I have this image and I would like to find where the crossties are (either bounding boxes or masks works). Crossties are the horizontal blocks between the two rails. Just the rails in the middle are sufficient.
I have been struggling for quite a while now. I found the function cv2.HoughLinesP but I could not make it work.
Has anyone ever done something similar or know how to do it?
It would be very helpful.
# 213, 205, 210
# 207, 200, 204
# 201, 195, 199
# 215, 208, 206
# 200, 195, 192
import cv2
import numpy as np
img = cv2.cvtColor(cv2.imread('out2168.png'), cv2.COLOR_BGR2RGB)
img = img[:, 300:400]
canny = cv2.Canny(img, 30, 120)
lines = cv2.HoughLines(canny, 1, np.pi / 360, 20)
for rho, theta in lines[0]:
a = np.cos(theta)
b = np.sin(theta)
x0 = a * rho
y0 = b * rho
x1 = int(x0 + 1000 * (-b))
y1 = int(y0 + 1000 * a)
x2 = int(x0 - 1000 * (-b))
y2 = int(y0 - 1000 * a)
cv2.line(img, (x1, y1), (x2, y2), (0, 0, 255), 2)
cv2.imshow('rail', img)
cv2.waitKey(0)
References:
OpenCV houghLinesP parameters
https://docs.opencv.org/3.4/d9/db0/tutorial_hough_lines.html
Related
i have a problem in my code as shown in this code
import os
import cv2
import numpy as np
import matplotlib.pyplot as plt
labels = ['Background', 'Korosi', 'Tanah', 'Tanaman']
np.random.seed(42)
COLORS = np.random.randint(0, 255, size=(len(labels), 3), dtype="uint8")
net = cv2.dnn.readNetFromONNX('anomali_model1.onnx')
layer_names = net.getLayerNames()
output_layers = [layer_names[i - 1] for i in net.getUnconnectedOutLayers)]
capture = cv2.VideoCapture(0)
while True: re, img = capture.read()
#img = cv2.cvtColor(img, cv2.COLOR_RGBA2RGB)
#height, width, channels = img.shape
#blob = cv2.dnn.blobFromImage(img, 0.00392, (256, 256),
#swapRB=True, crop=False)
blob = cv2.dnn.blobFromImage(img, swapRB=True, crop=False)
net.setInput(blob)
outs = net.forward(output_layers)
class_ids = []
confidences = []
boxes = []
for out in outs:
for detection in out:
scores = detection[5:]
class_id = np.argmax(scores)
confidence = scores[class_id]
if confidence > 0.5:
# Object detected
center_x = int(detection[0] * width)
center_y = int(detection[1] * height)
w = int(detection[2] * width)
h = int(detection[3] * height)
# Rectangle coordinates
x = int(center_x - w / 2)
y = int(center_y - h / 2)
boxes.append([x, y, w, h])
confidences.append(float(confidence))
class_ids.append(class_id)
indexes = cv2.dnn.NMSBoxes(boxes, confidences, 0.5, 0.4)
font = cv2.FONT_HERSHEY_PLAIN
colors = np.random.uniform(0, 255, size=(len(classes), 3))
for i in range(len(boxes)):
if i in indexes:
x, y, w, h = boxes[i]
label = str(classes[class_ids[i]])
color = colors[class_ids[i]]
cv2.rectangle(img, (x, y), (x + w, y + h), color, 2)
cv2.putText(img, label, (x, y + 30), font, 2, color, 3)
cv2.imshow("Image",cv2.resize(img, (800,600)))
if cv2.waitKey(1) & 0xFF == ord('q'):
break
video_capture.release()
cv2.destroyAllWindows()
And i get error like this:
error Traceback (most recent call last)
~\AppData\Local\Temp\ipykernel_10644\3517982312.py in <module>
9 blob = cv2.dnn.blobFromImage(img, swapRB=True, crop=False)
10 net.setInput(blob)
---> 11 outs = net.forward(output_layers)
12
13 class_ids = []
error: OpenCV(3.4.17) D:\a\opencv-python\opencv-python\opencv\modules\dnn\src\layers\convolution_layer.cpp:331: error: (-2:Unspecified error) Number of input channels should be multiple of 3 but got 640 in function 'cv::dnn::ConvolutionLayerImpl::getMemoryShapes'
can you help me to solve this problem? because I've looked into various sources but did not find a solution.
library version for this code
python version 3.7
tensorflow version 2.0
opencv version 3.4.17
I hope you all can solve this problem and share with me
How to display the application in windows.
