Global motion estimation under translation-zoom ambiguity

Qian, Chun Hua; Bajić, Ivan V.

doi:10.1109/pacrim.2013.6625447

Cited by 4 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chen and Bajic [1] proposed an outlier rejection filter that explicitly filters motion vectors by checking their similarity in a pre-defined window. Chen and Bajic [2], and Qian and Bajic [3] proposed a joint global motion estimation, which iteratively updates the inlier model by segmenting outliers out. Although these methods have achieved great progress in dealing with the independent motions, they are very likely to over-segment objects due to the motion bias introduced by camera motion [2].…”

Section: Using Optical Flowmentioning

confidence: 99%

See 1 more Smart Citation

A General Inlier Estimation for Moving Camera Motion Segmentation

Liang

Zhang

Matsuyama

2015

IPSJ Transactions on Computer Vision and Applications

View full text Add to dashboard Cite

In moving camera videos, motion segmentation is often achieved by determining the motion coherence of each moving object. However, it is a nontrivial task on optical flow due to two problems: 1) Optical flow of the camera motions in 3D world consists of three primary 2D motion flows: translation, rotation, and radial flow. Their coherence analysis is done by a variety of models, and further requires plenty of priors in existing frameworks; 2) A moving camera introduces 3D motion, the depth discontinuities cause the motion discontinuities that severely break down the coherence. Meanwhile, the mixture of the camera motion and moving objects' motions make it difficult to clearly identify foreground and background. In this work, our solution is to transform the optical flow into a potential space where the coherence of the background flow field is easily modeled by a low order polynomial. To this end, we first amend the Helmholts-Hodge Decomposition by adding coherence constraints, which can transform translation, rotation, and radial flow fields to two potential surfaces 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. We present results on more than twenty videos from four benchmarks. Extensive experiments demonstrate better performance in dealing with challenging scenes with complex backgrounds. Our method improves the segmentation accuracy of state-of-the-arts by 10%∼30%.

show abstract

Section: Using Optical Flowmentioning

confidence: 99%

“…As optical flow is a dense projection of motion from 3D world to 2D image plane, it can be directly used for clustering or to compensate for the camera motion. Therefore, the pixel-wise model is often used for segmentation [1], [2], [3], [4].…”

Section: Introductionmentioning

confidence: 99%

A General Inlier Estimation for Moving Camera Motion Segmentation

Liang

Zhang

Matsuyama

2015

IPSJ Transactions on Computer Vision and Applications

View full text Add to dashboard Cite

show abstract

“…Chen and Bajic [1] proposed an outlier rejection filter that explicitly filters motion vectors by checking their similarity in a pre-defined window. Chen and Bajic [2], and Qian and Bajic [3] proposed a joint global motion estimation, which iteratively update the inlier model by segmenting outliers out. Although these methods have achieved great progress in dealing with independent motions, they are very likely to over-segment ob- jects due to the motion bias introduced by camera motion [2].…”

Section: Introductionmentioning

confidence: 99%

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

Prior-Free Dependent Motion Segmentation Using Helmholtz-Hodge Decomposition Based Object-Motion Oriented Map

Zhang

Liu

2017

J. Comput. Sci. Technol.

View full text Add to dashboard Cite

Global motion estimation under translation-zoom ambiguity

Cited by 4 publications

References 9 publications

A General Inlier Estimation for Moving Camera Motion Segmentation

A General Inlier Estimation for Moving Camera Motion Segmentation

Inlier Estimation for Moving Camera Motion Segmentation

Prior-Free Dependent Motion Segmentation Using Helmholtz-Hodge Decomposition Based Object-Motion Oriented Map

Contact Info

Product

Resources

About