TreeBASIS Feature Descriptor and Its Hardware Implementation

Table 3

Accuracy results and memory footprints for SIFT, SURF, BASIS, and TreeBASIS on the Idaho dataset. Memory usage assumes that 1,000 features per image are kept for each algorithm.

Algorithm	Average memory usage per image	Homography accuracy
SIFT	1,024 Kilobytes	34.7%
SURF	512 Kilobytes	73.5%
BASIS	288 Kilobytes	75.5%
TreeBASIS	2.1 Kilobytes	79.6%