Related
I am trying to filter the background of images presenting electric cables. I tried to do the following:
Transform from color to gray
Apply cv2.Laplacian or 2 times of cv2.Sobel for finding edges in both directions.
Apply thresholding cv2.THRESH_BINARY(_INV), cv2.THRESH_OTSU
Lastly, I tried to find edges with 'filtered' images using cv2.Canny together with cv2.HoughLinesP
Overall, the results aren't satisfying at all. I will give an example of 2 images:
And the output of my script:
I also played with the values in config, but the results weren't different much.
Here's the little script I managed to do:
import cv2
import matplotlib.pyplot as plt
import numpy as np
def img_show(images, cmap=None):
fig = plt.figure(figsize=(17, 10))
root = 3 # len(images) ** 0.5
for i, img in enumerate(images):
ax = fig.add_subplot(root, root, i + 1)
ax.imshow(img, cmap=cmap[i])
plt.show()
class Config:
scale = 0.4
min_threshold = 120
max_threshold = 200
canny_min_threshold = 100
canny_max_threshold = 200
config = Config()
def find_lines(img, rgb_img):
dst = cv2.Canny(img, config.canny_min_threshold, config.canny_max_threshold)
cdstP = np.copy(rgb_img)
lines = cv2.HoughLinesP(dst, 1, np.pi / 180, 150, None, 0, 0)
lines1 = lines[:, 0, :]
for x1, y1, x2, y2 in lines1[:]:
cv2.line(cdstP, (x1, y1), (x2, y2), (255, 0, 0), 5)
return cdstP
if __name__ == "__main__":
bgr_img = cv2.imread('DJI_0009.JPG')
bgr_img = cv2.resize(bgr_img, (0, 0), bgr_img, config.scale, config.scale)
rgb_img = cv2.cvtColor(bgr_img, cv2.COLOR_BGR2RGB)
gray_img = cv2.cvtColor(bgr_img, cv2.COLOR_BGR2GRAY)
# _, threshold = cv2.threshold(gray_img, config.min_threshold, config.max_threshold, cv2.THRESH_BINARY)
# laplacian = cv2.Laplacian(rgb_img, cv2.CV_8UC1)
sobelx = cv2.Sobel(gray_img, cv2.CV_8UC1, 1, 0)
sobely = cv2.Sobel(gray_img, cv2.CV_8UC1, 0, 1)
blended = cv2.addWeighted(src1=sobelx, alpha=0.5, src2=sobely, beta=0.5, gamma=0)
_, threshold = cv2.threshold(blended, config.min_threshold, config.max_threshold,
cv2.THRESH_BINARY | cv2.THRESH_OTSU)
p1 = find_lines(threshold, rgb_img)
p2 = find_lines(blended, rgb_img)
p3 = find_lines(gray_img, rgb_img)
plots = [rgb_img, p1, p2, p3]
cmaps = [None] + ['gray'] * (len(plots) - 1)
img_show(plots, cmaps)
I am assuming I need to do much better filtring. However, I also tried image segmentation, but the results weren't promising at all.
Any ideas on how to improve this?
