Related
I have a program that allows me to find the disparity map with 2 images from two non-stereocalibrated cameras. The disparity map looks good but when I add a piece of program to get a 3D map via meshlab, I get some scattered points (see photo result_clou.png)
On the other topics, I saw that I had to change the type and divide the disparity map by 16. I tried with a new map called disparity_SGBM2 as follows: disparity_SGBM2 = disparity_SGBM.astype(np.float32) / 16.0
I took a screenshot of the .ply with his error message (see result_disparity_SGBM2.png)
Does anyone have an idea how to unblock me please?
I also joined my python program below (because I can't send a python file) and the images used with the program (clou-l.png and clou-r.png).
import numpy as np
import cv2 as cv
import matplotlib.pyplot as plt
# Read both images and convert to grayscale
img1 = cv.imread('clou-l.png', cv.IMREAD_GRAYSCALE)
img2 = cv.imread('clou-r.png', cv.IMREAD_GRAYSCALE)
# ------------------------------------------------------------
# PREPROCESSING
# Compare unprocessed images
#fig, axes = plt.subplots(1, 2, figsize=(15, 10))
#axes[0].imshow(img1, cmap="gray")
#axes[1].imshow(img2, cmap="gray")
#axes[0].axhline(250)
#axes[1].axhline(250)
#axes[0].axhline(450)
#axes[1].axhline(450)
#plt.suptitle("Original images")
#plt.savefig("original_images.png")
#plt.show()
# 1. Detect keypoints and their descriptors
# Based on: https://docs.opencv.org/master/dc/dc3/tutorial_py_matcher.html
# Initiate SIFT detector
sift = cv.SIFT_create()
# find the keypoints and descriptors with SIFT
kp1, des1 = sift.detectAndCompute(img1, None)
kp2, des2 = sift.detectAndCompute(img2, None)
# Visualize keypoints
imgSift = cv.drawKeypoints(
img1, kp1, None, flags=cv.DRAW_MATCHES_FLAGS_DRAW_RICH_KEYPOINTS)
#cv.imshow("SIFT Keypoints", imgSift)
#cv.imwrite("sift_keypoints.png", imgSift)
# Match keypoints in both images
# Based on: https://docs.opencv.org/master/dc/dc3/tutorial_py_matcher.html
FLANN_INDEX_KDTREE = 1
index_params = dict(algorithm=FLANN_INDEX_KDTREE, trees=5)
search_params = dict(checks=50) # or pass empty dictionary
flann = cv.FlannBasedMatcher(index_params, search_params)
matches = flann.knnMatch(des1, des2, k=2)
# Keep good matches: calculate distinctive image features
# Lowe, D.G. Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision 60, 91–110 (2004). https://doi.org/10.1023/B:VISI.0000029664.99615.94
# https://www.cs.ubc.ca/~lowe/papers/ijcv04.pdf
matchesMask = [[0, 0] for i in range(len(matches))]
good = []
pts1 = []
pts2 = []
for i, (m, n) in enumerate(matches):
if m.distance < 0.7*n.distance:
# Keep this keypoint pair
matchesMask[i] = [1, 0]
good.append(m)
pts2.append(kp2[m.trainIdx].pt)
pts1.append(kp1[m.queryIdx].pt)
# Draw the keypoint matches between both pictures
# Still based on: https://docs.opencv.org/master/dc/dc3/tutorial_py_matcher.html
draw_params = dict(matchColor=(0, 255, 0),
singlePointColor=(255, 0, 0),
matchesMask=matchesMask[300:500],
flags=cv.DrawMatchesFlags_DEFAULT)
keypoint_matches = cv.drawMatchesKnn(
img1, kp1, img2, kp2, matches[300:500], None, **draw_params)
#cv.imshow("Keypoint matches", keypoint_matches)
#cv.imwrite("keypoint_matches.png", keypoint_matches)
# ------------------------------------------------------------
# STEREO RECTIFICATION
# Calculate the fundamental matrix for the cameras
# https://docs.opencv.org/master/da/de9/tutorial_py_epipolar_geometry.html
pts1 = np.int32(pts1)
pts2 = np.int32(pts2)
fundamental_matrix, inliers = cv.findFundamentalMat(pts1, pts2, cv.FM_RANSAC)
# We select only inlier points
pts1 = pts1[inliers.ravel() == 1]
pts2 = pts2[inliers.ravel() == 1]
# Visualize epilines
# Adapted from: https://docs.opencv.org/master/da/de9/tutorial_py_epipolar_geometry.html
def drawlines(img1src, img2src, lines, pts1src, pts2src):
''' img1 - image on which we draw the epilines for the points in img2
lines - corresponding epilines '''
r, c = img1src.shape
img1color = cv.cvtColor(img1src, cv.COLOR_GRAY2BGR)
img2color = cv.cvtColor(img2src, cv.COLOR_GRAY2BGR)
# Edit: use the same random seed so that two images are comparable!
np.random.seed(0)
for r, pt1, pt2 in zip(lines, pts1src, pts2src):
color = tuple(np.random.randint(0, 255, 3).tolist())
x0, y0 = map(int, [0, -r[2]/r[1]])
x1, y1 = map(int, [c, -(r[2]+r[0]*c)/r[1]])
img1color = cv.line(img1color, (x0, y0), (x1, y1), color, 1)
img1color = cv.circle(img1color, tuple(pt1), 5, color, -1)
img2color = cv.circle(img2color, tuple(pt2), 5, color, -1)
return img1color, img2color
# Find epilines corresponding to points in right image (second image) and
# drawing its lines on left image
lines1 = cv.computeCorrespondEpilines(
pts2.reshape(-1, 1, 2), 2, fundamental_matrix)
lines1 = lines1.reshape(-1, 3)
img5, img6 = drawlines(img1, img2, lines1, pts1, pts2)
# Find epilines corresponding to points in left image (first image) and
# drawing its lines on right image
lines2 = cv.computeCorrespondEpilines(
pts1.reshape(-1, 1, 2), 1, fundamental_matrix)
lines2 = lines2.reshape(-1, 3)
img3, img4 = drawlines(img2, img1, lines2, pts2, pts1)
#plt.subplot(121), plt.imshow(img5)
#plt.subplot(122), plt.imshow(img3)
#plt.suptitle("Epilines in both images")
#plt.savefig("epilines.png")
#plt.show()
# Stereo rectification (uncalibrated variant)
# Adapted from: https://stackoverflow.com/a/62607343
h1, w1 = img1.shape
h2, w2 = img2.shape
_, H1, H2 = cv.stereoRectifyUncalibrated(
np.float32(pts1), np.float32(pts2), fundamental_matrix, imgSize=(w1, h1)
)
# Rectify (undistort) the images and save them
# Adapted from: https://stackoverflow.com/a/62607343
img1_rectified = cv.warpPerspective(img1, H1, (w1, h1))
img2_rectified = cv.warpPerspective(img2, H2, (w2, h2))
cv.imwrite("rectified_1.png", img1_rectified)
cv.imwrite("rectified_2.png", img2_rectified)
# Draw the rectified images
#fig, axes = plt.subplots(1, 2, figsize=(15, 10))
#axes[0].imshow(img1_rectified, cmap="gray")
#axes[1].imshow(img2_rectified, cmap="gray")
#axes[0].axhline(250)
#axes[1].axhline(250)
#axes[0].axhline(450)
#axes[1].axhline(450)
#plt.suptitle("Rectified images")
#plt.savefig("rectified_images.png")
#plt.show()
