![Constraints (Scribbles and Trimap)
Trimap Interface :
Bayesian Matting (Chuang et al CVPR 01)
Poisson Matting (Sun et al SIGGRAPH 04)
Random walk (Grady et al 05)
Etc..
Scribbles Interface :
Wang&Cohen ICCV 05
Closed Form Matting TPAMI 08
Nonlocal Matting CVPR 11
Etc..
𝛼 = 1
𝛼 = 1
𝛼 = 0
𝛼 = 0
𝛼 ∈ [1,0]](https://image.slidesharecdn.com/presentation-160803073850/85/Video-Object-Extraction-Using-Feature-Matching-Based-on-Nonlocal-Matting-4-320.jpg)
Video Object Extraction Using Feature Matching Based on Nonlocal Matting
- 1. Video Object Extraction Using Feature Matching Based on Nonlocal Matting Meidya Koeshardianto, Eko Mulyanto and Mochamad Hariadi | ITS Surabaya, Indonesia
- 2. What is video object extraction and how to make it easy implementation? Question :
- 3. Matting Equations • Video object extraction is used for extracting foreground and background object from still image or video sequences. 𝐼 = 𝛼𝐹 + 1 − 𝛼 𝐵
- 4. Constraints (Scribbles and Trimap) Trimap Interface : Bayesian Matting (Chuang et al CVPR 01) Poisson Matting (Sun et al SIGGRAPH 04) Random walk (Grady et al 05) Etc.. Scribbles Interface : Wang&Cohen ICCV 05 Closed Form Matting TPAMI 08 Nonlocal Matting CVPR 11 Etc.. 𝛼 = 1 𝛼 = 1 𝛼 = 0 𝛼 = 0 𝛼 ∈ [1,0]
- 5. Problems 1. Every frames need constraints to determine Foreground and Background 2. Accurate object extraction on each frames. • Automatic constraints (stroke/scribbles) • Feature matching • Nonlocal matting for Video Object Extracting SIFT Algorithm is used Laplacian Transform Video / image sequence Image Template Nonlocal MattingPoint Matching Alpha Matte Point Extraction
- 6. Procedure Key Point Extraction Step 1 Feature Matching Step 2 Laplacian Transform (Nonlocal Matting) Step 3
- 7. Why nonlocal matting is employed? Intepretation Laplacian as a graph 𝐺 = 𝑉, 𝐸 where 𝐴 is weight of edge 𝐸(𝑖, 𝑗) With derivation of 𝑫𝜶 = 𝑨𝜶 then 𝑫 − 𝑨 𝜶 ≈ 𝟎 or 𝜶 𝑻 𝑳𝜶 ≈ 𝟎 where 𝑳 = 𝑫 − 𝑨 𝑻 (𝑫 − 𝑨) The quadratic form 𝜶 𝑻 𝑳𝜶 Measure of smoothness along the edge of 𝐺
- 8. Why nonlocal matting is employed? If there is a subset of pixels that exactly cluster in the graph implied by Laplacian 𝐿 then the value of the objective function 𝑞(𝛼) is minimized if the rest of the pixels in the cluster are labeled
- 9. Automatic Scribbles - SIFT Key Detection Keypoint Descriptor
- 10. Automatic Scribbles - SIFT Feature Matching 𝜃 = 0,2 – 0,4 𝜃 = 0,5 𝜃 = 0,6 𝜃 = 0,7 𝜃 = 0,8 𝜃 = 0,9
- 11. Image template for automatic video object extraction Answer :
- 12. Experiments – Samples Video
- 13. Conclusion and Road a Head • Feature matching could be used as scribbles or stoke for object extraction, nonlocal matting method. • According from our sample video, it show that objects can be extracted by most satisfactory parameter using 𝜃 = 0,05 • Future work include investigating updated or replaced image template periodically. So that, the image template feature will be still recognized on the frame.
Editor's Notes
- #3: This is the question that your experiment answers
- #7: List all of the steps used in completing your experiment. Remember to number your steps. Include photos of your experiment.
- #8: Summarize your research in three to five points.
- #12: Write hypothesis before you begin the experiment. This should be your best educated guess based on your research.