Thanks
Here is one way to do that in Python/OpenCV. I threshold, then optionally clean with morphology. Then get the contours and for each contour compute its rotated rectangle. Then get the dimensions of the rotated rectangle and compute the aspect ratio (largest dimension / smallest dimension) and optionally the area. Then I threshold on the aspect ratio (and optionally the area) and keep only those contours that pass)
Input:
import cv2
import numpy as np
image = cv2.imread("DCIM-100-MEDIA-DJI-0009-JPG.jpg")
hh, ww = image.shape[:2]
# convert to grayscale
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
# create a binary thresholded image
thresh = cv2.threshold(gray, 64, 255, cv2.THRESH_BINARY)[1]
# invert so line is white on black background
thresh = 255 - thresh
# apply morphology
kernel = np.ones((11,11), np.uint8)
clean = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel)
# get external contours
contours = cv2.findContours(clean, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
area_thresh = ww / 2
aspect_thresh = ww / 30
print(area_thresh,aspect_thresh)
print('')
result = image.copy()
for c in contours:
# get rotated rectangle from contour
# get its dimensions
rotrect = cv2.minAreaRect(c)
(center), (dim1,dim2), angle = rotrect
maxdim = max(dim1,dim2)
mindim = min(dim1,dim2)
area = dim1 * dim2
if mindim != 0:
aspect = maxdim / mindim
#print(area, aspect)
#if area > area_thresh and aspect > aspect_thresh:
if aspect > aspect_thresh:
# draw contour on input
cv2.drawContours(result,[c],0,(0,0,255),3)
print(area, aspect)
# save result
cv2.imwrite("DCIM-100-MEDIA-DJI-0009-JPG_thresh.jpg",thresh)
cv2.imwrite("DCIM-100-MEDIA-DJI-0009-JPG_clean.jpg",clean)
cv2.imwrite("DCIM-100-MEDIA-DJI-0009-JPG_result.jpg",result)
# display result
cv2.imshow("thresh", thresh)
cv2.imshow("clean", clean)
cv2.imshow("result", result)
cv2.waitKey(0)
cv2.destroyAllWindows()
Thresholded image:
Morphology cleaned image:
Result image:
I have a video file with 2 dot laser and I want to calculate the distance in pixels between them, I tried this code with OpenCV, but it is not working :
Image
import cv2
import numpy as np
cap = cv2.VideoCapture('D:\Books\Pav Man\PICS\Test\VID_20200609_195155.mp4')
#cap = cv2.VideoCapture(0)
old = 0
while (1):
# Take each frame
ret, frame = cap.read()
hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
lower_red = np.array([0, 0, 255])
upper_red = np.array([255, 255, 255])
mask = cv2.inRange(hsv, lower_red, upper_red)
cv2.imshow('mask', mask)
# cv2.imshow('Track Laser', frame)
moments = cv2.moments(hsv[:, :, 2])
output = cv2.connectedComponentsWithStats(mask, 8, cv2.CV_32S)
print (output[3])
print ("----**----")
if moments["m00"] > 0:
x = (moments['m10']/ moments['m00'])
y = (moments['m01']/ moments['m00'])
#print(moments['m00'],moments['m01'],moments['m10'])
#print(x, y)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
cap.release()
cv2.destroyAllWindows()
this code output = cv2.connectedComponentsWithStats(mask, 8, cv2.CV_32S) give me the centroid of points , but how to geat each point(laser dot) separately ? if I get the centroid I can measure the distance between these points
Here is your other way to do that in Python/OpenCV using connectedComponentsWithStats.
Read the input
Set min and max red colors
Use cv2.inRange() to threshold on the color range
Apply morphology open and close to clean up small spots and holes
Process with connectedComponentsWithStats to get the labels and centroids
Extract all the areas corresponding to the labels and centroids
For all labels, test if the area is smaller than some estimate of the background, as we want to exclude that centroid. Draw the label as a filled yellow region on a copy of the input. Extract the centroids of small regions and store in pts array. Draw the centroids as small green squares on the copy of the input.
For all saved points, compute the distance between successive ones.