# ------------------------------------------------------------
# CALCULATE DISPARITY (DEPTH MAP)
# Adapted from: https://github.com/opencv/opencv/blob/master/samples/python/stereo_match.py
# and: https://docs.opencv.org/master/dd/d53/tutorial_py_depthmap.html
# StereoSGBM Parameter explanations:
# https://docs.opencv.org/4.5.0/d2/d85/classcv_1_1StereoSGBM.html
# Matched block size. It must be an odd number >=1 . Normally, it should be somewhere in the 3..11 range.
block_size = 11
min_disp = -128
max_disp = 128
# Maximum disparity minus minimum disparity. The value is always greater than zero.
# In the current implementation, this parameter must be divisible by 16.
num_disp = max_disp - min_disp
# Margin in percentage by which the best (minimum) computed cost function value should "win" the second best value to consider the found match correct.
# Normally, a value within the 5-15 range is good enough
uniquenessRatio = 5
# Maximum size of smooth disparity regions to consider their noise speckles and invalidate.
# Set it to 0 to disable speckle filtering. Otherwise, set it somewhere in the 50-200 range.
speckleWindowSize = 200
# Maximum disparity variation within each connected component.
# If you do speckle filtering, set the parameter to a positive value, it will be implicitly multiplied by 16.
# Normally, 1 or 2 is good enough.
speckleRange = 2
disp12MaxDiff = 0
stereo = cv.StereoSGBM_create(
minDisparity=min_disp,
numDisparities=num_disp,
blockSize=block_size,
uniquenessRatio=uniquenessRatio,
speckleWindowSize=speckleWindowSize,
speckleRange=speckleRange,
disp12MaxDiff=disp12MaxDiff,
P1=8 * 1 * block_size * block_size,
P2=32 * 1 * block_size * block_size,
)
disparity_SGBM = stereo.compute(img1_rectified, img2_rectified)
#disparity_SGBM2 = disparity_SGBM.astype(np.float32) / 16.0
#plt.imshow(disparity_SGBM, cmap='plasma')
#plt.colorbar()
#plt.show()
#Normalize the values to a range from 0..255 for a grayscale image
disparity_SGBM = cv.normalize(disparity_SGBM, disparity_SGBM, alpha=255,
beta=0, norm_type=cv.NORM_MINMAX)
disparity_SGBM = np.uint8(disparity_SGBM)
#cv.imshow("Disparity", disparity_SGBM)
#cv.imwrite("disparity_SGBM_norm.png", disparity_SGBM)
#cv.waitKey()
#cv.destroyAllWindows()
# ---------------------------------------------------------------
"""That's the new part of the program for reconstructing the 3D map from the disparity map.
For seeing the 3D result, you need to open the clou.ply folder with Meshlab"""
def create_output(vertices, colors, filename):
colors = colors.reshape(-1, 3)
vertices = np.hstack([vertices.reshape(-1,3), colors])
ply_header = '''ply
format ascii 1.0
element vertex %(vert_num)d
property float x
property float y
property float z
property uchar red
property uchar green
property uchar blue
end_header
'''
with open(filename, 'w') as f:
f.write(ply_header % dict(vert_num=len(vertices)))
np.savetxt(f, vertices, '%f %f %f %d %d %d')
print("\nGenerating the 3D map ...")
h, w = img1.shape[:2]
focal_length = 0.8*w
#Perspective transformation matrix
Q = np.float32([[1, 0, 0, -w/2.0],
[0,-1, 0, h/2.0],
[0, 0, 0, -focal_length],
[0, 0, 1, 0]])
output_file = 'clou' + '.ply'
points_3D = cv.reprojectImageTo3D(disparity_SGBM, Q, handleMissingValues=0)
colors = cv.cvtColor(img1, cv.COLOR_BGR2RGB)
mask_map = disparity_SGBM > disparity_SGBM.min()
output_points = points_3D[mask_map]
output_colors = colors[mask_map]
print("\nCreating the output file ...\n")
create_output(output_points, output_colors, output_file)
clou-l.png
clou-r.png
result_clou.png
result_disparity_SGBM2.png
I think the problem is that you're using very shiny objects, which are typically hard to match in stereo images and photogrammetry. You could try moving the illuminating lights, possibly to a more oblique angle, or fit polarizers over each lens, then illuminate with polarized light. Another technique you can employ is to cover the subject in white powder to create a matt/diffused surface, which can work better.
I've used DMAG (http://3dstereophoto.blogspot.com/2013/04/depth-map-automatic-generator-dmag.html) to produce depth maps (with varying degrees of success) but it can produce intermediate files that firstly show the features it can find, then another step to show which features match between images. I've run your script to produce the rectified images to get an epipolar projection, then I ran those through DMAG. It shows very few matches, Features L Features R Matches. With so few matches you're not going to produce much of a mesh.
I am trying to detect a grainy printed line on a paper with cv2. I need the angle of the line. I dont have much knowledge in image processing and I only need to detect the line. I tried to play with the parameters but the angle is always detected wrong. Could someone help me. This is my code:
import cv2
import numpy as np
import matplotlib.pylab as plt
from matplotlib.pyplot import figure
img = cv2.imread('CamXY1_1.bmp')
crop_img = img[100:800, 300:900]
blur = cv2.GaussianBlur(crop_img, (1,1), 0)
ret,thresh = cv2.threshold(blur,150,255,cv2.THRESH_BINARY)
gray = cv2.cvtColor(thresh,cv2.COLOR_BGR2GRAY)
edges = cv2.Canny(gray, 60, 150)
figure(figsize=(15, 15), dpi=150)
plt.imshow(edges, 'gray')
lines = cv2.HoughLines(edges,1,np.pi/180,200)
for rho,theta in lines[0]:
a = np.cos(theta)
b = np.sin(theta)
x0 = a*rho
y0 = b*rho
x1 = int(x0 + 3000*(-b))
y1 = int(y0 + 3000*(a))
x2 = int(x0 - 3000*(-b))
y2 = int(y0 - 3000*(a))
cv2.line(img,(x1,y1),(x2,y2),(0, 255, 0),2)
imagetobedetected
Here's a possible solution to estimate the line (and its angle) without using the Hough line transform. The idea is to locate the start and ending points of the line using the reduce function. This function can reduce an image to a single column or row. If we reduce the image we can also get the total SUM of all the pixels across the reduced image. Using this info we can estimate the extreme points of the line and calculate its angle. This are the steps:
Resize your image because it is way too big
Get a binary image via adaptive thresholding
Define two extreme regions of the image and crop them
Reduce the ROIs to a column using the SUM mode, which is the sum of all rows
Accumulate the total values above a threshold value
Estimate the starting and ending points of the line
Get the angle of the line
Here's the code:
# imports:
import cv2
import numpy as np
import math
# image path
path = "D://opencvImages//"
fileName = "mmCAb.jpg"
# Reading an image in default mode:
inputImage = cv2.imread(path + fileName)
# Scale your BIG image into a small one:
scalePercent = 0.3
# Calculate the new dimensions
width = int(inputImage.shape[1] * scalePercent)
height = int(inputImage.shape[0] * scalePercent)
newSize = (width, height)
# Resize the image:
inputImage = cv2.resize(inputImage, newSize, None, None, None, cv2.INTER_AREA)
# Deep copy for results:
inputImageCopy = inputImage.copy()
# Convert BGR to grayscale:
grayInput = cv2.cvtColor(inputImage, cv2.COLOR_BGR2GRAY)
# Adaptive Thresholding:
windowSize = 51
windowConstant = 11
binaryImage = cv2.adaptiveThreshold(grayInput, 255, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY_INV, windowSize, windowConstant)
The first step is to get the binary image. Note that I previously downscaled your input because it is too big and we don't need all that info. This is the binary mask:
Now, we don't need most of the image. In fact, since the line is across the whole image, we can only "trim" the first and last column and check out where the white pixels begin. I'll crop a column a little bit wider, though, so we can ensure we have enough data and as less noise as possible. I'll define two Regions of Interest (ROIs) and crop them. Then, I'll reduce each ROI to a column using the SUM mode, this will give me the summation of all intensity across each row. After that, I can accumulate the locations where the sum exceeds a certain threshold and approximate the location of the line, like this:
# Define the regions that will be cropped
# from the original image:
lineWidth = 5
