ilana
Uploaded by
16 SLIDES
371 VUES
160LIKES

Robust and Fast Collaborative Tracking with Two Stage Sparse Optimization

DESCRIPTION

Robust and Fast Collaborative Tracking with Two Stage Sparse Optimization. Authors: Baiyang Liu, Lin Yang, Junzhou Huang , Peter Meer, Leiguang Gong and Casimir Kulikowski. Outline. Problem of Tracking State of the art algorithms The proposed algorithm Experiment result. The problem.

1 / 16

Télécharger la présentation

Robust and Fast Collaborative Tracking with Two Stage Sparse Optimization

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Robust and Fast Collaborative Tracking with Two Stage Sparse Optimization Authors: Baiyang Liu, Lin Yang, Junzhou Huang, Peter Meer, Leiguang Gong and CasimirKulikowski

  2. Outline • Problem of Tracking • State of the art algorithms • The proposed algorithm • Experiment result

  3. The problem • Tracking: estimate the state of moving target in the observed video sequences • Challenges • Illumination, pose of target changes • Object occlusion, complex background clutters • Landmark ambiguity • Two categories of tracking • Discriminative • Generative

  4. Outline • Problem of Tracking • State of the art algorithms • The proposed algorithm • Experiment result

  5. Related work • Multiple Instance Learning boosting method(MIL Boosting) put all samples into bags and labeled them with bag labels. • Incremental Visual Tracking(IVT) the target is represented as a single online learned appearance model • L1 norm optimization a linear combination of the learned template set composed of both target templates and the trivial template.

  6. Basic sparse representation • Sparse representation • Basis pursuit • Disadvantages • Computationally expensive • Temporal and spatial features are not considered • The background pixels do not lie on the linear template subspace

  7. Outline • Problem of Tracking • State of the art algorithms • The proposed algorithm • Experiment result

  8. Problem Analysis • Given ,Let , , • Feature space can be decreased to K0 dimension • Two stage greedy method

  9. Stage I: Feature selection • Loss function Given , L= as labels, • To minimize the loss function, solve the sparse problem below • Feature selection matrix

  10. Stage II: Sparse reconstruction • Problem after stage I • Simplify the aim function above as

  11. Bayesian tracking framework • Let represents the affine paramters • Estimation of the state probability prediction: updating: • Transition model: ~ • likelihood where

  12. Review of the algorithm

  13. Outline • Problem of Tracking • State of the art algorithms • The proposed algorithm • Experiment result

  14. Visual results

  15. Quantitative results

More Related