app.py

import streamlit as st
import numpy as np
import laspy
from sklearn.cluster import DBSCAN
from sklearn.metrics import accuracy_score
from scipy.spatial import ConvexHull
from skimage.measure import profile_line

st.title("Tree Analysis App")

# Upload LAS file
uploaded_file = st.file_uploader("Upload a LAS file", type=["las", "laz"])

if uploaded_file is not None:
    # Load the LAS file
    las_file = laspy.read(uploaded_file)
    height_filter = np.logical_and(las_file.z > 1, las_file.z < 30)
    las_file = las_file[height_filter]
    # Extract the x and y coordinates from the LAS file
    x = las_file.x
    y = las_file.y

    # Combine the x and y coordinates into a feature matrix
    feature_matrix = np.column_stack((x, y))

    # Segment the trees using DBSCAN clustering with a specified distance threshold (e.g., 2 meters)
    tree_labels = DBSCAN(eps=2, min_samples=10).fit_predict(feature_matrix)

    # Count the number of trees
    num_trees = len(set(tree_labels)) - (1 if -1 in tree_labels else 0)
    st.write(f"Number of trees: {num_trees}")
    for i in range(num_trees):
        indices = np.where(tree_labels == i)[0]

        tree_x = x[indices]
        tree_y = y[indices]

        tree_mid_x = np.mean(tree_x)
        tree_mid_y = np.mean(tree_y)

        st.write(f"Tree {i+1} middle point: ({tree_mid_x:.3f}, {tree_mid_y:.3f})")

    def calculate_tree_data(points):
        height = np.max(points.z) - np.min(points.z)
        xy_points = np.column_stack((points.X, points.Y))
        hull = ConvexHull(xy_points)
        crown_spread = np.sqrt(hull.area / np.pi)/10
        z_trunk = np.percentile(points.z, 20)  # assume trunk is the lowest 20% of the points
        trunk_points = points[points.z < z_trunk]
        dbh = 2 * np.mean(np.sqrt((trunk_points.X - np.mean(trunk_points.X)) ** 2 + (trunk_points.Y - np.mean(trunk_points.Y)) ** 2))
        return height, crown_spread, dbh

    tree_data = []
    for tree_label in range(num_trees):
        # Extract points for the current tree
        tree_points = las_file.points[tree_labels == tree_label]
        # Calculate tree data
        data = calculate_tree_data(tree_points)
        # Append data to list
        tree_data.append(data)

    # Print the data for each tree
    for i, data in enumerate(tree_data):
        st.write(f"Tree {i + 1} - Height: {data[0]:.3f} m, Crown Spread: {data[1]:.3f} m, DBH: {data[2]:.3f} mm")