cropPoints = [(0, 0, lineWidth, height), (width-lineWidth, 0, lineWidth, height)]
# Store the line points here:
linePoints = []
# Loop through the crop points and
# crop de ROI:
for p in range(len(cropPoints)):
# Get the ROI:
(x,y,w,h) = cropPoints[p]
# Crop the ROI:
imageROI = binaryImage[y:y+h, x:x+w]
# Reduce the ROI to a n row x 1 columns matrix:
reducedImg = cv2.reduce(imageROI, 1, cv2.REDUCE_SUM, dtype=cv2.CV_32S)
# Get the height (or lenght) of the arry:
reducedHeight = reducedImg.shape[0]
# Define a threshold and accumulate
# the coordinate of the points:
threshValue = 100
pointSum = 0
pointCount = 0
for i in range(reducedHeight):
currentValue = reducedImg[i]
if currentValue > threshValue:
pointSum = pointSum + i
pointCount = pointCount + 1
# Get average coordinate of the line:
y = int(accX / pixelCount)
# Store in list:
linePoints.append((x, y))
The red rectangles show the regions I cropped from the input image:
Note that I've stored both points in the linePoints list. Let's check out our approximation by drawing a line that connects both points:
# Get the two points:
p0 = linePoints[0]
p1 = linePoints[1]
# Draw the line:
cv2.line(inputImageCopy, (p0[0], p0[1]), (p1[0], p1[1]), (255, 0, 0), 1)
cv2.imshow("Line", inputImageCopy)
cv2.waitKey(0)
Which yields:
Not bad, huh? Now that we have both points, we can estimate the angle of this line:
# Get angle:
adjacentSide = p1[0] - p0[0]
oppositeSide = p0[1] - p1[1]
# Compute the angle alpha:
alpha = math.degrees(math.atan(oppositeSide / adjacentSide))
print("Angle: "+str(alpha))
This prints:
Angle: 0.534210901840831
Is there a Contour Method to detect arrows in Python CV? Maybe with Contours, Shapes, and Vertices.
# find contours in the thresholded image and initialize the shape detector
cnts = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = imutils.grab_contours(cnts)
perimeterValue = cv2.arcLength(cnts , True)
vertices = cv2.approxPolyDP(cnts , 0.04 * perimeterValue, True)
Perhaps we can look at tips of the contours, and also detect triangles?
Hopefully it can detect arrows among different objects, among squares, rectangles, and circles. (otherwise, will have to use machine learning).
Also nice to get these three results if possible (arrow length, thickness, directionAngle)
This question recommends template matching, and doesn't specify any code base. Looking for something workable that can be code created
how to detect arrows using open cv python?
If PythonOpenCV doesn't have capability, open to utilizing another library.
The solution you are asking for is too complex to be solved by one function or particular algorithm. In fact, the problem could be broken down into smaller steps, each with their own algorithms and solutions. Instead of offering you a free, complete, copy-paste solution, I'll give you a general outline of the problem and post part of the solution I'd design. These are the steps I propose:
Identify and extract all the arrow blobs from the image, and process them one by one.
Try to find the end-points of the arrow. That is end and starting point (or "tail" and "tip")
Undo the rotation, so you have straightened arrows always, no matter their angle.
After this, the arrows will always point to one direction. This normalization let's itself easily for classification.
After processing, you can pass the image to a Knn classifier, a Support Vector Machine or even (if you are willing to call the "big guns" on this problem) a CNN (in which case, you probably won't need to undo the rotation - as long as you have enough training samples). You don't even have to compute features, as passing the raw image to a SVM would be probably enough. However, you need more than one training sample for each arrow class.
Alright, let's see. First, let's extract each arrow from the input. This is done using cv2.findCountours, this part is very straightforward:
# Imports:
import cv2
import math
import numpy as np
# image path
path = "D://opencvImages//"
fileName = "arrows.png"
# Reading an image in default mode:
inputImage = cv2.imread(path + fileName)
# Grayscale conversion:
grayscaleImage = cv2.cvtColor(inputImage, cv2.COLOR_BGR2GRAY)
grayscaleImage = 255 - grayscaleImage
# Find the big contours/blobs on the binary image:
contours, hierarchy = cv2.findContours(grayscaleImage, cv2.RETR_CCOMP, cv2.CHAIN_APPROX_SIMPLE)
Now, let's check out the contours and process them one by one. Let's compute a (non-rotated) bounding box of the arrow and crop that sub-image. Now, note that some noise could come up. In which case, we won't be processing that blob. I apply an area filter to bypass blobs of small area. Like this:
# Process each contour 1-1:
for i, c in enumerate(contours):
# Approximate the contour to a polygon:
contoursPoly = cv2.approxPolyDP(c, 3, True)
# Convert the polygon to a bounding rectangle:
boundRect = cv2.boundingRect(contoursPoly)
# Get the bounding rect's data:
rectX = boundRect[0]
rectY = boundRect[1]
rectWidth = boundRect[2]
rectHeight = boundRect[3]
# Get the rect's area:
rectArea = rectWidth * rectHeight
minBlobArea = 100
We set a minBlobArea and process that contour. Crop the image if the contour is above that area threshold value:
# Check if blob is above min area:
if rectArea > minBlobArea:
# Crop the roi:
croppedImg = grayscaleImage[rectY:rectY + rectHeight, rectX:rectX + rectWidth]
# Extend the borders for the skeleton:
borderSize = 5
croppedImg = cv2.copyMakeBorder(croppedImg, borderSize, borderSize, borderSize, borderSize, cv2.BORDER_CONSTANT)
# Store a deep copy of the crop for results:
grayscaleImageCopy = cv2.cvtColor(croppedImg, cv2.COLOR_GRAY2BGR)
# Compute the skeleton:
skeleton = cv2.ximgproc.thinning(croppedImg, None, 1)
There are some couple of things going on here. After I crop the ROI of the current arrow, I extend borders on that image. I store a deep-copy of this image for further processing and, lastly, I compute the skeleton. The border-extending is done prior to skeletonizing because the algorithm produces artifacts if the contour is too close to the image limits. Padding the image in all directions prevents these artifacts. The skeleton is needed for the way I'm finding ending and starting points of the arrow. More of this latter, this is the first arrow cropped and padded:
This is the skeleton:
Note that the "thickness" of the contour is normalized to 1 pixel. That's cool, because that's what I need for the following processing step: Finding start/ending points. This is done by applying a convolution with a kernel designed to identify one-pixel wide end-points on a binary image. Refer to this post for the specifics. We will prepare the kernel and use cv2.filter2d to get the convolution:
# Threshold the image so that white pixels get a value of 0 and
# black pixels a value of 10:
_, binaryImage = cv2.threshold(skeleton, 128, 10, cv2.THRESH_BINARY)
# Set the end-points kernel:
h = np.array([[1, 1, 1],
[1, 10, 1],
[1, 1, 1]])
# Convolve the image with the kernel:
imgFiltered = cv2.filter2D(binaryImage, -1, h)
# Extract only the end-points pixels, those with
# an intensity value of 110:
binaryImage = np.where(imgFiltered == 110, 255, 0)
# The above operation converted the image to 32-bit float,
# convert back to 8-bit uint
binaryImage = binaryImage.astype(np.uint8)
After the convolution, all end-points have a value of 110. Setting these pixels to 255, while the rest are set to black, yields the following image (after proper conversion):
Those tiny pixels correspond to the "tail" and "tip" of the arrow. Notice there's more than one point per "Arrow section". This is because the end-points of the arrow do not perfectly end in one pixel. In the case of the tip, for example, there will be more end-points than in the tail. This is a characteristic we will exploit latter. Now, pay attention to this. There are multiple end-points but we only need an starting point and an ending point. I'm gonna use K-Means to group the points in two clusters.
