在图像中识别可见的石头 - opencv＆amp;深度学习

Question

我有图像中存在的石头的样品图像。我只需要识别可见的石头。我尝试的方法是基于阈值的过滤和检测Cv2.Contours 。另外，我正在研究 enet体系结构 。样品图像在下面。
示例Image1： 示例Image2：

我尝试用于基于轮廓的检测的代码如

image = cv2.imread(os.path.join(img_path, img_name2))
# threshold based customization
lower_bound = np.array([0, 0, 0])
upper_bound = np.array([250,55,100])

hsv = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)
#masking the image using inRange() function
imagemask = cv2.inRange(hsv, lower_bound, upper_bound)
plt.figure(figsize=(20,10)) 
plt.imshow(imagemask, cmap="gray")
# erode and diluation to smoothen the edeges
final_mask = cv2.erode(imagemask, np.ones((3, 3), dtype=np.uint8))
final_mask = cv2.dilate(imagemask, np.ones((5, 5), dtype=np.uint8))
# find contours based on the mask
contours = cv2.findContours(final_mask.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
# draw contours
img_conts = cv2.drawContours(image.copy(), contours[0], -1, (0,255,0), 3)

plt.figure(figsize=(20,10)) 
plt.imshow(img_conts, cmap="gray")

示例轮廓OUPUT下方。我知道可以在此处调整阈值以获得更好的结果。

但是，我在这里寻找的任何更好的方法或解决方案都可以在这个繁重的环境中起作用，以检测像石头这样的小颗粒。有什么想法可以更好地解决吗？

Answer 1

这是您可以使用Canny Edge检测器来检测图像中的岩石：

import cv2
import numpy as np

def process(img):
    img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    _, thresh = cv2.threshold(img_gray, 103, 255, cv2.THRESH_BINARY)
    img_blur = cv2.GaussianBlur(thresh, (23, 23), 0)
    img_canny = cv2.Canny(img_blur, 65, 0)
    img_dilate = cv2.dilate(img_canny, None, iterations=2)
    return cv2.erode(img_dilate, None, iterations=2)

imgs = [cv2.imread("image1.jpg"), cv2.imread("image2.jpg")]

for i, img in enumerate(imgs):
    contours = cv2.findContours(process(img), cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)[0]
    cv2.drawContours(img, contours, -1, (0, 255, 0), 1)
    cv2.imshow(str(i), img)

cv2.waitKey(0)
cv2.destroyAllWindows()

示例图像1和2的输出：

​使用以下代码的跟踪栏：

import cv2
import numpy as np
from random import randint, sample

def process(img, c_t1, c_t2):
    img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    _, thresh = cv2.threshold(img_gray, 103, 255, cv2.THRESH_BINARY)
    img_blur = cv2.GaussianBlur(thresh, (23, 23), 0)
    img_canny = cv2.Canny(img_blur, c_t1, c_t2)
    img_dilate = cv2.dilate(img_canny, None, iterations=2)
    return cv2.erode(img_dilate, None, iterations=2)

def show(imgs, win="Image", scale=1):
    imgs = [cv2.cvtColor(img, cv2.COLOR_GRAY2BGR) if len(img.shape) == 2 else img for img in imgs]
    img_concat = np.concatenate(imgs, 1)
    h, w = img_concat.shape[:2]
    cv2.imshow(win, cv2.resize(img_concat, (int(w * scale), int(h * scale))))

d = {"Canny Threshold 1": (65, 500),
     "Canny Threshold 2": (0, 500)}

imgs = [cv2.imread("image1.jpg"), cv2.imread("image2.jpg")]

cv2.namedWindow("Track Bars")
for i in d:
    cv2.createTrackbar(i, "Track Bars", *d[i], id)

while True:
    c_t1, c_t2 = (cv2.getTrackbarPos(i, "Track Bars") for i in d)
    for i, img in enumerate(imgs):
        img_copy = img.copy()
        processed = process(img, c_t1, c_t2)
        contours = cv2.findContours(processed, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)[0]
        cv2.drawContours(img_copy, contours, -1, (0, 255, 0), 1)
        show([img_copy, processed], str(i))
    if cv2.waitKey(1) & 0xFF == ord("q"):
        break

cv2.destroyAllWindows()

outupt：

_{（单击图像以展开）}