Save the output
Input:
import cv2
import numpy as np
import math
# read image
frame = cv2.imread('red_spots.jpg')
hh, ww = frame.shape[:2]
# convert to hsv hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
# threshold image
lower_red = np.array([0, 0, 225])
upper_red = np.array([255, 255, 255])
thresh = cv2.inRange(hsv, lower_red, upper_red)
# apply close and open morphology to smooth
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (9,9))
morph = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel)
morph = cv2.morphologyEx(morph, cv2.MORPH_OPEN, kernel)
# do connected components processing
nlabels, labels, stats, centroids = cv2.connectedComponentsWithStats(morph, None, None, None, 8, cv2.CV_16U)
# get all areas from stats[label_start_id:label_stop_id, area_flag]
areas = stats[0:, cv2.CC_STAT_AREA]
# draw labels and get centroids and draw centroids
result = frame.copy()
pts = []
for i in range(0, nlabels):
if areas[i] <= ww*hh/5 :
# labels start at 1 not 0
result[labels == i+1] = (0,255,255)
pt = centroids[i]
pts.append(pt)
cx = pt[0]
cy = pt[1]
x = int(round(cx))
y = int(round(cy))
# draw small square at centroids
result[y-2:y+3,x-2:x+3] = (0,255,0)
print('centroid =',cx,",",cy)
number = len(pts)
for i in range(number-1):
pt1 = pts[i]
x1 = pt1[0]
y1 = pt1[1]
pt2 = pts[i+1]
x2 = pt2[0]
y2 = pt2[1]
dist = math.sqrt( (x2-x1)**2 + (y2-y1)**2 )
print('distance =', dist)
print('')
#save images
cv2.imwrite('red_spots_thresh2.jpg',thresh)
cv2.imwrite('red_spots_morph2.jpg',morph)
cv2.imwrite('red_spots_centroids2.jpg',result)
# show images
cv2.imshow("thresh", thresh)
cv2.imshow("morph", morph)
cv2.imshow("result", result)
cv2.waitKey(0)
cv2.destroyAllWindows()
Threshold image:
Morphology cleaned image:
Result image with colored region labels and centroids:
Centroids and Distances:
centroid = 1006.7307283673711 , 433.70499350726004
centroid = 1036.418693371483 , 750.4024797329519
distance = 318.08595229553544
Distance is the square root of the sum of the squares of the x difference and the y difference. So
import math
dist = math.sqrt( (x1-x2)**2 + (y1-y2)**2 )
for points x1,y1 and x2,y2
Here is one way to do your processing in Python/OpenCV using contours.
Read the input
Set min and max red colors
Use cv2.inRange() to threshold on the color range
Apply morphology open and close to clean up small spots and holes
Find contours
For each contour, draw the contour, use moments to compute the centroid, save the centroids in a list and draw a small square at the centroid location
For each successive pair of centroid points, compute the distance between them in pixels
Save the results
Input:
import cv2
import numpy as np
import math
# read image
frame = cv2.imread('red_spots.jpg')
# convert to hsv hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
# threshold image
lower_red = np.array([0, 0, 225])
upper_red = np.array([255, 255, 255])
thresh = cv2.inRange(hsv, lower_red, upper_red)
# apply close and open morphology to smooth
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (9,9))
morph = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel)
morph = cv2.morphologyEx(morph, cv2.MORPH_OPEN, kernel)
# draw contours and get centroids
spots = frame.copy()
contours = cv2.findContours(morph, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]
pts = []
count = 0
for c in contours:
cv2.drawContours(spots, [c], -1, (0,255,0), 2)
M = cv2.moments(c)
cx = M["m10"] / M["m00"]
cy = M["m01"] / M["m00"]
pt = (cx,cy)
pts.append(pt)
x = round(cx)
y = round(cy)
# draw small square at centroids
spots[y-2:y+3,x-2:x+3] = (255,0,0)
print('centroid =',cx,",",cy)
count = count + 1
for i in range(count-1):
pt1 = pts[i]
x1 = pt1[0]
y1 = pt1[1]
pt2 = pts[i+1]
x2 = pt2[0]
y2 = pt2[1]
dist = math.sqrt( (x2-x1)**2 + (y2-y1)**2 )
print('distance =', dist)
print('')
#save images
cv2.imwrite('red_spots_thresh.png',thresh)
cv2.imwrite('red_spots_morph.png',morph)
cv2.imwrite('red_spots_centroids.png',spots)
# show images
cv2.imshow("thresh", thresh)
cv2.imshow("morph", morph)
cv2.imshow("spots", spots)
cv2.waitKey(0)
cv2.destroyAllWindows()
Threshold image:
Morphology cleaned image:
Contours and centroids image:
Centroids and Distances:
centroid = 1036.4038142620232 , 750.3941127694858
centroid = 1006.6605586230609 , 433.9662237323787
distance = 317.8227024875417
You can do this:
The function cv2.InRange() to find two red dots.
The function cv2.connectedComponentsWithStats() to find the centroids of these red points.
Calculate the Euclidean distance between centroids.
