Multimodal Deep Feature Fusion (MMDFF) for RGB-D Tracking

Table 1

Comparison results: SR using different deep features fusions on the PTB dataset.

Deep Features	All SR	Target type			Target size		Movement		Occlusion		Motion type
		human	animal	rigid	large	small	slow	fast	yes	no	passive	active
Only RGB	0.73	0.75	0.69	0.74	0.80	0.72	0.71	0.72	0.74	0.85	0.78	0.73
RGB+Depth	0.77	0.79	0.71	0.77	0.81	0.77	0.76	0.73	0.81	0.86	0.79	0.75
RGB+Depth + RGB-depth correlated	0.79	0.81	0.74	0.79	0.83	0.79	0.78	0.74	0.83	0.86	0.81	0.77
RGB+Depth + RGB-depth correlated +Motion	0.84	0.83	0.86	0.85	0.85	0.86	0.82	0.83	0.87	0.87	0.82	0.83