Robust segmentation in laser scanning 3D point cloud data
Segmentation is a most important intermediate step in point cloud data processing and understanding. Covariance statistics based local saliency features from Principal Component Analysis (PCA) are frequently used for point cloud segmentation. However it is well known that PCA is sensitive to outlier...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Published: |
IEEE eXpress Conference Publishing
2012
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/20.500.11937/16069 |
| Summary: | Segmentation is a most important intermediate step in point cloud data processing and understanding. Covariance statistics based local saliency features from Principal Component Analysis (PCA) are frequently used for point cloud segmentation. However it is well known that PCA is sensitive to outliers. Hence segmentation results can be erroneous and unreliable. The problems of surface segmentation in laser scanning point cloud data are investigated in this paper. We propose a region growing based statistically robust segmentation algorithm that uses a recently introduced fast Minimum Covariance Determinant (MCD) based robust PCA approach. Experiments for several real laser scanning datasets show that PCA gives unreliable and non-robust results whereas the proposed robust PCA based method has intrinsic ability to deal with noisy data and gives more accurate and robust results for planar and non planar smooth surface segmentation. |
|---|