Also, you can select points by brightness only, without even using their color.
import cv2
img = cv2.imread('HAgbc.jpg')
gray=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
cv2.normalize(gray, gray, 0, 255, cv2.NORM_MINMAX, cv2.CV_8UC1)
points=cv2.threshold(gray, 230, 255, cv2.THRESH_BINARY )[1]
output = cv2.connectedComponentsWithStats(points, 8, cv2.CV_32S)
centroids = output[3]
x,y=(centroids[1]-centroids[2])
dist=cv2.magnitude(x, y)[0]
print('distance is: ', *dist)
Or this code (find two brightness maximum):
import cv2
img = cv2.imread('HAgbc.jpg')
gray=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
pos1=cv2.minMaxLoc(gray)[3]
cv2.circle(gray, pos1, 30, 0, -1) # masking first spot
pos2=cv2.minMaxLoc(gray)[3]
x=pos1[0]-pos2[0]
y=pos1[1]-pos2[1]
dist=cv2.magnitude(x, y)[0]
print('distance is: ', *dist)
I have pictures of apple slices that have been soaked in an iodine solution. The goal is to segment the apples into individual regions of interest and evaluate the starch level of each one. This is for a school project so my goal is to test different methods of segmentation and objectively find the best solution whether it be a single technique or a combination of multiple techniques.
The problem is that so far I have only come close on one method. That method is using HoughCircles. I had originally planned to use the Watershed method, Morphological operations, or simple thresholding. This plan failed when I couldn't modify any of them to work.
The original images look similar to this, with varying shades of darkness of the apple
I've tried removing the background tray using cv2.inRange with HSV values, but it doesn't work well with darker apples.
This is what the HoughCircles produced on the original image with a grayscale and median blur applied, also with an attempted mask of the tray.
Any advice or direction on where to look next would be greatly appreciated. I can supply the code I'm using if that will help.
Thank you!
EDIT 1 : Adding some code and clarifying the question
Thank you for the responses. My real question is are there any other methods of segmentation that this scenario lends itself well to? I would like to try a couple different methods and compare results on a large set of photos. My next in line to try is using k-means segmentation. Also I'll add some code below to show what I've tried so far.
HSV COLOR FILTERING
import cv2
import numpy as np
# Load image
image = cv2.imread('ApplePic.jpg')
# Set minimum and max HSV values to display
lower = np.array([0, 0, 0])
upper = np.array([105, 200, 255])
# Create HSV Image and threshold into a range.
hsv = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)
mask = cv2.inRange(hsv, lower, upper)
maskedImage = cv2.bitwise_and(image, image, mask=mask)
# Show Image
cv2.imshow('HSV Mask', image)
cv2.waitKey(0)
HoughCircles
# import the necessary packages
import numpy as np
import argparse
import cv2
import os
directory = os.fsencode('Photos\\Sample N 100')
for file in os.listdir(directory):
filename = os.fsdecode(file)
if filename.endswith('.jpg'):
# Load the image
image = cv2.imread('Photos\\Sample N 100\\' + filename)
# Calculate scale
scale_factor = 800 / image.shape[0]
width = int(image.shape[1] * scale_factor)
height = 800
dimension = (width, height)
min_radius = int((width / 10) * .8)
max_radius = int((width / 10) * 1.2)
# Resize image
image = cv2.resize(image, dimension, interpolation=cv2.INTER_AREA)
# Copy Image
output = image.copy()
# Grayscale Image
gray = cv2.medianBlur(cv2.cvtColor(image, cv2.COLOR_BGR2GRAY), 5)
# Detect circles in image
circles = cv2.HoughCircles(gray, cv2.HOUGH_GRADIENT, 1, min_radius * 2, 4, 60, 20, min_radius, max_radius)
# ensure at least some circles were found
if circles is not None:
# convert the (x, y) coordinates and radius of the circles to integers
circles = np.round(circles[0, :]).astype("int")
# loop over the (x, y) coordinates and radius of the circles
for (x, y, r) in circles:
# draw the circle in the output image, then draw a rectangle
# corresponding to the center of the circle
cv2.circle(output, (x, y), r, (0, 255, 0), 4)
cv2.rectangle(output, (x - 5, y - 5), (x + 5, y + 5), (0, 128, 255), -1)
cv2.putText(output, '(' + str(x) + ',' + str(y) + ',' + str(r) + ')', (x, y),
cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, 255)
# show the output image
cv2.imshow("output", np.hstack([image, output, maskedImage]))
cv2.waitKey(0)
continue
else:
continue
An alternative approach to segmenting the apples is to perform Kmeans color segmentation before thresholding then using contour filtering to isolate the apple objects:
Apply Kmeans color segmentation. We load the image, resize smaller using imutils.resize then apply Kmeans color segmentation. Depending on the number of clusters, we can segment the image into the desired number of colors.