Using K-means will also let me identify which end-points belong to the tail and which to the tip, so I'll always know the direction of the arrow. Let's roll:
# Find the X, Y location of all the end-points
# pixels:
Y, X = binaryImage.nonzero()
# Check if I got points on my arrays:
if len(X) > 0 or len(Y) > 0:
# Reshape the arrays for K-means
Y = Y.reshape(-1,1)
X = X.reshape(-1,1)
Z = np.hstack((X, Y))
# K-means operates on 32-bit float data:
floatPoints = np.float32(Z)
# Set the convergence criteria and call K-means:
criteria = (cv2.TERM_CRITERIA_EPS + cv2.TERM_CRITERIA_MAX_ITER, 10, 1.0)
_, label, center = cv2.kmeans(floatPoints, 2, None, criteria, 10, cv2.KMEANS_RANDOM_CENTERS)
Be careful with the data types. If I print the label and center matrices, I get this (for the first arrow):
Center:
[[ 6. 102. ]
[104. 20.5]]
Labels:
[[1]
[1]
[0]]
center tells me the center (x,y) of each cluster – That is the two points I was originally looking for. label tells me on which cluster the original data falls in. As you see, there were originally 3 points. 2 of those points (the points belonging to the tip of the arrow) area assigned to cluster 1, while the remaining end-point (the arrow tail) is assigned to cluster 0. In the centers matrix the centers are ordered by cluster number. That is – first center is that one of cluster 0, while second cluster is the center of cluster 1. Using this info I can easily look for the cluster that groups the majority of points - that will be the tip of the arrow, while the remaining will be the tail:
# Set the cluster count, find the points belonging
# to cluster 0 and cluster 1:
cluster1Count = np.count_nonzero(label)
cluster0Count = np.shape(label)[0] - cluster1Count
# Look for the cluster of max number of points
# That cluster will be the tip of the arrow:
maxCluster = 0
if cluster1Count > cluster0Count:
maxCluster = 1
# Check out the centers of each cluster:
matRows, matCols = center.shape
# We need at least 2 points for this operation:
if matCols >= 2:
# Store the ordered end-points here:
orderedPoints = [None] * 2
# Let's identify and draw the two end-points
# of the arrow:
for b in range(matRows):
# Get cluster center:
pointX = int(center[b][0])
pointY = int(center[b][1])
# Get the "tip"
if b == maxCluster:
color = (0, 0, 255)
orderedPoints[0] = (pointX, pointY)
# Get the "tail"
else:
color = (255, 0, 0)
orderedPoints[1] = (pointX, pointY)
# Draw it:
cv2.circle(grayscaleImageCopy, (pointX, pointY), 3, color, -1)
cv2.imshow("End Points", grayscaleImageCopy)
cv2.waitKey(0)
This is the result; the tip of the end-point of the arrow will always be in red and the end-point for the tail in blue:
Now, we know the direction of the arrow, let's compute the angle. I will measure this angle from 0 to 360. The angle will always be the one between the horizon line and the tip. So, we manually compute the angle:
# Store the tip and tail points:
p0x = orderedPoints[1][0]
p0y = orderedPoints[1][1]
p1x = orderedPoints[0][0]
p1y = orderedPoints[0][1]
# Compute the sides of the triangle:
adjacentSide = p1x - p0x
oppositeSide = p0y - p1y
# Compute the angle alpha:
alpha = math.degrees(math.atan(oppositeSide / adjacentSide))
# Adjust angle to be in [0,360]:
if adjacentSide < 0 < oppositeSide:
alpha = 180 + alpha
else:
if adjacentSide < 0 and oppositeSide < 0:
alpha = 270 + alpha
else:
if adjacentSide > 0 > oppositeSide:
alpha = 360 + alpha
Now you have the angle, and this angle is always measured between the same references. That's cool, we can undo the rotation of the original image like follows:
# Deep copy for rotation (if needed):
rotatedImg = croppedImg.copy()
# Undo rotation while padding output image:
rotatedImg = rotateBound(rotatedImg, alpha)
cv2. imshow("rotatedImg", rotatedImg)
cv2.waitKey(0)
else:
print( "K-Means did not return enough points, skipping..." )
else:
print( "Did not find enough end points on image, skipping..." )
This yields the following result:
The arrow will always point top the right regardless of its original angle. Use this as normalization for a batch of training images, if you want to classify each arrow in its own class.
Now, you noticed that I used a function to rotate the image: rotateBound. This function is taken from here. This functions correctly pads the image after rotation, so you do not end up with a rotated image that is cropped incorrectly.
This is the definition and implementation of rotateBound:
def rotateBound(image, angle):
# grab the dimensions of the image and then determine the
# center
(h, w) = image.shape[:2]
(cX, cY) = (w // 2, h // 2)
# grab the rotation matrix (applying the negative of the
# angle to rotate clockwise), then grab the sine and cosine
# (i.e., the rotation components of the matrix)
M = cv2.getRotationMatrix2D((cX, cY), -angle, 1.0)
cos = np.abs(M[0, 0])
sin = np.abs(M[0, 1])
# compute the new bounding dimensions of the image
nW = int((h * sin) + (w * cos))
nH = int((h * cos) + (w * sin))
# adjust the rotation matrix to take into account translation
M[0, 2] += (nW / 2) - cX
M[1, 2] += (nH / 2) - cY
# perform the actual rotation and return the image
return cv2.warpAffine(image, M, (nW, nH))
These are results for the rest of your arrows. The tip (always in red), the tail (always in blue) and their "projective normalization" - always pointing to the right:
What remains is collect samples of your different arrow classes, set up a classifier, train it with your samples and test it with the straightened image coming from the last processing block we examined.
