sGNG: Online Surface Reconstruction Based on Growing Neural Gas
نویسندگان
چکیده
In this report we present an online algorithm to reconstruct a triangulated surface from an unorganized point cloud. Our algorithm called sgng, which is based on an artificial neural network, does not make any assumptions about the technique used to acquire the input points. Furthermore, sgng can update a previously reconstructed surface incrementally when previous input points are moved or deleted or new input points are added. Even arbitrary topology can be learnt without relying on predefined heuristics. In contrast to existing similar algorithms, sgng is able to create all triangles while learning without post-processing. All learning decisions are solely based on a local neighbourhood to keep overall complexity low. We demonstrate that the new algorithm efficiently and robustly reconstructs d surfaces from even huge, arbitrary unorganized point clouds.
منابع مشابه
A supervised growing neural gas algorithm for cluster analysis
In this paper, a prototype-based supervised clustering algorithm is proposed. The proposed algorithm, called the Supervised Growing Neural Gas algorithm (SGNG), incorporates several techniques from some unsupervised GNG algorithms such as the adaptive learning rates and the cluster repulsion mechanisms of the Robust Growing Neural Gas algorithm, and the Type Two Learning Vector Quantization (LV...
متن کاملA Comparison between the Performance of Feed Forward Neural Networks and the Supervised Growing Neural Gas Algorithm
AI 057 Abstract The Supervised Growing Neural Gas algorithm (SGNG) provides an interesting alternative to standard multilayer perceptrons (MLP). A comparison is drawn between the performance of SGNG and MLP in the domain of function mapping. A further eld of interest is classiication power, which has been investigated with real data taken by PS197 at CERN. The characteristics of the two network...
متن کاملScatter-partitioning Rbf Network for Function Regression and Image Segmentation: Preliminary Results
Scatter-partitioning Radial Basis Function (RBF) networks increase their number of degrees of freedom with the complexity of an input-output mapping to be estimated on the basis of a supervised training data set. Due to its superior expressive power a scatter-partitioning Gaussian RBF (GRBF) model, termed Supervised Growing Neural Gas (SGNG), is selected from the literature. SGNG employs a one-...
متن کاملNeural Gas for Surface Reconstruction
In this paper we present an adaptation of Neural Gas (NG) for reconstructing 3D-surfaces from point clouds. NG is based on online adaptation according to given data points and constitutes a neural clustering algorithm that is robust with respect to noisy data and efficient, because the runtime depends solely on the accuracy of the surface reconstruction and is independent of the size of the inp...
متن کاملA Self-Reconstructing Algorithm for Single and Multiple-Sensor Fault Isolation Based on Auto-Associative Neural Networks
Recently different approaches have been developed in the field of sensor fault diagnostics based on Auto-Associative Neural Network (AANN). In this paper we present a novel algorithm called Self reconstructing Auto-Associative Neural Network (S-AANN) which is able to detect and isolate single faulty sensor via reconstruction. We have also extended the algorithm to be applicable in multiple faul...
متن کامل