Global optical flow estimation methods contain a regularization parameter (or prior and likelihood hyper‐parameters if we consider the statistical point of view) which control the tradeoff between the different const...
Global optical flow estimation methods contain a regularization parameter (or prior and likelihood hyper‐parameters if we consider the statistical point of view) which control the tradeoff between the different constraints on the optical flow field. Although experiments (see e.g. Ng et al. [Ng and Solo(1997)]) indicate the importance of the optimal choice of the hyper‐parameters, only little attention has been focused on the optimal choice of these parameters in global motion estimation techniques in literature so far (the authors are only aware of one contribution [Ng and Solo(1997)] which attempts to estimate only the prior hyper‐parameter whereas the likelihood hyper‐parameter needs to be known). We adapt the marginalized maximum a posteriori (MMAP) estimator proposed in [Mohammad‐Djafari(1995)] to simultaneously estimating hyper‐parameters and optical flow for global motion estimation techniques. Experiments demonstrate the performance of this optimization technique and show that the choice of the regularization parameter/hyper‐parameters is an essential key‐point in order to obtain precise motion estimates.
The 2nd International Workshop on Statistical Methods in Video processing, SMVP 2004, was held in Prague, Czech Republic, as an associated workshop of ECCV 2004, the 8th European Conference on Computer Vision. A total...
详细信息
ISBN:
(数字)9783540302124
ISBN:
(纸本)9783540239895
The 2nd International Workshop on Statistical Methods in Video processing, SMVP 2004, was held in Prague, Czech Republic, as an associated workshop of ECCV 2004, the 8th European Conference on Computer Vision. A total of 30 papers were submitted to the workshop. Of these, 17 papers were accepted for presentation and included in these proceedings, following a double-blind review process. The workshop had 42 registered participants. The focus of the meeting was on recent progress in the application of - vanced statistical methods to solve computer vision tasks. The one-day scienti?c program covered areas of high interest in vision research, such as dense rec- struction of 3D scenes, multibody motion segmentation, 3D shape inference, errors-in-variables estimation, probabilistic tracking, information fusion, optical ?owcomputation,learningfornonstationaryvideodata,noveltydetectionin- namic backgrounds, background modeling, grouping using feature uncertainty, and crowd segmentation from video. We wish to thank the authors of all submitted papers for their interest in the *** external reviewers for their commitment of time and e?ort in providing valuable recommendations for each submission. We are thankful to Vaclav Hlavac, the General Chair of ECCV 2004, and to Radim Sara, for the local organization of the workshop and registration management. We hope you will ?nd these proceedings both inspiring and of high scienti?c quality.
This book constitutes the refereed proceedings of the 33rd Symposium of the German Association for Pattern Recognition, DAGM 2011, held in Frankfurt/Main, Germany, in August/September 2011. The 20 revised full papers ...
详细信息
ISBN:
(数字)9783642231230
ISBN:
(纸本)9783642231223
This book constitutes the refereed proceedings of the 33rd Symposium of the German Association for Pattern Recognition, DAGM 2011, held in Frankfurt/Main, Germany, in August/September 2011. The 20 revised full papers and 22 revised poster papers were carefully reviewed and selected from 98 submissions. The papers are organized in topical sections on object recognition, adverse vision conditions challenge, shape and matching, segmentation and early vision, robot vision, machine learning, and motion. The volume also includes the young researcher's forum, a section where a carefully jury-selected ensemble of young researchers present their Master thesis work.
暂无评论