Skip to main content

Table 2 Spectral and textural features and their corresponding equations used in this study

From: Use of vegetation change tracker, spatial analysis, and random forest regression to assess the evolution of plantation stand age in Southeast China

Group

Features

Description

Tasselled cap transformation (Crist 1985)

Brightness (TCT_B)

(B × 0.3561) + (G × 0.3972) + (R × 0.3904) + (NIR × 0.6966) + (SWIR1 × 0.2286) + (SWIR2 × 0.1596)

Greenness

(TCT_G)

[B × (−0.3344)] + [G × (−0.3544)] + [R × (−0.4556)] + (NIR × 0.6966) + [SWIR1 × (−0.0242)] + [SWIR2 × (−0.2630)]

Wetness (TCT_W)

(B × 0.2626) + (G × 0.2141) + (R × 0.0926) + (NIR × 0.0656) + [SWIR1 × (−0.7629)] + [SWIR2 × (−0.5388)]

Spectral vegetation indices

Enhanced vegetation index

(EVI) (Huete et al. 2002)

\( 2.5\times \frac{\left( NIR-R\right)}{\left( NIR+6\times R-7.5\times B+1\right)} \)

Green normalized difference vegetation index

(GNDVI) (Gitelson and Merzlyak 1998)

\( \frac{\left( NIR-G\right)}{\left( NIR+G\right)} \)

Green ration vegetation index (GRVI) (Fiorella and Ripple 1993)

\( \frac{NIR}{G} \)

Modified Simple Ratio

(MSR) (Chen 1996)

\( \frac{\left(\frac{NIR}{R}\right)-1}{\left(\sqrt{\frac{NIR}{R}}\right)+1} \)

Normalized difference vegetation index (NDVI) (Rouse Jr et al. 1974)

\( \frac{\left( NIR-R\right)}{\left( NIR+R\right)} \)

Simple ratio (SR) (Birth and McVey 1968)

\( \frac{NIR}{R} \)

Transformed difference vegetation index (TDVI) (Bannari et al. 2002)

\( \sqrt{0.5+\frac{\left( NIR-R\right)}{\left( NIR+R\right)}} \)

Textural features(Anys et al. 1994)

Data Range (DR) for Red (DR_Red),NIR(DR_NIR), SWIR1(DR_SWIR1),SWIR2(DR_SWIR2)

Vmax − Vmin

Mean(ME) for Red (ME_Red),NIR(ME_NIR), SWIR1(ME_SWIR1),SWIR2(ME_SWIR2)

\( \sum \limits_{i=0}^{N_{g-1}} iP(i) \)

Variance(VA) for Red (VA_Red),NIR(VA_NIR), SWIR1(VA_SWIR1),SWIR2(VA_SWIR2)

\( \sum \limits_{i=0}^{N_{g-1}}{\left(i-M\right)}^2\ P(i) \)

Entropy(EN) for Red (EN_Red),NIR(EN_NIR), SWIR1(EN_SWIR1),SWIR2(EN_SWIR2)

\( -\sum \limits_{i=0}^{N_{g-1}}P(i)\ast lnP(i) \)

Skewness(SK) for Red (SK_Red),NIR(SK_NIR), SWIR1(SK_SWIR1),SWIR2(SK_SWIR2)

\( \sum \limits_{i=0}^{N_{g-1}}{\left(i-M\right)}^3P(i) \)

  1. Note: B is blue band, G is green band, R is red band, NIR is near infrared band, SWIR 1 is short-wave infrared band 1, and SWIR2 is short-wave infrared band 2. P(i) is the probability of each pixel value in the window, and Ngis the number of distinct grey levels in the window of the quantized image