Graph Laplacian Regularization for Robust Optical Flow Estimation

Young, Sean I.; Naman, Aous Thabit; Taubman, David

doi:10.1109/tip.2019.2945653

Cited by 8 publications

(5 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The total outlier score for each data point was obtained by equation ( 12): In equation (12), gn is the number of graphs G. The ranking of the statistical outlier total score by equation ( 11), the vector with the top k% of occurrence frequency or Score(s) greater than a threshold, is thresholded, and the feature points with probability values higher than a certain threshold are marked as outliers; thus, these outliers can be eliminated, and a valid optical flow estimate can be obtained. The B-SNG pseudocode proposed in this study is presented in table 2.…”

Section: Outlier Probabilitymentioning

confidence: 99%

“…Table 3 demonstrates that in the outlier elimination algorithm comparison experiments, the dataset Odataset includes three motion pattern datasets (Normal amplitude motion scene dataset n_datas, small amplitude motion scene dataset s_datas, and large amplitude motion scene dataset l_datas), each of which consists of the inlier optical flow values (u gt , v gt ) and the outlier optical flow values (u ft , v ft ). [34] bamboo_2(frame_0001 ∼ 0010) [34] temple_2.1(frame_0001 ∼ 0010) [34] temple_2.2(frame_0011 ∼ 0021) [34] 15-50 pixels s_datas 30 group 100 alley_1(frame_0001 ∼ 0016) [34] FlyingChairs (6,7,11,12,16,33,40,78,82 104) [35] Middlebury(grov(2 ∼ 3)、urban(2 ∼ 3)、venus) [36] >15 pixels l_datas 40 group 100 ambush_2.1(frame_0001 ∼ 0010) [34] ambush_2.2(frame_0010 ∼ 0021) [34] market_5.1(frame_0001 ∼ 0010) [34] market_5.2(frame_0011 ∼ 0021) [34] <50 pixels…”

Section: Datasetsmentioning

confidence: 99%

“…These light displacement group values seriously affect the analysis results and need to be eliminated. Currently, researchers have widely used methods based on threshold [7][8][9], local area consistency [10,11], and statistics [12] to eliminate outliers in the optical flow values.…”

Section: Introductionmentioning

confidence: 99%

“…The method based on a statistical approach is to model the optical flow field using Gaussian distribution, Laplace distribution, etc [12], and to use this model to detect outliers and eliminate them.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Sparse optical flow outliers elimination method based on Borda stochastic neighborhood graph

Wang,

Li,

Wang

et al. 2024

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

During the tracking of moving targets in dynamic scenes, efficiently handling outliers in the optical flow and maintaining robustness across various motion amplitudes represents a critical challenge. So far, studies have used thresholding and local consistency based approaches to deal with optical outliers. However, there is subjectivity through expert-defined thresholds or delineated regions, and therefore these methods do not perform consistently enough under different target motion amplitudes. Other studies have focused on complex statistical-mathematical modelling which, although theoretically valid, requires significant computational resources. Aiming at the above problems this paper proposes a new method to calculate the optical outliers by using stochastic neighborhood graph combined with the Borda counting method, which reduces the computation amount on the basis of objectively eliminating the outliers. Sparse optical flow values are used as the overall population and the outlier and inlier sparse optical flow values are used as samples. Analyze the dissimilarity between sparse optical flow data points, obtaining the dissimilarity matrix, introducing the Gaussian function to smooth and reduce the dimensionality of the dissimilarity matrix, and then normalizing the smoothing matrix to generate the binding matrix, where the probability sum of each node to other nodes in the matrix is equal to 1. Stochastic neighborhood graphs are then generated based on a binding matrix to obtain the outlier probabilities of data points in different neighborhood graphs, and outlier samples are obtained based on the probability. To avoid the subjectivity of the expert thresholds, the outlier probabilities are weighted and ranked to calculate the data point Borda scores to obtain accurate optical outliers. The experimental results show that the method in this paper is robust to different amplitude motions and real scenarios, and the accuracy, precision and recall of outliers elimination are better than the current mainstream algorithms.

show abstract

Section: Outlier Probabilitymentioning

confidence: 99%

Section: Datasetsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Sparse optical flow outliers elimination method based on Borda stochastic neighborhood graph

Wang,

Li,

Wang

et al. 2024

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…The use of the Welsch loss function has been shown previously to be highly effective in limiting the influence of outliers and occlusions on a flow field in the domain of optical flow [21]. In the domain of multiview disparity estimation with potentially large occluded areas, this turns out to be particularly valuable.…”

Section: Data Termmentioning

confidence: 99%

Welsch Based Multiview Disparity Estimation

Gray

Naman

Taubman

2021

2021 IEEE International Conference on Image Processing (ICIP)

Self Cite

View full text Add to dashboard Cite

In this work, we explore disparity estimation from a high number of views. We experimentally identify occlusions as a key challenge for disparity estimation for applications with high numbers of views. In particular, occlusions can actually result in a degradation in accuracy as more views are added to a dataset. We propose the use of a Welsch loss function for the data term in a global variational framework for disparity estimation. We also propose a disciplined warping strategy and a progressive inclusion of views strategy that can reduce the need for coarse to fine strategies that discard high spatial frequency components from the early iterations. Experimental results demonstrate that the proposed approach produces superior and/or more robust estimates than other conventional variational approaches.

show abstract