Some remarks: Some arrows, like the one that is not filled, failed the end-point identification part, thus, not yielding enough points for clustering. That arrow is by-passed by the algorithm. The problem is tougher than initially though, right? I recommend doing some research on the topic, because not matter how "easy" the task seems, at the end, it will be performed by an automated "smart" system. And those systems aren't really that smart at the end of the day.
Here is the workflow I put together that would make this work:
Import the necessary libraries:
import cv2
import numpy as np
Define a function that will take in an image, and process it into something that can allow python to more easily find the necessary contours of each shape. The values can be adjusted to better suit your needs:
def preprocess(img):
img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
img_blur = cv2.GaussianBlur(img_gray, (5, 5), 1)
img_canny = cv2.Canny(img_blur, 50, 50)
kernel = np.ones((3, 3))
img_dilate = cv2.dilate(img_canny, kernel, iterations=2)
img_erode = cv2.erode(img_dilate, kernel, iterations=1)
return img_erode
Define a function that will take in two lists; an approximate contour of a shape, points, and the indices of the convex hull of that contour, convex_hull. For the below function, you must make sure that the length of the points list is exactly 2 units greater than the length of the convex_hull list before calling the function. The reasoning is that optimally, the arrow should have exactly 2 more points that aren't present in the convex hull of the arrow.
def find_tip(points, convex_hull):
In the find_tip function, define a list of the indices of the points array where the values are not present in the convex_hull array:
length = len(points)
indices = np.setdiff1d(range(length), convex_hull)
In order to find the tip of the arrow, given we have the approximate outline of the arrow as points and the indices of the two points that are concave to the arrow, indices, we can find the tip by either subtracting 2 from the first index in the indices list, or by adding 2 to the first index of the indices list. See the below examples for reference:
In order to know whether you should subtract 2 from the first element of the indices list, or add 2, you'll need to do the exact opposite to the second (which is the last) element of the indices list; if the resulting two indices returns the same value from the points list, then you found the tip of the arrow. I used a for loop that loops through numbers 0 and 1. The first iteration will add 2 to the second element of the indices list: j = indices[i] + 2, and subtract 2 from the first element of the indices list: indices[i - 1] - 2:
for i in range(2):
j = indices[i] + 2
if j > length - 1:
j = length - j
if np.all(points[j] == points[indices[i - 1] - 2]):
return tuple(points[j])
This part:
if j > length - 1:
j = length - j
is there for cases like this:
where if you try adding 2 to the index 5, you will get an IndexError. So if, say j becomes 7 from the j = indices[i] + 2, the above condition will convert j to len(points) - j.
Read the image and get its contours, utilizing the preprocess function defined earlier before passing it into the cv2.findContours method:
img = cv2.imread("arrows.png")
contours, hierarchy = cv2.findContours(preprocess(img), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
Loop through the contours, and find the approximate contour and convex hull of each shape:
for cnt in contours:
peri = cv2.arcLength(cnt, True)
approx = cv2.approxPolyDP(cnt, 0.025 * peri, True)
hull = cv2.convexHull(approx, returnPoints=False)
sides = len(hull)
If the number of sides of the convex hull is 4 or 5 (the extra side in case the arrow has a flat bottom), and if the shape of the arrow has exactly two more points that are not present in the convex hull, find the tip of the arrow:
if 6 > sides > 3 and sides + 2 == len(approx):
arrow_tip = find_tip(approx[:,0,:], hull.squeeze())
If there is indeed a tip, then congratulation! You found a decent arrow! Now the arrow can be highlighted, and a circle can be drawn at the location of the tip of the arrow:
if arrow_tip:
cv2.drawContours(img, [cnt], -1, (0, 255, 0), 3)
cv2.circle(img, arrow_tip, 3, (0, 0, 255), cv2.FILLED)
Finally, show the image:
cv2.imshow("Image", img)
cv2.waitKey(0)
Altogether:
import cv2
import numpy as np
def preprocess(img):
img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
img_blur = cv2.GaussianBlur(img_gray, (5, 5), 1)
img_canny = cv2.Canny(img_blur, 50, 50)
kernel = np.ones((3, 3))
img_dilate = cv2.dilate(img_canny, kernel, iterations=2)
img_erode = cv2.erode(img_dilate, kernel, iterations=1)
return img_erode
def find_tip(points, convex_hull):
length = len(points)
indices = np.setdiff1d(range(length), convex_hull)
for i in range(2):
j = indices[i] + 2
if j > length - 1:
j = length - j
if np.all(points[j] == points[indices[i - 1] - 2]):
return tuple(points[j])
img = cv2.imread("arrows.png")
contours, hierarchy = cv2.findContours(preprocess(img), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
for cnt in contours:
peri = cv2.arcLength(cnt, True)
approx = cv2.approxPolyDP(cnt, 0.025 * peri, True)
hull = cv2.convexHull(approx, returnPoints=False)
sides = len(hull)
if 6 > sides > 3 and sides + 2 == len(approx):
arrow_tip = find_tip(approx[:,0,:], hull.squeeze())
if arrow_tip:
cv2.drawContours(img, [cnt], -1, (0, 255, 0), 3)
cv2.circle(img, arrow_tip, 3, (0, 0, 255), cv2.FILLED)
cv2.imshow("Image", img)
cv2.waitKey(0)
Original image:
Python program output:
Here is an approach with cv2.connectedComponentsWithStats. After extracting every arrow individually, I am getting the farthest points on the arrow. The distance between these points give me (more or less) the length of the arrow. Also, I am calculating the angle of the arrow by using these two points, i.e., slope between two points. Finally, in order to find the thickness, I am drawing a straight line between these points. And, I am calculating the shortest distance of each pixel of the arrow to the line. The most repeated distance value should give me the thickness of arrow.
The algorithm is not perfect, as it is. Especially, if the arrow is tilted. But, I feel like it is a good starting point and you can improve it.