Obtain binary image. Next we convert to grayscale, Gaussian blur and Otsu's threshold.
Filter using contour approximation. We filter out non-circle contours and small noise.
Morphological operations. We perform a morph close to fill adjacent contours
Draw minimum enclosing circles using contour area as filter. We find contours and draw the approximated circles. For this we use two sections, one where there was a good threshold and another where we approximate the radius.
Kmeans color quantization with clusters=3 and binary image
Morph close and result
The "good" contours that had the radius automatically calculated using cv2.minEnclosingCircle is highlighted in green while the approximated contours are highlighted in teal. These approximated contours were not segmented well from the thresholding process so we average the "good" contours radius and use that to draw the circle.
Code
import cv2
import numpy as np
import imutils
# Kmeans color segmentation
def kmeans_color_quantization(image, clusters=8, rounds=1):
h, w = image.shape[:2]
samples = np.zeros([h*w,3], dtype=np.float32)
count = 0
for x in range(h):
for y in range(w):
samples[count] = image[x][y]
count += 1
compactness, labels, centers = cv2.kmeans(samples,
clusters,
None,
(cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_MAX_ITER, 10000, 0.0001),
rounds,
cv2.KMEANS_RANDOM_CENTERS)
centers = np.uint8(centers)
res = centers[labels.flatten()]
return res.reshape((image.shape))
# Load image, resize smaller, perform kmeans, grayscale
# Apply Gaussian blur, Otsu's threshold
image = cv2.imread('1.jpg')
image = imutils.resize(image, width=600)
kmeans = kmeans_color_quantization(image, clusters=3)
gray = cv2.cvtColor(kmeans, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (9,9), 0)
thresh = cv2.threshold(blur, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)[1]
# Filter out contours not circle
cnts = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
peri = cv2.arcLength(c, True)
approx = cv2.approxPolyDP(c, 0.04 * peri, True)
if len(approx) < 4:
cv2.drawContours(thresh, [c], -1, 0, -1)
# Morph close
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (5,5))
close = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel, iterations=3)
# Find contours and draw minimum enclosing circles
# using contour area as filter
approximated_radius = 63
cnts = cv2.findContours(close, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
area = cv2.contourArea(c)
x,y,w,h = cv2.boundingRect(c)
# Large circles
if area > 6000 and area < 15000:
((x, y), r) = cv2.minEnclosingCircle(c)
cv2.circle(image, (int(x), int(y)), int(r), (36, 255, 12), 2)
# Small circles
elif area > 1000 and area < 6000:
((x, y), r) = cv2.minEnclosingCircle(c)
cv2.circle(image, (int(x), int(y)), approximated_radius, (200, 255, 12), 2)
cv2.imshow('kmeans', kmeans)
cv2.imshow('thresh', thresh)
cv2.imshow('close', close)
cv2.imshow('image', image)
cv2.waitKey()
I am tasked to build a license plate detection system and my code does not work if the plate has the same colour of the paint of car (background).
Take a look at this picture below.
I have tried a variety of edge detection technique and my findings are they hardly work.
Here is my image processing pipeline:
Extract the gray channel from the image.
Reduce noise with Iterative Bilaterial Filtering
Detect edges with Adaptive Thresholding
Dilate the edges slightly
Locate contours based on some heuristics.
The edge detection part performed miserably around the plate region.
The pipeline works good and I am able to detect license plates if the car is has a different paint colour than the plate.