Code for Reference:
from tkinter import N
import numpy as np
from keras.preprocessing.image import img_to_array
import cv2
import imutils
from keras.models import load_model
import numpy as np
# parameters for loading data and images
detection_model_path = 'ER_Project//haar-cascade-files-master/haarcascade_frontalface_default.xml'
emotion_model_path = 'ER_Project/_mini_XCEPTION.102-0.66.hdf5'
# hyper-parameters for bounding boxes shape
# loading models
face_detection = cv2.CascadeClassifier(detection_model_path)
emotion_classifier = load_model(emotion_model_path, compile=False)
EMOTIONS = ["angry", "disgust", "scared", "happy", "sad", "surprised",
"neutral"]
#feelings_faces = []
# for index, emotion in enumerate(EMOTIONS):
# feelings_faces.append(cv2.imread('emojis/' + emotion + '.png', -1))
# starting video streaming
cv2.namedWindow('your_face')
camera = cv2.VideoCapture(0)
while True:
print("Hello")
frame = camera.read()[1]
# reading the frame
frame = imutils.resize(frame, width=300)
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
faces = face_detection.detectMultiScale(
gray, scaleFactor=1.1, minNeighbors=5, minSize=(30, 30), flags=cv2.CASCADE_SCALE_IMAGE)
canvas = np.zeros((250, 300, 3), dtype="uint8")
frameClone = frame.copy()
if len(faces) > 0:
faces = sorted(faces, reverse=True,
key=lambda x: (x[2] - x[0]) * (x[3] - x[1]))[0]
(fX, fY, fW, fH) = faces
# Extract the ROI of the face from the grayscale image, resize it to a fixed 28x28 pixels, and then prepare
# the ROI for classification via the CNN
roi = gray[fY:fY + fH, fX:fX + fW]
roi = cv2.resize(roi, (64, 64))
roi = roi.astype("float") / 255.0
roi = img_to_array(roi)
roi = np.expand_dims(roi, axis=0)
preds = emotion_classifier.predict(roi)[0]
emotion_probability = np.max(preds)
label = EMOTIONS[preds.argmax()]
else:
continue
for (i, (emotion, prob)) in enumerate(zip(EMOTIONS, preds)):
# construct the label text
text = "{}: {:.2f}%".format(emotion, prob * 100)
# draw the label + probability bar on the canvas
# emoji_face = feelings_faces[np.argmax(preds)]
w = int(prob * 300)
cv2.rectangle(canvas, (7, (i * 35) + 5),
(w, (i * 35) + 35), (0, 0, 255), -1)
cv2.putText(canvas, text, (10, (i * 35) + 23),
cv2.FONT_HERSHEY_SIMPLEX, 0.45,
(255, 255, 255), 2)
cv2.putText(frameClone, label, (fX, fY - 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.45, (0, 0, 255), 2)
cv2.rectangle(frameClone, (fX, fY), (fX + fW, fY + fH),
(0, 0, 255), 2)
# for c in range(0, 3):
# frame[200:320, 10:130, c] = emoji_face[:, :, c] * \
# (emoji_face[:, :, 3] / 255.0) + frame[200:320,
# 10:130, c] * (1.0 - emoji_face[:, :, 3] / 255.0)
cv2.imshow('your_face', frameClone)
cv2.imshow("Probabilities", canvas)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
camera.release()
cv2.destroyAllWindows()
NUMA SUPPORT:
2022-04-20 04:36:21.181568: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:922] could not open file to read NUMA node: /sys/bus/pci/devices/0000:01:00.0/numa_node
Your kernel may have been built without NUMA support.