import cv2
import numpy as np
import matplotlib.pyplot as plt
from scipy.spatial import distance
import math
img = cv2.imread('arrows.png',0)
_,img = cv2.threshold(img,10,255,cv2.THRESH_BINARY_INV)
labels, stats = cv2.connectedComponentsWithStats(img, 8)[1:3]
for label in np.unique(labels)[1:]:
arrow = labels==label
indices = np.transpose(np.nonzero(arrow)) #y,x
dist = distance.cdist(indices, indices, 'euclidean')
far_points_index = np.unravel_index(np.argmax(dist), dist.shape) #y,x
far_point_1 = indices[far_points_index[0],:] # y,x
far_point_2 = indices[far_points_index[1],:] # y,x
### Slope
arrow_slope = (far_point_2[0]-far_point_1[0])/(far_point_2[1]-far_point_1[1])
arrow_angle = math.degrees(math.atan(arrow_slope))
### Length
arrow_length = distance.cdist(far_point_1.reshape(1,2), far_point_2.reshape(1,2), 'euclidean')[0][0]
### Thickness
x = np.linspace(far_point_1[1], far_point_2[1], 20)
y = np.linspace(far_point_1[0], far_point_2[0], 20)
line = np.array([[yy,xx] for yy,xx in zip(y,x)])
thickness_dist = np.amin(distance.cdist(line, indices, 'euclidean'),axis=0).flatten()
n, bins, patches = plt.hist(thickness_dist,bins=150)
thickness = 2*bins[np.argmax(n)]
print(f"Thickness: {thickness}")
print(f"Angle: {arrow_angle}")
print(f"Length: {arrow_length}\n")
plt.figure()
plt.imshow(arrow,cmap='gray')
plt.scatter(far_point_1[1],far_point_1[0],c='r',s=10)
plt.scatter(far_point_2[1],far_point_2[0],c='r',s=10)
plt.scatter(line[:,1],line[:,0],c='b',s=10)
plt.show()
Thickness: 4.309328382835436
Angle: 58.94059117029002
Length: 102.7277956543408
Thickness: 7.851144897915465
Angle: -3.366460663429801
Length: 187.32325002519042
Thickness: 2.246710258748367
Angle: 55.51004336926862
Length: 158.93709447451215
Thickness: 25.060450615293227
Angle: -37.184706453233126
Length: 145.60219778561037
As your main concern is to filter out arrows from different shapes. I have implemented a method using convexityDefects. you can read more about convexity defects here.
Also, I have added more arrow inside other shapes to demonstrate the robustness of the method.
Updated Image
Method to filter arrows from image using convexity defects.
def get_filter_arrow_image(threslold_image):
blank_image = np.zeros_like(threslold_image)
# dilate image to remove self-intersections error
kernel_dilate = cv2.getStructuringElement(cv2.MORPH_RECT, (2, 2))
threslold_image = cv2.dilate(threslold_image, kernel_dilate, iterations=1)
contours, hierarchy = cv2.findContours(threslold_image, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
if hierarchy is not None:
threshold_distnace = 1000
for cnt in contours:
hull = cv2.convexHull(cnt, returnPoints=False)
defects = cv2.convexityDefects(cnt, hull)
if defects is not None:
for i in range(defects.shape[0]):
start_index, end_index, farthest_index, distance = defects[i, 0]
# you can add more filteration based on this start, end and far point
# start = tuple(cnt[start_index][0])
# end = tuple(cnt[end_index][0])
# far = tuple(cnt[farthest_index][0])
if distance > threshold_distnace:
cv2.drawContours(blank_image, [cnt], -1, 255, -1)
return blank_image
else:
return None
filter arrow image
I have added methods for the angle and length of the arrow, If this isn't good enough, let me know; there are more complicated methods for angle detection based on 3 coordinate points.
def get_max_distace_point(cnt):
max_distance = 0
max_points = None
for [[x1, y1]] in cnt:
for [[x2, y2]] in cnt:
distance = get_length((x1, y1), (x2, y2))
if distance > max_distance:
max_distance = distance
max_points = [(x1, y1), (x2, y2)]
return max_points
def angle_beween_points(a, b):
arrow_slope = (a[0] - b[0]) / (a[1] - b[1])
arrow_angle = math.degrees(math.atan(arrow_slope))
return arrow_angle
def get_arrow_info(arrow_image):
arrow_info_image = cv2.cvtColor(arrow_image.copy(), cv2.COLOR_GRAY2BGR)
contours, hierarchy = cv2.findContours(arrow_image, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
arrow_info = []
if hierarchy is not None:
for cnt in contours:
# draw single arrow on blank image
blank_image = np.zeros_like(arrow_image)
cv2.drawContours(blank_image, [cnt], -1, 255, -1)
point1, point2 = get_max_distace_point(cnt)
angle = angle_beween_points(point1, point2)
lenght = get_length(point1, point2)
cv2.line(arrow_info_image, point1, point2, (0, 255, 255), 1)
cv2.circle(arrow_info_image, point1, 2, (255, 0, 0), 3)
cv2.circle(arrow_info_image, point2, 2, (255, 0, 0), 3)
cv2.putText(arrow_info_image, "angle : {0:0.2f}".format(angle),
point2, cv2.FONT_HERSHEY_PLAIN, 0.8, (0, 0, 255), 1)
cv2.putText(arrow_info_image, "lenght : {0:0.2f}".format(lenght),
(point2[0], point2[1]+20), cv2.FONT_HERSHEY_PLAIN, 0.8, (0, 0, 255), 1)
return arrow_info_image, arrow_info
else:
return None, None
angle and length image
CODE
import math
import cv2
import numpy as np
def get_filter_arrow_image(threslold_image):
blank_image = np.zeros_like(threslold_image)
# dilate image to remove self-intersections error
kernel_dilate = cv2.getStructuringElement(cv2.MORPH_RECT, (2, 2))
threslold_image = cv2.dilate(threslold_image, kernel_dilate, iterations=1)
contours, hierarchy = cv2.findContours(threslold_image, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
if hierarchy is not None:
threshold_distnace = 1000
for cnt in contours:
hull = cv2.convexHull(cnt, returnPoints=False)
defects = cv2.convexityDefects(cnt, hull)
if defects is not None:
for i in range(defects.shape[0]):
start_index, end_index, farthest_index, distance = defects[i, 0]
# you can add more filteration based on this start, end and far point
# start = tuple(cnt[start_index][0])
# end = tuple(cnt[end_index][0])
# far = tuple(cnt[farthest_index][0])
if distance > threshold_distnace:
cv2.drawContours(blank_image, [cnt], -1, 255, -1)
return blank_image
else:
return None
def get_length(p1, p2):
line_length = ((p1[0] - p2[0]) ** 2 + (p1[1] - p2[1]) ** 2) ** 0.5
return line_length
def get_max_distace_point(cnt):
max_distance = 0
max_points = None
for [[x1, y1]] in cnt:
for [[x2, y2]] in cnt:
distance = get_length((x1, y1), (x2, y2))
if distance > max_distance:
max_distance = distance
max_points = [(x1, y1), (x2, y2)]
return max_points
def angle_beween_points(a, b):
arrow_slope = (a[0] - b[0]) / (a[1] - b[1])
arrow_angle = math.degrees(math.atan(arrow_slope))
return arrow_angle
def get_arrow_info(arrow_image):
arrow_info_image = cv2.cvtColor(arrow_image.copy(), cv2.COLOR_GRAY2BGR)
contours, hierarchy = cv2.findContours(arrow_image, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
arrow_info = []
if hierarchy is not None:
for cnt in contours:
# draw single arrow on blank image
blank_image = np.zeros_like(arrow_image)
cv2.drawContours(blank_image, [cnt], -1, 255, -1)
point1, point2 = get_max_distace_point(cnt)
angle = angle_beween_points(point1, point2)
lenght = get_length(point1, point2)
cv2.line(arrow_info_image, point1, point2, (0, 255, 255), 1)
cv2.circle(arrow_info_image, point1, 2, (255, 0, 0), 3)
cv2.circle(arrow_info_image, point2, 2, (255, 0, 0), 3)
cv2.putText(arrow_info_image, "angle : {0:0.2f}".format(angle),
point2, cv2.FONT_HERSHEY_PLAIN, 0.8, (0, 0, 255), 1)
cv2.putText(arrow_info_image, "lenght : {0:0.2f}".format(lenght),
(point2[0], point2[1] + 20), cv2.FONT_HERSHEY_PLAIN, 0.8, (0, 0, 255), 1)
return arrow_info_image, arrow_info
else:
return None, None
if __name__ == "__main__":
image = cv2.imread("image2.png")
gray_image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
_, thresh_image = cv2.threshold(gray_image, 100, 255, cv2.THRESH_BINARY_INV)
cv2.imshow("thresh_image", thresh_image)
arrow_image = get_filter_arrow_image(thresh_image)
if arrow_image is not None:
cv2.imshow("arrow_image", arrow_image)
cv2.imwrite("arrow_image.png", arrow_image)
arrow_info_image, arrow_info = get_arrow_info(arrow_image)
cv2.imshow("arrow_info_image", arrow_info_image)
cv2.imwrite("arrow_info_image.png", arrow_info_image)
cv2.waitKey(0)
cv2.destroyAllWindows()
convexity defects on a thin arrow.
