Temporal Posture Estimation of Nonrigid Objects Lacking Sufficient Features Based on the Automatically Generated Stick and Ellipse Model

摘要

We propose a method for tracking nonrigid objects using an object model automatically generated from a set of sample images. Our model consists of multiple sticks and ellipses that represent the skeleton and the areas of an object, respectively. In previous methods, it is difficult to estimate the entire area and posture of a nonrigid object, which lacks sufficient characteristic features (e.g., texture patterns and shapes), because the previous methods have not dealt with the extraction of appearance features for any object from a 2D image of the object. With the proposed model, on the other hand, our method is effective because (1) each component of the model can fit each rigid part of a nonrigid object and (2) the reliability of each component is evaluated. In order to confirm the effectiveness of the proposed method, we conducted several experiments with goldfish and human subjects. The tracking system automatically generated a model of the target; it could then track multiple targets even when they were partially occluded.