Figures & data
Table 1. Number of training and testing samples.
Table 2. Class-specific accuracies of spectral classification for optical and LWIR image.
Table 3. Class-specific accuracies of spectral-spatial classifications for both optical and LWIR image.
Figure 2. Percentage of improvement for the AA obtained by the spectral-spatial classification methods, compared to the raw spectral-based method.
![Figure 2. Percentage of improvement for the AA obtained by the spectral-spatial classification methods, compared to the raw spectral-based method.](/cms/asset/dff6bcfe-745a-43af-a369-cbe1b9955f59/tgsi_a_1403731_f0002_oc.gif)
Table 4. Class-specific accuracies for the joint classification optical and LWIR image (with spatial features calculated on the first PC of optical image).
Table 5. Class-specific accuracies for the joint classification optical and LWIR Image (with spatial features calculated on the first PC of LWIR image).
Table 6. Class-specific accuracies for the multiple features classification.
Table 7. Class-specific accuracies for the object-based classification.
Figure 3. Classification maps for the object-based classification: (a) Multiple features classification map using majority voting; (b) Multiple features classification map using posterior probability; (c) Multiple features classification map using uncertainty; (d) Spectral-spatial classification map using GLCM textures; (e) Joint classification map using GLCM textures.
![Figure 3. Classification maps for the object-based classification: (a) Multiple features classification map using majority voting; (b) Multiple features classification map using posterior probability; (c) Multiple features classification map using uncertainty; (d) Spectral-spatial classification map using GLCM textures; (e) Joint classification map using GLCM textures.](/cms/asset/16af5a52-ff29-4f97-95ef-b8f30a5e7aee/tgsi_a_1403731_f0003_oc.gif)