Method: Drost-CVPR10-3D-Only-Thresholded

User Berti
Publication Drost et al., Model globally, match locally: Efficient and robust 3D object recognition, CVPR 2010
Training image modalities None
Test image modalities D

An implementation of the paper, including ICP for post-processing. The parameters are set to a slower, but more accurate mode (relative sampling distance of 0.03 for model creation and matching). No images are used.

Depth images are thresholded using the ranges defined for each dataset.

CPU only, no GPU is used for either training or detection.

Implementation: HALCON 19.05 progress.

Computer specifications Max. 12 Threads on intel Xeon CPU E5-2690 v4 @ 2.60GHz, 2601 Mhz

Public submissions

No submissions yet.