Abstract

We describe an efficient approach to construct shape mod- els composed of contour parts with partially-supervised learning. The proposed approach can easily transfer parts structure to different ob ject classes as long as they have similar shape. The spatial layout between parts is described by a non-parametric density, which is more flexible and easier to learn than commonly used Gaussian or other parametric distributions. We express ob ject detection as state estimation inference executed using a novel Particle Filters (PF) framework with static ob- servations, which is quite different from previous PF methods. Although the underlying graph structure of our model is given by a fully connected graph, the proposed PF algorithm efficiently linearizes it by exploring the conditional dependencies of the nodes representing contour parts. Ex- perimental results demonstrate that the proposed approach can not only yield very good detection results but also accurately locates contours of target ob jects in cluttered images.