Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Proposed target recognition framework.

More »

Fig 1 Expand

Fig 2.

Off-board recognition system.

More »

Fig 2 Expand

Fig 3.

On-board/real-time recognition system.

More »

Fig 3 Expand

Table 1.

CNN configurations.

More »

Table 1 Expand

Fig 4.

Experimental scenario.

A and B represent waypoints while the search area was 40m*40m.

More »

Fig 4 Expand

Fig 5.

Simulation environment, UAV moving from one-way point to another while searching for the target a) UAV taking off b) searching target c) target recognized.

More »

Fig 5 Expand

Fig 6.

UAV used in the experiment.

More »

Fig 6 Expand

Fig 7.

Comparing the supervised learning classifiers’ results on five different evaluation sets a) F1 score for training sets b) F1 score for testing sets.

More »

Fig 7 Expand

Fig 8.

Recognition with a confidence score.

More »

Fig 8 Expand

Table 2.

Average training results of classifiers for the five evaluation tests.

More »

Table 2 Expand

Table 3.

Average testing results of classifiers for the five evaluation tests.

More »

Table 3 Expand

Fig 9.

Average F1 score and processing time for all configurations.

More »

Fig 9 Expand

Fig 10.

MSM for comparing two sets of images [31].

More »

Fig 10 Expand

Fig 11.

Typical LeNet-5 architecture [35].

More »

Fig 11 Expand

Fig 12.

VGG-16 model for bird species classification [36].

More »

Fig 12 Expand

Table 4.

Average testing results of classifiers for the 5 evaluation tests.

More »

Table 4 Expand

Fig 13.

Average F1 score and processing time for comparison.

More »

Fig 13 Expand