Circular Color Cubic Higher-order Local Auto-Correlation (C3-HLAC) is an efficient descriptor extracted from color voxel data, as presented in A. Kanezaki, T. Suzuki, T. Harada & Y. Kuniyoshi. Fast Object Detection for Robots in a Cluttered Indoor Environment Using Integral 3D Feature Table, Proceedings of the 2011 IEEE International Conference on Robotics and Automation (ICRA2011), 2011. It is obtained as a 981-dimensional histogram, where each bin is differentiated by the RGB color space and the relative position of the two neighboring voxels.

Please also see our project page here.


$ rosrun c3_hlac example_c3_hlac `rospack find c3_hlac`/data/sample.pcd

This executable reads color point cloud "sample.pcd" and writes its C3-HLAC descriptor into "c3_hlac.pcd" in the current directory.

If you have pcl_visualization, you can see the histogram by:

$ rosrun pcl_visualization pcd_viewer c3hlac.pcd

Wiki: c3_hlac (last edited 2011-04-22 02:39:07 by Asako Kanezaki)