如何从HFS分割图像中提取轮廓 [英] How to extract contours from HFS segmented image

问题描述

如何从HFS模型输出中获取轮廓?我正在尝试检测地板.任何帮助将不胜感激.

How to grab contours from HFS model output? I'm trying to detect floor. Any help would be appreciated.

推荐答案

由于地板具有特定的颜色范围，我们可以使用 cv2.inRange()设置颜色阈值.我们将图像转换为HSV格式，然后使用上下阈值生成二进制分割的蒙版

Since the floor has a specific color range, we can color threshold using cv2.inRange(). We convert the image to HSV format then use a lower and upper threshold to generate a binary segmented mask

lower = np.array([0, 31, 182])
upper = np.array([57, 75, 209])

要找到地板轮廓，我们可以在蒙版图像上找到轮廓.这是地板突出显示为绿色的结果

To find the floor contour, we can just find contours on the mask image. Here's the result with the floor highlighted in green

import numpy as np
import cv2

# Color threshold
image = cv2.imread('1.jpg')
original = image.copy()
hsv = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)
lower = np.array([0, 31, 182])
upper = np.array([57, 75, 209])
mask = cv2.inRange(hsv, lower, upper)
result = cv2.bitwise_and(original,original,mask=mask)

# Find floor contour on mask
cnts = cv2.findContours(mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
    cv2.drawContours(original,[c], -1, (36,255,12), 2)

cv2.imshow('mask', mask)
cv2.imshow('result', result)
cv2.imshow('original', original)
cv2.waitKey()

这篇关于如何从HFS分割图像中提取轮廓的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！