Title | ||
---|---|---|
Neural Network Based Foreground Segmentation with an Application to Multi-Sensor 3D Modeling |
Abstract | ||
---|---|---|
This paper presents a technique for foreground/background segmentation using either color images or a combination of color and range images. In the case of images captured from a single 2D camera, a hybrid experience-based foreground segmentation technique is developed using a neural network and graph cut paradigm. This gives an advantage over methods that are based on color distribution or gradient information if the foreground/background color distributions are not well separated or the boundary is not clear. The system can segment images more effectively than the latest technology of graph cut, even if the foreground is very similar to the background. It also shows how to use the method for multi-sensor based 3D modeling by segmenting the foreground of each viewpoint in order to generate 3D models. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1109/MFI.2006.265586 | MFI |
Keywords | Field | DocType |
gradient methods,graph theory,image colour analysis,image fusion,image segmentation,neural nets,background segmentation,color images,foreground segmentation,gradient information,graph cut paradigm,multisensor 3d modeling,neural network,interactive image segmentation,machine learning,multi-sensor 3d modeling | Cut,Market segmentation,Image fusion,Computer science,Image segmentation,Artificial intelligence,Artificial neural network,Graph theory,Computer vision,Pattern recognition,Segmentation,3D modeling,Machine learning | Conference |
ISBN | Citations | PageRank |
1-4244-0567-X | 3 | 0.40 |
References | Authors | |
14 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Miti Ruchanurucks | 1 | 42 | 5.40 |
Koichi Ogawara | 2 | 163 | 20.41 |
Katsushi Ikeuchi | 3 | 4651 | 881.49 |