Function that computes the ISS Keypoints from an input point cloud. This implements the keypoint detection module proposed in Yu Zhong ,"Intrinsic Shape Signatures: A Shape Descriptor for 3D Object
Recognition", 2009. The implementation is inspired by the PCL one.
- Parameters
-
input | The input PointCloud where to compute the ISS Keypoints. |
salient_radius | The radius of the spherical neighborhood used to detect the keypoints |
non_max_radius | The non maxima supression radius. If non of the input parameters are specified or are 0.0, then they will be computed from the input data, taking into account the Model Resolution. |
gamma_21 | The upper bound on the ratio between the second and the first eigenvalue |
gamma32 | The upper bound on the ratio between the third and the second eigenvalue |
min_neighbors | Minimum number of neighbors that has to be found to consider a keypoint. |
- Authors
- Ignacio Vizzo and Cyrill Stachniss, University of Bonn.