Blue point - start point of defect
Green point - far point if defect
Red point - end point of defect
yellow line = defect line from start point to end point.
image
defect-1
defect-2
and so on...
..
I am trying to detect a white Object on a black/white road to let an autonmous RC car drive around it. And i am detecting everything but the white box on the road.
What I tried can be seen in my code Example
#input= one video stream frame 320x240
frame = copy.deepcopy(input)
grayFrame = cv2.cvtColor(frame,cv2.COLOR_BGR2GRAY)
threshGray = cv2.adaptiveThreshold(
grayFrame,
255,
cv2.ADAPTIVE_THRESH_MEAN_C,
cv2.THRESH_BINARY,
blockSize=123,
C=-19,
)
contours,_ = cv2.findContours(threshGray, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
for cnt in contours:
#some filtering needs to be done
#
#after filtering append contour
filteredContours.append(cnt)
cv2.rectangle(frame, (x, y), (x + w, y + h), (3, 244, 244), 1)
cv2.drawContours(frame, filteredContours, -1, (255, 0, 255),1 )
cv2.imshow("with contours", frame)
cv2.imshow("adaptiveThreshhold", threshGray)
cv2.imshow("input", input)
I'm looking for a way to draw a bounding box around the obstacle.
Problem is I dont know how to extract this box from the rest.
It is probably because the contour of the box and the lines on the right are connected and thats why the bounding box is that big. Would be great if someone knows a way to do that.
Click here to see the Result
First: Input image
Second: after adaptiveThreshold
third: with contours(pink) and bounding boxes(yellow)
At this point in time, you got several candidates of white color value.
You need to add code in to the #some filtering needs to be done to rid candidate list of NOT bounding box you want to find.
I suggest you to compare your candidate list with square box as bigger as enough.
Because all of contours without BOX(that you want to find on the road) do not satisfy condition about square box as I mentioned above.
I think what you are looking for is triangular masking, as seen in the input image you have lane marking as well. Did try using a lane detector with this all the areas out of lane can be masked and only the spaces in lane can be processed.
Below I have tried to use Lane detector using HoughLinesP and added Contours as well. Try to use this, I did not test this code but I see no issues.
#! /usr/bin/env python 3
"""
Lane detector using the Hog transform method
"""
import cv2 as cv
import numpy as np
# import matplotlib.pyplot as plt
import random as rng
rng.seed(369)
def do_canny(frame):
# Converts frame to grayscale because we only need the luminance channel for detecting edges - less computationally expensive
gray = cv.cvtColor(frame, cv.COLOR_RGB2GRAY)
# Applies a 5x5 gaussian blur with deviation of 0 to frame - not mandatory since Canny will do this for us
blur = cv.GaussianBlur(gray, (5, 5), 0)
# Applies Canny edge detector with minVal of 50 and maxVal of 150
canny = cv.Canny(blur, 50, 150)
return canny
def do_segment(frame):
# Since an image is a multi-directional array containing the relative intensities of each pixel in the image, we can use frame.shape to return a tuple: [number of rows, number of columns, number of channels] of the dimensions of the frame
# frame.shape[0] give us the number of rows of pixels the frame has. Since height begins from 0 at the top, the y-coordinate of the bottom of the frame is its height
height = frame.shape[0]
# Creates a triangular polygon for the mask defined by three (x, y) coordinates
polygons = np.array([
[(0, height), (800, height), (380, 290)]
])
# Creates an image filled with zero intensities with the same dimensions as the frame
mask = np.zeros_like(frame)
# Allows the mask to be filled with values of 1 and the other areas to be filled with values of 0
cv.fillPoly(mask, polygons, 255)
# A bitwise and operation between the mask and frame keeps only the triangular area of the frame
segment = cv.bitwise_and(frame, mask)
return segment
def calculate_lines(frame, lines):
# Empty arrays to store the coordinates of the left and right lines
left = []
right = []
# Loops through every detected line
for line in lines:
# Reshapes line from 2D array to 1D array
x1, y1, x2, y2 = line.reshape(4)
# Fits a linear polynomial to the x and y coordinates and returns a vector of coefficients which describe the slope and y-intercept
parameters = np.polyfit((x1, x2), (y1, y2), 1)
slope = parameters[0]
y_intercept = parameters[1]
# If slope is negative, the line is to the left of the lane, and otherwise, the line is to the right of the lane
if slope < 0:
left.append((slope, y_intercept))
else:
right.append((slope, y_intercept))
# Averages out all the values for left and right into a single slope and y-intercept value for each line
left_avg = np.average(left, axis = 0)
right_avg = np.average(right, axis = 0)
# Calculates the x1, y1, x2, y2 coordinates for the left and right lines
left_line = calculate_coordinates(frame, left_avg)
right_line = calculate_coordinates(frame, right_avg)
return np.array([left_line, right_line])
def calculate_coordinates(frame, parameters):
slope, intercept = parameters
# Sets initial y-coordinate as height from top down (bottom of the frame)
y1 = frame.shape[0]
# Sets final y-coordinate as 150 above the bottom of the frame
y2 = int(y1 - 150)
# Sets initial x-coordinate as (y1 - b) / m since y1 = mx1 + b
x1 = int((y1 - intercept) / slope)
# Sets final x-coordinate as (y2 - b) / m since y2 = mx2 + b
x2 = int((y2 - intercept) / slope)
return np.array([x1, y1, x2, y2])
def visualize_lines(frame, lines):
# Creates an image filled with zero intensities with the same dimensions as the frame
lines_visualize = np.zeros_like(frame)
# Checks if any lines are detected
if lines is not None:
for x1, y1, x2, y2 in lines:
# Draws lines between two coordinates with green color and 5 thickness
cv.line(lines_visualize, (x1, y1), (x2, y2), (0, 255, 0), 5)
return lines_visualize
# The video feed is read in as a VideoCapture object
cap = cv.VideoCapture(1)
while (cap.isOpened()):
# ret = a boolean return value from getting the frame, frame = the current frame being projected in the video
ret, frame = cap.read()
canny = do_canny(frame)
cv.imshow("canny", canny)
# plt.imshow(frame)
# plt.show()
segment = do_segment(canny)
hough = cv.HoughLinesP(segment, 2, np.pi / 180, 100, np.array([]), minLineLength = 100, maxLineGap = 50)
# Averages multiple detected lines from hough into one line for left border of lane and one line for right border of lane
lines = calculate_lines(frame, hough)
# Visualizes the lines
lines_visualize = visualize_lines(frame, lines)
cv.imshow("hough", lines_visualize)
# Overlays lines on frame by taking their weighted sums and adding an arbitrary scalar value of 1 as the gamma argument
output = cv.addWeighted(frame, 0.9, lines_visualize, 1, 1)
contours, _ = cv.findContours(output, cv.RETR_TREE, cv.CHAIN_APPROX_SIMPLE)
contours_poly = [None]*len(contours)
boundRect = [None]*len(contours)
centers = [None]*len(contours)
radius = [None]*len(contours)
for i, c in enumerate(contours):
contours_poly[i] = cv.approxPolyDP(c, 3, True)
boundRect[i] = cv.boundingRect(contours_poly[i])
centers[i], radius[i] = cv.minEnclosingCircle(contours_poly[i])
## [allthework]
## [zeroMat]
drawing = np.zeros((output.shape[0], output.shape[1], 3), dtype=np.uint8)
## [zeroMat]
## [forContour]
# Draw polygonal contour + bonding rects + circles
for i in range(len(contours)):
color = (rng.randint(0,256), rng.randint(0,256), rng.randint(0,256))
cv.drawContours(drawing, contours_poly, i, color)
cv.rectangle(drawing, (int(boundRect[i][0]), int(boundRect[i][1])), \
(int(boundRect[i][0]+boundRect[i][2]), int(boundRect[i][1]+boundRect[i][3])), color, 2)
# Opens a new window and displays the output frame
cv.imshow('Contours', drawing)
# Frames are read by intervals of 10 milliseconds. The programs breaks out of the while loop when the user presses the 'q' key
if cv.waitKey(10) & 0xFF == ord('q'):
break
# The following frees up resources and closes all windows
cap.release()
cv.destroyAllWindows()
try different values in the threshold for canny.
