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.

Preprocessing of HSI.

More »

Fig 1 Expand

Fig 2.

Proposed multibranch CNN architecture.

More »

Fig 2 Expand

Table 1.

Segmentation details of the datasets: Indian Pines (IP), Salinas Scene (SC), and The Pavia University (PU). Seg-L denotes the dataset is split into L highly correlated subgroups; in Seg-3, the dataset is split into 3 sub-groups.

More »

Table 1 Expand

Table 2.

Configuration of deep neural network used in feature learning procedure.

More »

Table 2 Expand

Table 3.

Number of pixels corresponding to their land cover categories for SC dataset.

More »

Table 3 Expand

Table 4.

Number of pixels corresponding to their land cover categories for the PU dataset.

More »

Table 4 Expand

Table 5.

Number of pixels corresponding to their land cover categories for the IP dataset.

More »

Table 5 Expand

Fig 3.

Band-to-band correlation matrix for the datasets, (a) SC, (b) PU, (c) IP, and (d) Band-to-band correlation matrix show the segmentation of SC when L=3.

More »

Fig 3 Expand

Table 6.

Outcomes of the proposed model for different segmentations of datasets.

More »

Table 6 Expand

Table 7.

Comparison of the proposed model with the state of the arts for SC dataset.

More »

Table 7 Expand

Table 8.

Comparison of the proposed model with the state of the arts for the PU dataset.

More »

Table 8 Expand

Table 9.

Comparison of the proposed model with the state of the arts for the IP dataset.

More »

Table 9 Expand

Fig 4.

Overall accuracy comparison of (a) SC, (b) PU, and (c) IP datasets for different training samples.

More »

Fig 4 Expand

Table 10.

Computational parameter comparison and analysis.

More »

Table 10 Expand

Table 11.

Class-wise accuracies (%) for the SC dataset with 10% training samples.

More »

Table 11 Expand

Table 12.

Class-wise accuracies (%) for the PU dataset with 10% training samples.

More »

Table 12 Expand

Table 13.

Class-wise accuracies (%) for the IP dataset with 10% training samples.

More »

Table 13 Expand

Fig 5.

Loss and accuracy curves of all datasets for training samples, (a) SC loss, (b) PU loss, (c) IP loss, (d) SC accuracy, (e) PU accuracy, and (f) IP accuracy.

More »

Fig 5 Expand

Table 14.

Outcomes of the ablation studies.

More »

Table 14 Expand