23.7 Linear Spectral Mixture Analysis

The HYDICE 15-panel scene in Figure 1.15 was used for experiments where the 19 R panel pixels, p11, p12, p13, p211, p221, p22, p23, p311, p312, p32, p33, p411, p412, p42, p43, p511, p521, p52, and p53, provided by the ground truth in Figure 1.15(b) were used for quantitative analysis. According to the ground truth in Figures 1.15, 1.16, 1.17, nine signatures, m1 = p1, m2 = p2, m3 = p3, m4 = p4, and m5 = p5 in Figure 1.16 and background signatures, m6 = grass, m7 = road, m8 = tree, and m9 = interferer in Figure 1.17, were used to unmix these 19 R panel pixels for panel detection and quantification.

Table 23.4 gives the first 35 highest prioritized “de-correlated bands” by ID-BD with the threshold value ε set to 0.1 and the corresponding “BD-removed bands” where seven BP criteria, variance, SNR, skewness, kurtosis, entropy, ID, and negentropy, are used to prioritize bands.

Table 23.4 First 35 highest prioritized BP/BD bands and corresponding removed bands after ID-BD with ε = 0.1 using 7 BP criteria for BP of HYDICE data.

BR/BD bands Corresponding removed bands
Variance 60/56/78/53/52/55/54/49/45/92/38/34/28/26/27/25/24/23/22/20/21/102/19/18/17/16/15/14/13/12/11/10/84/9/8 61/67/66/65/59/57/68/62/64/77/76/79/63/80/58/75/81/69/50/82/48/51/46/70/47/44/43/42/41/74/93/91/40/95/39/90/94/37/96/89/83/36/35/33/88/32/71/31/30/97/29/87/73/103/108/105/104/109/101/106/107/111/110/112/113/100/114/72/115/99/86/116
Skewness 1/122/50/127/2/169/168/128/129/45/167/22/ ...

Get Hyperspectral Data Processing: Algorithm Design and Analysis now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.