Sampling Minimal Subsets with Large Spans for Robust Estimation

Tran, Quoc; Chin, Tat-Jun; Chojnacki, Wojciech; Suter, David

doi:10.1007/s11263-013-0643-y

Cited by 29 publications

(9 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The suggested optimization method relates on the gradients of the cost function rather than second derivatives, which limits its speed. Moreover, the cost function derivatives are very high in areas close to structures, so prior knowledge such as spatial continuity is necessary to produce good initializations (Tran et al (2014)).…”

Section: Guided Sampling Methods For Robust Model Fittingmentioning

confidence: 99%

Robust visual data segmentation: Sampling from distribution of model parameters

Sadri

Tennakoon

Hosseinnezhad

et al. 2018

Computer Vision and Image Understanding

View full text Add to dashboard Cite

Section: Guided Sampling Methods For Robust Model Fittingmentioning

confidence: 99%

Robust visual data segmentation: Sampling from distribution of model parameters

Sadri

Tennakoon

Hosseinnezhad

et al. 2018

Computer Vision and Image Understanding

View full text Add to dashboard Cite

“…Unfortunately, for multi-structure data, these methods usually fail to achieve one clean solution within a reasonable time budget. Note that all of Multi-GS [17], RCMSA [32,33] and Multi-GS-Oset [41]accelerate promising hypothesis generation by using information derived from residual sorting. These methods can effectively handle most multi-structure data.…”

Section: Related Workmentioning

confidence: 99%

A Robust Transform Estimator Based on Residual Analysis and Its Application on UAV Aerial Images

Cai

Leng

et al. 2018

Remote Sensing

View full text Add to dashboard Cite

Abstract:Estimating the transformation between two images from the same scene is a fundamental step for image registration, image stitching and 3D reconstruction. State-of-the-art methods are mainly based on sorted residual for generating hypotheses. This scheme has acquired encouraging results in many remote sensing applications. Unfortunately, mainstream residual based methods may fail in estimating the transform between Unmanned Aerial Vehicle (UAV) low altitude remote sensing images, due to the fact that UAV images always have repetitive patterns and severe viewpoint changes, which produce lower inlier rate and higher pseudo outlier rate than other tasks. We performed extensive experiments and found the main reason is that these methods compute feature pair similarity within a fixed window, making them sensitive to the size of residual window. To solve this problem, three schemes that based on the distribution of residuals are proposed, which are called Relational Window (RW), Sliding Window (SW), Reverse Residual Order (RRO), respectively. Specially, RW employs a relaxation residual window size to evaluate the highest similarity within a relaxation model length. SW fixes the number of overlap models while varying the length of window size. RRO takes the permutation of residual values into consideration to measure similarity, not only including the number of overlap structures, but also giving penalty to reverse number within the overlap structures. Experimental results conducted on our own built UAV high resolution remote sensing images show that the proposed three strategies all outperform traditional methods in the presence of severe perspective distortion due to viewpoint change.

show abstract

“…Owing to the fact that drawing an all-inlier minimal random sample is insufficient to ensure a proper model hypothesis, a random sampling strategy with constraints and guidance can be adopted to accelerate and strengthen the RANSAC algorithm. In [53], a novel sampling strategy that aimed to draw allinlier minimal samples with large spans was proposed, and a theoretical reasoning was presented. It was found in [54] that the actual iterative number was significantly higher than the theoretically predicted value, which was caused by the incorrect assumption that a model computed from an uncontaminated minimal sample is consistent with all the real noisy inliers.…”

Section: B Unified Ransacmentioning

confidence: 99%

“…The truncated quadratic cost function in the M-estimator SAC (MSAC) [52] replaces the top-hat type of RANSAC. In the minimal subset sampling stage, a prior sampling constraint is incorporated to prevent the minimal subset from containing data points that are too close, according to the principle in [53] that a minimal subset with a large spatial extent is desirable. A model refinement step, namely, inner RANSAC with an iteration method in locally optimized RANSAC [54], is inserted into the algorithm whenever a new best model so far is found.…”

Section: B Unified Ransacmentioning

confidence: 99%

“…The use of the cost function in MSAC enhances the tolerance to the choice of the inlier threshold and makes it possible to select a suitable threshold for a diverse set of data [52]. A sampling strategy with a prior sampling constraint reduces the necessary number of iterations [53]. The additional local optimization step strengthens the precision, robustness, and stability of the algorithm [54].…”

Section: B Unified Ransacmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Subpixel Phase Correlation Method Using Singular Value Decomposition and Unified Random Sample Consensus

Tong

et al. 2015

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Subpixel translation estimation using phase correlation is a fundamental task for numerous applications in the remote sensing community. The major drawback of the existing subpixel phase correlation methods lies in their sensitivity to corruption, including aliasing and noise, as well as the poor performance in the case of practical remote sensing data. This paper presents a novel subpixel phase correlation method using singular value decomposition (SVD) and the unified random sample consensus (RANSAC) algorithm. In the proposed method, SVD theoretically converts the translation estimation problem to one dimensions for simplicity and efficiency, and the unified RANSAC algorithm acts as a robust estimator for the line fitting, in this case for the high accuracy, stability, and robustness. The proposed method integrates the advantages of Hoge's method and the RANSAC algorithm and avoids the corresponding shortfalls of the original phase correlation method based only on SVD. A pixel-to-pixel dense matching scheme on the basis of the proposed method is also developed for practical image registration. Experiments with both simulated and real data were carried out to test the proposed method. In the simulated case, the comparative results estimated from the generated synthetic image pairs indicate that the proposed method outperforms the other existing methods in the presence of both aliasing and noise, in both accuracy and robustness. Moreover, the pixel locking effect that commonly occurs in subpixel matching was also investigated. The degree of pixel locking effect was found to be significantly weakened by the proposed method, as compared with the original Hoge's method. In the real data case, experiments using different bands of ZY-3 multispectral sensor-corrected images demonstrate the promising performance and feasibility of the proposed method, which is able to identify seams of the image stitching between sub-charge-coupled device units.Index Terms-Aliasing and noise, singular value decomposition (SVD), subpixel phase correlation, unified random sample consensus.

show abstract

Sampling Minimal Subsets with Large Spans for Robust Estimation

Cited by 29 publications

References 29 publications

Robust visual data segmentation: Sampling from distribution of model parameters

Robust visual data segmentation: Sampling from distribution of model parameters

A Robust Transform Estimator Based on Residual Analysis and Its Application on UAV Aerial Images

A Novel Subpixel Phase Correlation Method Using Singular Value Decomposition and Unified Random Sample Consensus

Contact Info

Product

Resources

About