Name
Abstract | ||
|---|---|---|
We propose a human object inpainting scheme that divides the process into three steps: 1) human posture synthesis; 2) graphical model construction; and 3) posture sequence estimation. Human posture synthesis is used to enrich the number of postures in the database, after which all the postures are used to build a graphical model that can estimate the motion tendency of an object. We also introduce two constraints to confine the motion continuity property. The first constraint limits the maximum search distance if a trajectory in the graphical model is discontinuous, and the second confines the search direction in order to maintain the tendency of an object's motion. We perform both forward and backward predictions to derive local optimal solutions. Then, to compute an overall best solution, we apply the Markov random field model and take the potential trajectory with the maximum total probability as the final result. The proposed posture sequence estimation model can help identify a set of suitable postures from the posture database to restore damaged/missing postures. It can also make a reconstructed motion sequence look continuous. |
Year | DOI | Venue |
|---|---|---|
2011 | 10.1109/TIP.2011.2158228 | IEEE Transactions on Image Processing |
Keywords | Field | DocType |
proposed posture sequence estimation,missing posture,posture database,markov random field model,motion continuity property,human object inpainting,posture sequence estimation,graphical model,graphical model construction,suitable posture,human posture synthesis,manifold learning-based posture sequence,dimensionality reduction,manifolds,estimation,vision,databases,pose estimation,trajectory,manifold learning,shape,markov processes,graphical models,nonlinear dimensionality reduction,video,motion estimation | Computer vision,Markov process,Pattern recognition,Markov random field,Inpainting,Pose,Artificial intelligence,Motion estimation,Graphical model,Nonlinear dimensionality reduction,Mathematics,Trajectory | Journal |
Volume | Issue | ISSN |
20 | 11 | 1941-0042 |
Citations | PageRank | References |
6 | 0.47 | 23 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Chih-Hung Ling | 1 | 23 | 2.23 |
| Yu-Ming Liang | 2 | 95 | 10.83 |
| Chia-Wen Lin | 3 | 1639 | 120.23 |
| Yong-Sheng Chen | 4 | 314 | 30.12 |
| h y m liao | 5 | 2353 | 198.72 |