Dynamic Self-Occlusion Avoidance Approach Based on the Depth Image Sequence of Moving Visual Object

Table 2

The self-occlusion avoidance process of visual object Bunny with both translation and rotation.

Information	Image number
	1	2	3	⋯	5	⋯	9	⋯	15	16
Depth image				⋯		⋯		⋯
Matching Gaussian curvature feature matrices with SIFT algorithm	—			⋯		⋯		⋯		—
Total matched points	—	224	162	⋯	205	⋯	247	⋯	338	—
Error matched points	—	20	11	⋯	30	⋯	42	⋯	29	—
Error rate	—	8.9%	6.8%	⋯	14.6%	⋯	17.0%	⋯	8.6%	—
Observation position	0.00, −1.00, 300.00	0.00, −1.00, 300.00	56.68, −2.00, 295.07	⋯	127.16, −45.74, 266.26	⋯	211.41, −97.78, 180.11	⋯	253.84, −111.47, 102.68	262.32, −117.25, 92.19
Observation direction	0.00, 1.00, −300.00	0.00, 1.00, −300.00	−59.09, −4.85, −294.09	⋯	−133.20, 50.28, −264.07	⋯	−226.40, 129.39, −148.33	⋯	−255.15, 134.29, −82.87	−256.98, 145.29, −53.43
Observed area	—	167.61	625.48	⋯	1453.64	⋯	2431.37	⋯	2648.57	2654.63