Code
def rectangleness(hull):
rect = cv2.boundingRect(hull)
rectPoints = np.array([[rect[0], rect[1]],
[rect[0] + rect[2], rect[1]],
[rect[0] + rect[2], rect[1] + rect[3]],
[rect[0], rect[1] + rect[3]]])
intersection_area = cv2.intersectConvexConvex(np.array(rectPoints), hull)[0]
rect_area = cv2.contourArea(rectPoints)
rectangleness = intersection_area/rect_area
return rectangleness
def preprocess(image):
image = imutils.resize(image, 1000)
# Attenuate shadows by using H channel instead of converting to gray directly
imgHSV = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)
_, _, gray = cv2.split(imgHSV)
# Reduce noise while preserve edge with Iterative Bilaterial Filtering
blur = cv2.bilateralFilter(gray, 11, 6, 6)
# Detect edges by thresholding
edge = cv2.adaptiveThreshold(blur, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY_INV, 11, 5)
# Dilate edges, kernel size cannot be too big as some fonts are very closed to the edge of the plates
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (2, 2))
dilated = cv2.dilate(edge, kernel)
# Detect contours
edge, contours, _ = cv2.findContours(dilated, cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
# Loop through contours and select the most probable ones
contours = sorted(contours, key = cv2.contourArea, reverse=True)[:10]
for contour in contours:
perimeter = cv2.arcLength(contour, closed=True)
approximate = cv2.approxPolyDP(contour, 0.02*perimeter, closed=True)
if len(approximate) == 4:
(x, y, w, h) = cv2.boundingRect(approximate)
whRatio = w / h
# Heuristics:
# 1. Width of plate should at least be 2x greater than height
# 2. Width of contour should be more than 5 (eliminate false positive)
# 3. Height must not be too small
# 4. Polygon must resemble a rectangle
if (2.0 < whRatio < 6.0) and (w > 5.0) and (h > 20):
hull = cv2.convexHull(approximate, returnPoints=True)
if rectangleness(hull) > 0.75:
print("X Y {} {}".format(x, y))
print("Height: {}".format(h))
print("Width : {}".format(w))
print("Ratio : {}\n".format(w/h))
cv2.drawContours(image, [approximate], -1, (0, 255, 0), 2)
cv2.imshow("Edge", edge)
cv2.imshow("Frame", image)
cv2.waitKey(0)
cv2.destroyAllWindows()
You can use cv2.morphologyEx for making the plate region become more visible. Next step is to find contours and set reasonable conditions to extract the contour that contains the plate. If you want, you can have a look at this github repository where my friend and I show detailed steps about license plate detection and recognition.
import cv2
import numpy as np
img = cv2.imread("a.png")
imgBlurred = cv2.GaussianBlur(img, (7, 7), 0)
gray = cv2.cvtColor(imgBlurred, cv2.COLOR_BGR2GRAY) # convert to gray
sobelx = cv2.Sobel(gray, cv2.CV_8U, 1, 0, ksize=3) # sobelX to get the vertical edges
ret,threshold_img = cv2.threshold(sobelx, 0, 255, cv2.THRESH_BINARY+cv2.THRESH_OTSU)
morph_img_threshold = threshold_img.copy()
element = cv2.getStructuringElement(shape=cv2.MORPH_RECT, ksize=(22, 3))
cv2.morphologyEx(src=threshold_img, op=cv2.MORPH_CLOSE, kernel=element,
dst=morph_img_threshold)
cv2.imshow("img", img)
cv2.imshow("sobelx", sobelx)
cv2.imshow("morph_img_threshold", morph_img_threshold)
cv2.waitKey()
cv2.destroyAllWindows()
I'm trying to make an OpenCV detect a bed in the image. I am running the usual Grayscale, Blur, Canny, and I've tried Convex Hull. However, since there's quite a number of "noise" which gives extra contours and messes up the object detection. Because of this, I am unable to detect the bed properly.
Here is the input image as well as the Canny Edge Detection result:
As you can see, it's almost there. I have the outline of the bed already, albeit, that the upper right corner has a gap - which is preventing me from detecting a closed rectangle.