2022-04-20 04:36:21.181664: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 3951 MB memory: -> device: 0, name: NVIDIA GeForce GTX 1660 Ti, pci bus id: 0000:01:00.0, compute capability: 7.5
I need to run this openCV gui app on windows.
I'm using OpenCV 4.4 and running the following code to detect lines of a grid. When I display the image it always detect one line as shown in the screenshot. How can I detect all vertical lines in the grid?
grid = cv2.imread('images/grid.jpeg')
grayscale = cv2.cvtColor(grid, cv2.COLOR_BGR2GRAY)
edges = cv2.Canny(grayscale, 50, 150, apertureSize=3)
lines = cv2.HoughLines(edges, 1, np.pi/180, 100)
for rho, theta in lines[0]:
a = np.cos(theta)
b = np.sin(theta)
x0 = a * rho
y0 = b * rho
x1 = int(x0 + 1000 * (-b))
y1 = int(y0 + 1000 * (a))
x2 = int(x0 - 1000 * (-b))
y2 = int(y0 - 1000 * (a))
cv2.line(grid, (x1, y1), (x2, y2), (255, 0, 0), 2)
cv2.imshow("Lines", grid)
cv2.waitKey(0)
cv2.destroyAllWindows()
Original Image:
You can use lineDetector algorithm.
Find the edges of your image, as #Micka suggested
img = cv2.imread("lines.png")
img_gry = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
img_cny = cv2.Canny(img_gry, 50, 200)
Result:
To detect the vertical edges, the difference between x-coordinates should be close to 0 Since only y-coordinates are changing.
if abs(x1 - x2) < 3:
cv2.line(img, pt1=(x1, y1), pt2=(x2, y2), color=(0, 0, 255), thickness=3)
Result:
Code:
import cv2
img = cv2.imread("lines.png")
img_gry = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
img_cny = cv2.Canny(img_gry, 50, 200)
lns = cv2.ximgproc.createFastLineDetector().detect(img_cny)
for ln in lns:
x1 = int(ln[0][0])
y1 = int(ln[0][1])
x2 = int(ln[0][2])
y2 = int(ln[0][3])
if abs(x1 - x2) < 3:
cv2.line(img, pt1=(x1, y1), pt2=(x2, y2), color=(0, 0, 255), thickness=3)
cv2.imshow("lns", img)
cv2.waitKey(0)
I want to detect playing cards and found .cfg and .weights for it. Classes has 52cards names. Following code is giving index out of range error. I couldn't understand the outputs of Yolo and how to get the detected labels. I am new to this, have been trying to understand. Can someone please help!
import cv2
import numpy as np
# Load Yolo
net = cv2.dnn.readNet("yolocards_608.weights", "yolocards.cfg")
classes = []
with open("cards.names", "r") as f:
classes = [line.strip() for line in f.readlines()]
layer_names = net.getLayerNames()
output_layers = [layer_names[i[0] - 1] for i in net.getUnconnectedOutLayers()]
colors = np.random.uniform(0, 255, size=(len(classes), 3))
# Loading image
img = cv2.imread("playing_cards_image.jpg")
img = cv2.resize(img, None, fx=0.4, fy=0.4)
height, width, channels = img.shape
# Detecting objects
blob = cv2.dnn.blobFromImage(img, 0.00392, (416, 416), (0, 0, 0), True, crop=False)
net.setInput(blob)
outs = net.forward(output_layers)
# Showing informations on the screen
class_ids = []
confidences = []
boxes = []
for out in outs:
print(out.shape)
for detection in out:
scores = detection[:]
class_id = np.argmax(scores)
confidence = scores[class_id]
if confidence > 0.5:
# Object detected
center_x = int(detection[0] * width)
center_y = int(detection[1] * height)
w = int(detection[2] * width)
h = int(detection[3] * height)
# Rectangle coordinates
x = int(center_x - w / 2)
y = int(center_y - h / 2)
boxes.append([x, y, w, h])
