# 1.1 Introduction
## Features this code extract
This code is desinged for extracting LiDAR features, including:
- Total number of points: number of non-ground pints in each plot
- Height/Intensity percent features: 30% height/intensity derived from non-ground points

- Height/Intensity statistic features: only based on non-ground points, calculated the following
1. Standard deviation
2. Quadratic mean: A type of average, calculated as the square root of the mean of the squares. $\large Q=\sqrt{\frac{x^2_1+x^2_2+...+x^2_n}{n}}$
3. Skewness: For normally distributed data, the skewness should be about zero. For unimodal continuous distributions, a skewness value greater than zero means that there is more weight in the right tail of the distribution.
4. Kurtosis: The fourth central moment divided by the square of the variance. (default is using Fisher’s definition, which means abstract another 3 to make the kurtosis of normal distribution equal to 0, here is not using Fisher’s definition)
5. Coefficient of variation: The ratio of the biased standard deviation to the mean. The higher the coefficient of variation, the greater the level of dispersion around the mean.
- $\large CV=\huge \frac{\sigma}{\mu}$
- Canopy cover features: calculate number of points above each red line, divided by number of all points in each plot
- $Plot\_LII_{30\%}= \huge \frac{\# NG\ points\ above\ 30\%\ height}{\# all\ points}$
- NG: non-ground

- Plots volume feature:
- calculate an average height of each grid:
$\large Average\ Height_{grid}= \huge \frac{95\%\ height\ of\ NG\ points+min\ height\ of\ NG\ points}{2}$
- Find grids belong to each plot based on the location of grid center as following, the blue area is one plot (row2&3), the red dash line is all the grids belong to this plot.
$\large Volume_{plot}=\huge \frac{\Sigma Average\ Height\times (grid\_resolution)^2}{\#\ grids}$