Motion Vector Outlier Rejection Cascade for Global Motion Estimation

Chen, Yue-Meng; Bajić, Ivan V.

doi:10.1109/lsp.2009.2036879

Cited by 30 publications

(8 citation statements)

References 13 publications

(18 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For block i, a similarity value i S is calculated based on the cosine of the similarity between input motion vector and the one in the smoothed motion vector field, as follows: The similarity of zero motion vectors is set to 0. In this research, 30% of motion vectors were found to be outliers, similarly to the work in [4]. Fig.…”

Section: Motion Vector Outlier Removalsupporting

confidence: 80%

“…The same four sets of global motion parameters as in [2,4], which are shown in Table 1, are used. The synthetic motion vector fields of these four motion models are illustrated in Fig.…”

Section: Resultsmentioning

confidence: 99%

“…Four popular motion models are: translational (2 parameters), geometric (4 parameters), affine (6 parameters) and perspective (8 parameters). GME can be performed in either the pixel domain [1] or the compressed domain [2][3][4] by solving a set of linear equations with the help of feature points correspondence or a motion vector field. An evaluation of pixel based and motion vector based GME methods can be found in [5].…”

Section: Introductionmentioning

confidence: 99%

“…Therefore, it generates poor results. In [4], a cascade method, which can take advantage of both magnitude and phase information, is presented. In this method, soft-decision thresholding is used instead of harddecision thresholding as in [3].…”

Section: Introductionmentioning

confidence: 99%

“…In this method, soft-decision thresholding is used instead of harddecision thresholding as in [3]. This method is fast and accurate, as shown by the experimental results cited in [4]. However, in this method, only eight neighbors of a vector are considered to determine whether or not a particular vector is an outlier.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Efficient motion vector outlier removal for global motion estimation

Dinh

Lee

2011

2011 IEEE International Conference on Multimedia and Expo

View full text Add to dashboard Cite

Because motion vector based global motion estimation methods have much lower complexity than pixel based ones, they are widely used in the compressed domain to estimate the camera motion in video sequences. However, the accuracy of these motion vector based methods largely depends on the quality of the input motion vector field. In real applications, many outlier motion vectors are present because of noise or foreground objects. In this paper, a novel tensor voting based motion vector outlier removal method is proposed to improve the quality of the input motion vector field. First, motion vectors are encoded by second order tensors. A 2-D voting process is then used to smooth the motion vector field. Finally, the smoothed motion vector field is compared to the input one to detect outliers. The experimental results on synthetic and real data show the effectiveness of the proposed method.

show abstract

Section: Motion Vector Outlier Removalsupporting

confidence: 80%

“…The same four sets of global motion parameters as in [2,4], which are shown in Table 1, are used. The synthetic motion vector fields of these four motion models are illustrated in Fig.…”

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Efficient motion vector outlier removal for global motion estimation

Dinh

Lee

2011

2011 IEEE International Conference on Multimedia and Expo

View full text Add to dashboard Cite

show abstract

Global Motion Estimation Using a New Motion Vector Outlier Rejection Algorithm

Yıldırım¹,

Ilgin

2013

Nostradamus 2013: Prediction, Modeling and Analysis of Complex Systems

View full text Add to dashboard Cite

Inlier Estimation for Moving Camera Motion Segmentation

Liang

Zhang

Matsuyama

2015

Computer Vision -- ACCV 2014

View full text Add to dashboard Cite

Abstract. In moving camera videos, motion segmentation is often performed on the optical flow. However, there exist two challenges: 1) Camera motions lead to three primary flows in optical flow: translation, rotation, and radial flow. They are not all solved in existing frameworks under Cartesian coordinate system; 2) A moving camera introduces 3D motion, the depth discontinuities cause the motion discontinuities that severely confuse the motion segmentation. Meanwhile, the mixture of the camera motion and moving objects' motions make indistinctness between foreground and background. In this work, our solution is to find a low order polynomial to model the background flow field due to its coherence. To this end, we first amend the Helmholts-Hodge Decomposition by adding coherence constraints, which can handle translation, rotation, and radial flow fields under a unified framework. Secondly, we introduce an Incoherence Map and a progressive Quad-Tree partition to reject moving objects and motion discontinuities. Finally, the low order polynomial is achieved from the rest flow samples on two potentials in HHD. We present results on more than twenty videos from four benchmarks. Extensive experiments demonstrate a better performance in dealing with challenging scenes with complex backgrounds. Our method improves the segmentation accuracy of state-of-the-art by 10% ∼ 30%.

show abstract

Motion Vector Outlier Rejection Cascade for Global Motion Estimation

Cited by 30 publications

References 13 publications

Efficient motion vector outlier removal for global motion estimation

Efficient motion vector outlier removal for global motion estimation

Global Motion Estimation Using a New Motion Vector Outlier Rejection Algorithm

Inlier Estimation for Moving Camera Motion Segmentation

Contact Info

Product

Resources

About