Outputs:
det_out - dictionary of RGB image, ground truth image, and detector outputs
6/2/2018 - Alina Zare
10/12/2018 - Python Implementation by Yutai Zhou
"""
# Load data
an_hsi_img_for_tgt_det_demo = loadmat('an_hsi_img_for_tgt_det_demo.mat')
hsi_sub = an_hsi_img_for_tgt_det_demo['hsi_sub']
tgt_spectra = an_hsi_img_for_tgt_det_demo['tgt_spectra']
tgt_spectra = tgt_spectra.squeeze()
wavelengths = an_hsi_img_for_tgt_det_demo['wavelengths']
gt_img_sub = an_hsi_img_for_tgt_det_demo['gtImg_sub']
det_out = {}
det_out['RGB'] = get_RGB(hsi_sub, wavelengths)
det_out['Ground Truth'] = gt_img_sub
# init detector args
guard_win = 1
bg_win = 3
beta = 0.001
n_dim_ss = 10
ems = hsi_sub[:3,
1, :].T # need to provide background endmembers (can get them using SPICE unmixing)
# call detectors
abd_out = abd_detector(hsi_sub, tgt_spectra, ems)
det_out['ABD'] = abd_out
ace_out, _, _ = ace_detector(hsi_sub, tgt_spectra)
det_out['ACE Squared'] = ace_out
# # Outputs: # im_reduced: cell array containing reduced data results # # Author: Alina Zare # Email Address: [email protected] # Created: June 3, 2018 # load data an_hsi_image_sub_for_demo = loadmat('an_hsi_image_sub_for_demo.mat') img = an_hsi_image_sub_for_demo['hsi_img_sub'] wavelengths = an_hsi_image_sub_for_demo['wavelengths'] # run hdr hdr_out = dimReduction(img) # run mnf mnf_out = mnf(img, 0.999)[0] mnf_out = (mnf_out - np.min(mnf_out)) / np.max(mnf_out) # visualize plt.subplot(1, 3, 1) plt.title("RGB Image") plt.imshow(get_RGB(img, wavelengths)) plt.subplot(1, 3, 2) plt.title("HDR Image") plt.imshow(hdr_out[:, :, :3]) plt.subplot(1, 3, 3) plt.title("MNF Image") plt.imshow(mnf_out[:, :, :3]) plt.show()
if not present or empty, no mask restrictions are used
wavelength - 1 x n_band vector listing wavelength values for hsi_img in nm
Outputs:
class_out - dictionary of rgb image and classifier outputs
6/3/2018 - Alina Zare
10/2018 - Python Implementation by Yutai Zhou
"""
an_hsi_img_for_class_demo = loadmat('an_hsi_img_for_class_demo.mat')
hsi_img = an_hsi_img_for_class_demo['hsi_sub']
train_data = an_hsi_img_for_class_demo['train_data']
wavelength = an_hsi_img_for_class_demo['wavlength']
class_out = {}
class_out['RGB'] = get_RGB(hsi_img, wavelength)
class_out['KNN'] = knn_classifier(hsi_img, train_data, K = 3)
class_out['FKNN'] = fuzzy_knn_classifier(hsi_img, train_data, K = 3, m = 2.1)
class_out['PKNN'] = poss_knn_classifier(hsi_img, train_data, K = 3, eta = 0.01, m = 2.1)
# KNN Results
fig, ax = plt.subplots(1,2,figsize=(15, 8))
plt.subplots_adjust(hspace=.5)
plt.suptitle('KNN Results')
ax[0].imshow(class_out['RGB']); ax[0].set_title('RGB')
cax = ax[1].imshow(class_out['KNN']); ax[1].set_title('KNN')
cbar = fig.colorbar(cax, ticks=[i for i in range(len(train_data[0]))], orientation='vertical')
cbar.ax.set_yticklabels([i[0] for i in train_data[0][:]['name']])
# Fuzzy KNN Results