Silhouette Extraction with Random Pattern Backgrounds for the Volume Intersection Method

Abstract

In this paper, we present a novel approach for extracting silhouettes by using a particular pattern that we call the random pattern. The volume intersection method reconstructs the shapes of 3D objects from their silhouettes obtained with multiple cameras. With the method, if some parts of the silhouettes are missed, the corresponding parts of the reconstructed shapes are also missed. When colors of the objects and the backgrounds are similar, many parts of the silhouettes are missed. We adopt random pattern backgrounds to extract correct silhouettes. The random pattern has many small regions with randomly-selected colors. By using the random pattern backgrounds, we can keep the rate of missing parts below a specified percentage, even for objects of unknown color. To refine the silhouettes, we detect and fill in the missing parts by integrating multiple images. From the images captured by multiple cameras used to observe the object, the object's colors can be estimated. The missing parts can be detected by comparing the object's color with its corresponding background's color. In our experiments, we confirmed that this method effectively extracts silhouettes and reconstructs 3D shapes.