Spatio-temporal prior shape constraint for level set segmentation
EMMCVPR'05 Proceedings of the 5th international conference on Energy Minimization Methods in Computer Vision and Pattern Recognition
| Hi-index | 0.00 |
We present a new fast method of modeling 3-D objects of arbitrary topology. The Level Set Methods have been used by many researchers to recover 3-D shapes of arbitrary topology. However, those methods are computationally inefficient. To reduce the computational cost, a new method named FNB (Fast Narrow Band Method) is proposed. FNB is based on the Narrow Band Method (NB) which is the well-known fast method of the Level Set Method. The main idea is to exploit the combinative use of the narrow band and the approximate distance from the front. The method has been applied in several experiments using range data and we find that our method is over 50 times faster than NB.