A Method for Registration of 3-D Shapes
IEEE Transactions on Pattern Analysis and Machine Intelligence - Special issue on interpretation of 3-D scenes—part II
An implicit surface polygonizer
Graphics gems IV
Piecewise smooth surface reconstruction
SIGGRAPH '94 Proceedings of the 21st annual conference on Computer graphics and interactive techniques
Zippered polygon meshes from range images
SIGGRAPH '94 Proceedings of the 21st annual conference on Computer graphics and interactive techniques
A dynamic integration algorithm to model surfaces from multiple range views
Machine Vision and Applications
A General Surface Approach to the Integration of a Set of Range Views
IEEE Transactions on Pattern Analysis and Machine Intelligence
An optimal algorithm for approximate nearest neighbor searching
SODA '94 Proceedings of the fifth annual ACM-SIAM symposium on Discrete algorithms
An Algorithm for Finding Best Matches in Logarithmic Expected Time
ACM Transactions on Mathematical Software (TOMS)
ICP Registration Using Invariant Features
IEEE Transactions on Pattern Analysis and Machine Intelligence
Digital Image Processing
Reliable Surface Reconstructiuon from Multiple Range Images
ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume I - Volume I
Multi-scale EM-ICP: A Fast and Robust Approach for Surface Registration
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part IV
Image Based Measurement Systems
Image Based Measurement Systems
Accurate integration of multi-view range images using k-means clustering
Pattern Recognition
Markov random field-based clustering for the integration of multi-view range images
ISVC'10 Proceedings of the 6th international conference on Advances in visual computing - Volume Part I
MRF labeling for multi-view range image integration
ACCV'10 Proceedings of the 10th Asian conference on Computer vision - Volume Part II
| Hi-index | 0.00 |
A complete pipeline of data fusion from rangeimages for a 3D object reconstruction and modeling ispresented. The proposed approach includes multi-viewregistration, data integration, smoothing, andresampling. Firstly, the range images taken frommultiple views are registered through a set oftranslation and rotation matrices whose coefficientsare carefully pre-calculated. Then, a definition andtwo criteria to overlap elimination are provided as thefoundation together with kd-tree data structure andnearest neighbor searching technique for dataintegration. A surface-based smoothing filter and areliable resampling method, called the ball-travel-basedresampling, are also given for surface qualityimprovement and data size reduction. All theoperations manipulate range images directly withoutadditional preprocessing operation, such as meshingor implicit surface function calculation to each rangeimage, and thus provide a straightforward way to fuseany 3D data. The approach is applied to various rangedata sets of objects with different geometry shapes. Theexperimental results demonstrate the efficiency andapplicability of the proposed method.