using four datasets captured with different oblique imaging systems, the proposed SfM solution is comprehensively compared and analyzed. The results demonstrate that linear computational costs can be achieved in feature extraction and matching; although high decrease ratios occur in image pairs, reliable orientation results are still obtained from both the relative and absolute bundle adjustment (BA) tests when compared with other software packages. For the orientation of oblique UAV images, the proposed method can be an efficient and reliable solution.

show abstract

An automatic image matching algorithm based on thin plate splines

et al. 2020

View full text Add to dashboard Cite

Hierarchical motion consistency constraint for efficient geometrical verification in UAV stereo image matching

Cited by 21 publications

References 27 publications

Mini-Unmanned Aerial Vehicle-Based Remote Sensing: Techniques, applications, and prospects

Mini-Unmanned Aerial Vehicle-Based Remote Sensing: Techniques, applications, and prospects

Efficient SfM for Oblique UAV Images: From Match Pair Selection to Geometrical Verification

An automatic image matching algorithm based on thin plate splines

Contact Info

Product

Resources

About