Here's the code I'm running:
import cv2
import numpy as np
def contoursConvexHull(contours):
print("contours length = ", len(contours))
print("contours length of first item = ", len(contours[1]))
pts = []
for i in range(0, len(contours)):
for j in range(0, len(contours[i])):
pts.append(contours[i][j])
pts = np.array(pts)
result = cv2.convexHull(pts)
print(len(result))
return result
def auto_canny(image, sigma = 0.35):
# compute the mediam of the single channel pixel intensities
v = np.median(image)
# apply automatic Canny edge detection using the computed median
lower = int(max(0, (1.0 - sigma) * v))
upper = int(min(255, (1.0 + sigma) *v))
edged = cv2.Canny(image, lower, upper)
# return edged image
return edged
# Get our image in color mode (1)
src = cv2.imread("bed_cv.jpg", 1)
# Convert the color from BGR to Gray
srcGray = cv2.cvtColor(src, cv2.COLOR_BGR2GRAY)
# Use Gaussian Blur
srcBlur = cv2.GaussianBlur(srcGray, (3, 3), 0)
# ret is the returned value, otsu is an image
##ret, otsu = cv2.threshold(srcBlur, 0, 255,
## cv2.THRESH_BINARY+cv2.THRESH_OTSU)
# Use canny
##srcCanny = cv2.Canny(srcBlur, ret, ret*2, 3)
srcCanny1 = auto_canny(srcBlur, 0.70)
# im is the output image
# contours is the contour list
# I forgot what hierarchy was
im, contours, hierarchy = cv2.findContours(srcCanny1,
cv2.RETR_TREE,
cv2.CHAIN_APPROX_SIMPLE)
##cv2.drawContours(src, contours, -1, (0, 255, 0), 3)
ConvexHullPoints = contoursConvexHull(contours)
##cv2.polylines(src, [ConvexHullPoints], True, (0, 0, 255), 3)
cv2.imshow("Source", src)
cv2.imshow("Canny1", srcCanny1)
cv2.waitKey(0)
Since the contour of the bed isn't closed, I can't fit a rectangle nor detect the contour with the largest area.
The solution I can think of is to extrapolate the largest possible rectangle using the contour points in the hopes of bridging that small gap, but I'm not too sure how to proceed since the rectangle is incomplete.
Since you haven't provided any other examples, I provide an algorithm working with this case. But bare in mind that you will have to find ways of adapting it to however the light and background changes on other samples.
Since there is a lot of noise and a relatively high dynamic range, I suggest not to use Canny and instead use Adaptive Thresholding and Find Contours on that (it doesn't need edges as an input), that helps with choosing different threshold values for different parts of the image.
My result:
Code:
import cv2
import numpy as np
def clahe(img, clip_limit=2.0, grid_size=(8,8)):
clahe = cv2.createCLAHE(clipLimit=clip_limit, tileGridSize=grid_size)
return clahe.apply(img)
src = cv2.imread("bed.png")
# HSV thresholding to get rid of as much background as possible
hsv = cv2.cvtColor(src.copy(), cv2.COLOR_BGR2HSV)
lower_blue = np.array([0, 0, 120])
upper_blue = np.array([180, 38, 255])
mask = cv2.inRange(hsv, lower_blue, upper_blue)
result = cv2.bitwise_and(src, src, mask=mask)
b, g, r = cv2.split(result)
g = clahe(g, 5, (3, 3))
# Adaptive Thresholding to isolate the bed
img_blur = cv2.blur(g, (9, 9))
img_th = cv2.adaptiveThreshold(img_blur, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C,
cv2.THRESH_BINARY, 51, 2)
im, contours, hierarchy = cv2.findContours(img_th,
cv2.RETR_CCOMP,
cv2.CHAIN_APPROX_SIMPLE)
# Filter the rectangle by choosing only the big ones
# and choose the brightest rectangle as the bed
max_brightness = 0
canvas = src.copy()
for cnt in contours:
rect = cv2.boundingRect(cnt)
x, y, w, h = rect
if w*h > 40000:
mask = np.zeros(src.shape, np.uint8)
mask[y:y+h, x:x+w] = src[y:y+h, x:x+w]
brightness = np.sum(mask)
if brightness > max_brightness:
brightest_rectangle = rect
max_brightness = brightness
cv2.imshow("mask", mask)
cv2.waitKey(0)
x, y, w, h = brightest_rectangle
cv2.rectangle(canvas, (x, y), (x+w, y+h), (0, 255, 0), 1)
cv2.imshow("canvas", canvas)
cv2.imwrite("result.jpg", canvas)
cv2.waitKey(0)