confidences.append(float(confidence))
class_ids.append(class_id)
indexes = cv2.dnn.NMSBoxes(boxes, confidences, 0.5, 0.4)
font = cv2.FONT_HERSHEY_PLAIN
for j in range(len(boxes)):
if i in indexes:
x, y, w, h = boxes[i]
print(class_ids[i])
label = str(classes[class_ids[i]])
print(label)
color = colors[i]
cv2.rectangle(img, (x, y), (x + w, y + h), color, 2)
cv2.putText(img, label, (x, y + 30), font, 3, color, 3)
error:
0
Ah
---------------------------------------------------------------------------
IndexError Traceback (most recent call last)
<ipython-input-46-adaf82305ab8> in <module>
6 label = str(classes[class_ids[i]])
7 print(label)
----> 8 color = colors[i]
9 cv2.rectangle(img, (x, y), (x + w, y + h), color, 2)
10 cv2.putText(img, label, (x, y + 30), font, 3, color, 3)
IndexError: index 52 is out of bounds for axis 0 with size 52
Am using Hough's Transform to detect straight lines in an image. Transformation is done after a Canny edge detection and am able to get the lines, however, i need to display only the Left most line. Here is the section of code
cv::Mat Final, Canned;
HoughLines(Canned, lines, 1, CV_PI / 180, 150, 0, 0);
for (size_t i = 0; i < lines.size(); i++)
{
float rho = lines[i][0], theta = lines[i][1];
cv::Point pt1, pt2;
double a = cos(theta), b = sin(theta);
double x0 = a*rho, y0 = b*rho;
pt1.x = cvRound(x0 + 1000 * (-b));
pt1.y = cvRound(y0 + 1000 * (a));
pt2.x = cvRound(x0 - 1000 * (-b));
pt2.y = cvRound(y0 - 1000 * (a));
line(Final,pt1, pt2, Scalar(0, 0, 255), 1, CV_AA);
}
imshow("detected lines", Final);
Am attaching the image generated after applying Hough Transform
I need to display only the Left most line
here is the elements of Line vector.
[-386, 3.12414]
[-332, 3.08923]
[-381, 3.12414]
[-337, 3.10669]
[386, 0]
[-323, 3.05433]
[-339, 3.10669]
[-335, 3.08923]
[-330, 3.07178]
[383, 0]
[-317, 3.08923]
You can iterate though the lines and find the left most line by averaging the x-coordinates of the expoints of the line.
# Iterate through lines and find the x-position
xPositions = []
for line in lines:
cdst, pt1, pt2 = draw_line(line, cdst, (0,0,255))
xPositions.append((pt1[0]+pt2[0])/2)
Here is the output image:
Here is the source image:
Here is the complete code:
import math
import cv2 as cv
import numpy as np
src = cv.imread('/home/stephen/Desktop/lines.png', cv.IMREAD_GRAYSCALE)
dst = cv.Canny(src, 50, 200, None, 3)
# Copy edges to the images that will display the results in BGR
cdst = cv.cvtColor(dst, cv.COLOR_GRAY2BGR)
cdstP = np.copy(cdst)
# Find lines
lines = cv.HoughLines(dst, 1, np.pi / 180, 100, None, 0, 0)
# Function that draws line
def draw_line(line, img, color):
rho = line[0][0]
theta = line[0][1]
a = math.cos(theta)
b = math.sin(theta)
x0 = a * rho
y0 = b * rho
pt1 = (int(x0 + 1000*(-b)), int(y0 + 1000*(a)))
pt2 = (int(x0 - 1000*(-b)), int(y0 - 1000*(a)))
cv.line(cdst, pt1, pt2, color, 3, cv.LINE_AA)
return img, pt1, pt2
# Iterate through lines and find the x-position
xPositions = []
for line in lines:
cdst, pt1, pt2 = draw_line(line, cdst, (0,0,255))
xPositions.append((pt1[0]+pt2[0])/2)
# Find the left most line
leftMost = xPositions.index(min(xPositions))
# Draw only the left most line
cdst, pt1, pt2 = draw_line(lines[leftMost], cdst, (0,255,0))
cv.imshow('lines', cdst)
cv.waitKey()
cv.destroyAllWindows()