Compressed domain global motion estimation using the Helmholtz Tradeoff Estimator

Tok, Michael; Glantz, Alexander; Arvanitidou, Marina Georgia; Krutz, Andreas; Sikora, Thomas

doi:10.1109/icip.2010.5652525

Cited by 12 publications

(8 citation statements)

References 9 publications

(16 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…clusters which contain less than 20 motion vectors would be marked as outlier clusters. The kernel bandwidth parameters used were (ℎ , ℎ ) = (8,4). Comparative studies is carried out with the following methods to validate our proposed outlier removal method using mean shift clustering: i) Gradient descent (Plain GD) [5], ii) Filter method (FLT GD) [8], iii) Cascade-of-rejectors (CAS GD) [6], iv) Tensor Voting method (TV GD) [10].…”

Section: Resultsmentioning

confidence: 99%

“…The estimation of the camera parameters can be done either in pixel domain [1]- [3] or block motion vector domain also referred to as the compressed domain [4]- [7]. GME techniques in the pixel domain minimize the prediction errors by utilizing an iterative non-linear estimation technique thereby achieving robust estimations for the camera motion parameters.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Mean shift clustering based outlier removal for global motion estimation

Okade

Biswas

2013

2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG)

View full text Add to dashboard Cite

This paper investigates a novel motion vector outlier rejection method based on using mean shift clustering on block motion vectors. The accuracy of compressed domain global motion estimation techniques is largely influenced by its ability to counter the outlier motion vectors. These outliers occur in the block motion vector field due to moving objects, noise or due to large matching errors as a result of the encoders priority on rate distortion optimization. In the present work it is shown that by using mean shift clustering on block motion vectors, those clusters which correspond to outlier motion vectors can be identified. Once detected these clusters are kept out of the global motion estimation process thereby increasing the robustness of estimated camera parameters. The proposed method is compared with existing state-of-the-art outlier removal methods using synthetic and real video sequences to establish and validate its superiority.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Mean shift clustering based outlier removal for global motion estimation

Okade

Biswas

2013

2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG)

View full text Add to dashboard Cite

show abstract

“…Notice, however, that both methods are extremely fast in comparison to the method proposed in [5]. for the uncompensated case, the block-based approach described in [4], the method described in this paper and the difference between these two methods. …”

Section: Experimental Evaluationmentioning

confidence: 90%

“…Table 1 shows the used sequences. For comparison with the method discussed in this paper, we used the algorithm proposed in [4] on motion vector fields created by encoding all sequences with a GOP structure of IPPP. .…”

Section: Experimental Evaluationmentioning

confidence: 99%

See 1 more Smart Citation

Feature-based global motion estimation using the Helmholtz principle

Tok

Glantz

Krutz

et al. 2011

2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

Global motion estimation is an important task for various video processing techniques. The estimation itself has to be robust in presence of arbitrarily moving foreground objects. For that task, two different kinds of estimation methods exist. On the one hand, pixel-based approaches deliver more precise results and work more robust on video sequences with foreground objects. On the other hand, when working on encoded video streams, block-based methods can be used for a much faster but often less precise estimation. We propose a two step estimation method based on the determination and tracking of feature points of video frames and robust motion model estimation using the Helmholtz principle. Therefore, good trackable features are detected and tracked in video sequences. Subsequently, a perspective motion model is derived from the resulting correspondencies by removing feature pairs not belonging to global motion.

show abstract