对CHM模型进行分水岭单木分割的代码

以下是对CHM模型进行分水岭单木分割的Python代码：

import numpy as np
import cv2
from skimage.segmentation import watershed
from scipy import ndimage as ndi

# 读取CHM模型数据并进行预处理
chm = cv2.imread('chm.tif', cv2.IMREAD_GRAYSCALE)
chm = cv2.medianBlur(chm, 5)
chm = cv2.GaussianBlur(chm, (5,5), 0)

# 获取CHM模型数据的梯度
sobelX = cv2.Sobel(chm,cv2.CV_64F,1,0,ksize=3)
sobelY = cv2.Sobel(chm,cv2.CV_64F,0,1,ksize=3)
gradient = cv2.subtract(sobelX, sobelY)
gradient = cv2.convertScaleAbs(gradient)

# 进行二值化处理
ret, binary = cv2.threshold(gradient, 0, 255, cv2.THRESH_BINARY+cv2.THRESH_OTSU)

# 进行形态学操作，去除小的噪点
kernel = np.ones((3,3),np.uint8)
binary = cv2.morphologyEx(binary, cv2.MORPH_OPEN, kernel, iterations = 2)

# 对二值图像进行分水岭分割
distance = ndi.distance_transform_edt(binary)
local_maxi = ndi.maximum_filter(distance, size=3)
markers = ndi.label(local_maxi)[0]
labels = watershed(-distance, markers, mask=binary)

# 对分割结果进行可视化
output = np.zeros_like(chm)
for label in np.unique(labels):
    if label == 0:
        continue
    mask = np.zeros_like(chm)
    mask[labels == label] = 255
    contours, _ = cv2.findContours(mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
    cv2.drawContours(output, contours, -1, (255,255,255), 2)

cv2.imshow('Output', output)
cv2.waitKey(0)

上述代码首先读取了CHM模型数据，并进行了预处理，包括中值滤波和高斯滤波。然后获取了CHM模型数据的梯度，并进行了二值化处理和形态学操作，去除小的噪点。接下来对二值图像进行分水岭分割，并对分割结果进行可视化。最后将分割结果显示出来。