Robotic Visual Tracking of Relevant Cues in Underwater Environments with Poor Visibility Conditions

Table 2

Comparison of the most relevant region detected as relevant (nonwater regions) by using the NVT and the proposed method. In the last row the total number of images and the average of the percentage of detected relevant regions are specified.

Seq.	Frames	Depth [m]	% of relevant region (NVT)	% of relevant region (AVA)
1	168	7.7	90.47	91.07
2	243	7.8	94.23	95.06
3	153	7.8	99.34	100
4	181	11.8	88.39	95.5
5	163	7.1	95.02	98.15
6	242	11.3	87.02	91.60
	1150		92.41	95.23