Title | ||
---|---|---|
Combining An Active Shape And Motion Models For Object Segmentation In Image Sequences |
Abstract | ||
---|---|---|
Obtaining the segmentation of an object in a sequence of images is usually achieved using a tracking methodology. However, in some applications, the whole sequence is available beforehand. This means that the segmentations can be determined simultaneously for all the frames in the sequence and taking into account the motion of the object. This paper proposes a new framework to incorporate motion information in the segmentation of image sequences using an active shape model (ASM). The motion of the object is modeled using a vector field, which is learned and refined online as the segmentation algorithm proceeds. The vector field is determined from the trajectories described by ASM points throughout the sequence. The vector field, in turn, influences the estimation of the ASM parameters by acting as a regularizer, ensuring that the segmentations are in agreement with the expected motion. The results show that coupling these models during the segmentation leads to an increase in performance, in particular by guarantee more consistent segmentations and by avoid gross errors in more challenging frames. |
Year | Venue | Keywords |
---|---|---|
2018 | 2018 25TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | Segmentation, Active Shape Model, Motion Model, Vector Field |
Field | DocType | ISSN |
Computer vision,Active shape model,Coupling,Pattern recognition,Vector field,Segmentation,Computer science,Image segmentation,Artificial intelligence,Trajectory | Conference | 1522-4880 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Carlos Santiago | 1 | 17 | 5.71 |
Jacinto C. Nascimento | 2 | 396 | 40.94 |
Jorge S. Marques | 3 | 535 | 67.78 |