I want to get the shade value of each circles from an image.
I try to detect circles using HoughCircle.
I get the center of each circle.
I put the text (the circle numbers) in a circle.
I set the pixel subset to obtain the shading values and calculate the averaged shading values.
I want to get the results of circle number, the coordinates of the center, and averaged shading values in CSV format.
But, in the 3rd step, the circle numbers were randomly assigned. So, it's so hard to find circle number.
How can I number circles in a sequence?
# USAGE
# python detect_circles.py --image images/simple.png
# import the necessary packages
import numpy as np
import argparse
import cv2
import csv
# define a funtion of ROI calculating the average value in specified sample size
def ROI(img,x,y,sample_size):
Each_circle=img[y-sample_size:y+sample_size, x-sample_size:x+sample_size]
average_values=np.mean(Each_circle)
return average_values
# open the csv file named circles_value
circles_values=open('circles_value.csv', 'w')
# construct the argument parser and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", required = True, help = "Path to the image")
args = vars(ap.parse_args())
# load the image, clone it for output, and then convert it to grayscale
image = cv2.imread(args["image"])
output = image.copy()
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
# detect circles in the image
circles = cv2.HoughCircles(gray, cv2.HOUGH_GRADIENT, 1.2,50, 100, 1, 1, 20, 30)
# 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")
number=1
font = cv2.FONT_HERSHEY_SIMPLEX
# 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
number=str(number)
cv2.circle(output, (x, y), r, (0, 255, 0), 4)
cv2.rectangle(output, (x - 10, y - 10), (x + 10, y + 10), (0, 128, 255), -1)
# number each circle, but its result shows irregular pattern
cv2.putText(output, number, (x,y), font,0.5,(0,0,0),2,cv2.LINE_AA)
# get the average value in specified sample size (20 x 20)
sample_average_value=ROI(output, x, y, 20)
# write the csv file with number, (x,y), and average pixel value
circles_values.write(number+','+str(x)+','+str(y)+','+str(sample_average_value)+'\n')
number=int(number)
number+=1
# show the output image
cv2.namedWindow("image", cv2.WINDOW_NORMAL)
cv2.imshow("image", output)
cv2.waitKey(0)
# close the csv file
circles_values.close()
You could sort your circles based on their x, y values, the width of the image and a rough line height, for example:
import numpy as np
import argparse
import cv2
import csv
# define a funtion of ROI calculating the average value in specified sample size
def ROI(img,x,y,sample_size):
Each_circle=img[y-sample_size:y+sample_size, x-sample_size:x+sample_size]
average_values=np.mean(Each_circle)
return average_values
# open the csv file named circles_value
with open('circles_value.csv', 'wb') as circles_values:
csv_output = csv.writer(circles_values)
# construct the argument parser and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", required = True, help = "Path to the image")
args = vars(ap.parse_args())
# load the image, clone it for output, and then convert it to grayscale
image = cv2.imread(args["image"])
output = image.copy()
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
# detect circles in the image
circles = cv2.HoughCircles(gray, cv2.cv.CV_HOUGH_GRADIENT, 1.2,50, 100, 1, 1, 20, 30)
# 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")
font = cv2.FONT_HERSHEY_SIMPLEX
height = 40
# loop over the (x, y) coordinates and radius of the circles
for number, (x, y, r) in enumerate(sorted(circles, key=lambda v: v[0] + (v[1] / height) * image.shape[1]), start=1):
text = str(number)
(tw, th), bl = cv2.getTextSize(text, font, 0.5, 2) # So the text can be centred in the circle
tw /= 2
th = th / 2 + 2
# 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), 3)
cv2.rectangle(output, (x - tw, y - th), (x + tw, y + th), (0, 128, 255), -1)
# number each circle, centred in the rectangle
cv2.putText(output, text, (x-tw, y + bl), font, 0.5, (0,0,0), 2, cv2.CV_AA)
# get the average value in specified sample size (20 x 20)
sample_average_value = ROI(output, x, y, 20)
# write the csv file with number, (x,y), and average pixel value
csv_output.writerow([number, x, y, sample_average_value])
# show the output image
cv2.namedWindow("image", cv2.WINDOW_NORMAL)
cv2.imshow("image", output)
cv2.waitKey(0)
Also, it is easier to use Python's CSV library to write entries to your output file. This way you don't need to convert each entry to a string and add commas between each entry. enumerate() can be used to count each circle automatically. Also getTextSize() can be used to determine the dimensions of the text to be printed enabling you to centre it in the rectangle.
This would give you an output as follows:
And a CSV starting as:
1,2,29,nan
2,51,19,nan
3,107,22,100.72437499999999
4,173,23,102.33291666666666
5,233,26,88.244791666666671
6,295,22,92.953541666666666
7,358,28,142.51625000000001
8,418,26,155.12875
9,484,31,127.02541666666667
10,547,25,112.57958333333333
The mistake in your code is that your number is dependent upon the order of circles in list returned from cv2.HoughCircles which can be random, So what I would have done in this situation is to devise a formula which would convert the center(x, y) value of each circle to an ID, and the same circle would yield same ID given its center position remains same:
def get_id_from_center(x, y):
return x + y*50
for (x, y, r) in circles:
number = str(get_id_from_center(x, y))