How can I increase FPS when detecting aruco markers? - python

When I using aruco markers, I am getting very low fps(10~15). Firstly I showed the FPS info, marker position, marker attitude, camera position and camera attitude on the detection screen. With this way, I get ~10 FPS. Then I removed all texts except FPS info. It was better(~13 FPS) but still not enough. I need at least 25 FPS. How can I increase FPS?
Resolution: 640x480
aruco_pose_estimation.py
import numpy as np
import cv2
import cv2.aruco as aruco
import sys, time, math
#--- Define Tag
id_to_find = 3
marker_size = 10 #- [cm]
#------------------------------------------------------------------------------
#------- ROTATIONS https://www.learnopencv.com/rotation-matrix-to-euler-angles/
#------------------------------------------------------------------------------
# Checks if a matrix is a valid rotation matrix.
def isRotationMatrix(R):
Rt = np.transpose(R)
shouldBeIdentity = np.dot(Rt, R)
I = np.identity(3, dtype=R.dtype)
n = np.linalg.norm(I - shouldBeIdentity)
return n < 1e-6
# Calculates rotation matrix to euler angles
# The result is the same as MATLAB except the order
# of the euler angles ( x and z are swapped ).
def rotationMatrixToEulerAngles(R):
assert (isRotationMatrix(R))
sy = math.sqrt(R[0, 0] * R[0, 0] + R[1, 0] * R[1, 0])
singular = sy < 1e-6
if not singular:
x = math.atan2(R[2, 1], R[2, 2])
y = math.atan2(-R[2, 0], sy)
z = math.atan2(R[1, 0], R[0, 0])
else:
x = math.atan2(-R[1, 2], R[1, 1])
y = math.atan2(-R[2, 0], sy)
z = 0
return np.array([x, y, z])
#--- Get the camera calibration path
calib_path = ""
camera_matrix = np.loadtxt(calib_path+'cameraMatrix_raspi.txt', delimiter=',')
camera_distortion = np.loadtxt(calib_path+'cameraDistortion_raspi.txt', delimiter=',')
#--- 180 deg rotation matrix around the x axis
R_flip = np.zeros((3,3), dtype=np.float32)
R_flip[0,0] = 1.0
R_flip[1,1] =-1.0
R_flip[2,2] =-1.0
#--- Define the aruco dictionary
aruco_dict = aruco.getPredefinedDictionary(aruco.DICT_ARUCO_ORIGINAL)
#aruco_dict = aruco.getPredefinedDictionary(aruco.DICT_4X4_250)
parameters = aruco.DetectorParameters_create()
#--- Capture the videocamera (this may also be a video or a picture)
cap = cv2.VideoCapture(0)
#-- Set the camera size as the one it was calibrated with
cap.set(cv2.CAP_PROP_FRAME_WIDTH, 640)
cap.set(cv2.CAP_PROP_FRAME_HEIGHT, 480)
cap.set(cv2.CAP_PROP_FPS, 40)
#-- Font for the text in the image
font = cv2.FONT_HERSHEY_PLAIN
prev_frame_time = time.time()
while True:
ret, frame = cap.read()
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY) #-- remember, OpenCV stores color images in Blue, Green, Red
#-- Find all the aruco markers in the image
corners, ids, rejected = aruco.detectMarkers(image=gray, dictionary=aruco_dict, parameters=parameters,
cameraMatrix=camera_matrix, distCoeff=camera_distortion)
if ids is not None:
ret = aruco.estimatePoseSingleMarkers(corners, marker_size, camera_matrix, camera_distortion)
#-- Unpack the output, get only the first
rvec, tvec = ret[0][0,0,:], ret[1][0,0,:]
#-- Draw the detected marker and put a reference frame over it
aruco.drawDetectedMarkers(frame, corners)
aruco.drawAxis(frame, camera_matrix, camera_distortion, rvec, tvec, 10)
#-- Print the tag position in camera frame
str_position = "MARKER Position x=%4.0f y=%4.0f z=%4.0f"%(tvec[0], tvec[1], tvec[2])
cv2.putText(frame, str_position, (0, 400), font, 1.3, (0, 255, 0), 2, cv2.LINE_AA)
#-- Obtain the rotation matrix tag->camera
R_ct = np.matrix(cv2.Rodrigues(rvec)[0])
R_tc = R_ct.T
#-- Get the attitude in terms of euler 321 (Needs to be flipped first)
roll_marker, pitch_marker, yaw_marker = rotationMatrixToEulerAngles(R_flip*R_tc)
#-- Print the marker's attitude respect to camera frame
str_attitude = "MARKER Attitude r=%4.0f p=%4.0f y=%4.0f"%(math.degrees(roll_marker),math.degrees(pitch_marker),
math.degrees(yaw_marker))
cv2.putText(frame, str_attitude, (0, 420), font, 1, (0, 255, 0), 2, cv2.LINE_AA)
#-- Now get Position and attitude f the camera respect to the marker
pos_camera = -R_tc*np.matrix(tvec).T
str_position = "CAMERA Position x=%4.0f y=%4.0f z=%4.0f"%(pos_camera[0], pos_camera[1], pos_camera[2])
cv2.putText(frame, str_position, (0, 440), font, 1, (0, 255, 0), 2, cv2.LINE_AA)
#-- Get the attitude of the camera respect to the frame
roll_camera, pitch_camera, yaw_camera = rotationMatrixToEulerAngles(R_flip*R_tc)
str_attitude = "CAMERA Attitude r=%4.0f p=%4.0f y=%4.0f"%(math.degrees(roll_camera),math.degrees(pitch_camera),
math.degrees(yaw_camera))
cv2.putText(frame, str_attitude, (0, 460), font, 1, (0, 255, 0), 2, cv2.LINE_AA)
#calculate the FPS and display on frame
new_frame_time = time.time()
fps = 1/(new_frame_time - prev_frame_time)
prev_frame_time = new_frame_time
cv2.putText(frame, "FPS" + str(int(fps)), (0,360), font, 1.3, (100, 255, 0), 2, cv2.LINE_AA)
#--- Display the frame
cv2.imshow('frame', frame)
#--- use 'q' to quit
key = cv2.waitKey(1) & 0xFF
if key == ord('q'):
cap.release()
cv2.destroyAllWindows()
break
.
.
After removed texts

Related

PutText overlap issue - image

I'm using FLIR Lepton camera to capture the thermal image, then try to display the temperature on the image using PutText method but getting very strange result. Any advice is appreciated in advance.
Code:
import cv2
import numpy as np
image_counter = 0
video = cv2.VideoCapture(0,cv2.CAP_DSHOW)
video.set(cv2.CAP_PROP_FOURCC, cv2.VideoWriter.fourcc('Y','1','6',' '))
video.set(cv2.CAP_PROP_CONVERT_RGB, 0)
if video.isOpened():
rval, frame = video.read()
else:
rval = False
clahe = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8,8))
while rval:
rval, frame = video.read()
frame_roi = frame[:-3, :]
normed = cv2.normalize(frame_roi, None, 0, 255, cv2.NORM_MINMAX, cv2.CV_8U)
cl1 = clahe.apply(normed)
nor = cv2.cvtColor(cl1, cv2.COLOR_GRAY2BGR)
color = cv2.applyColorMap(nor, cv2.COLORMAP_JET)
for i in range(frame.shape[0]):
for j in range(frame.shape[1]):
pixel = frame [i,j]
Temp_C = pixel/100 - 273.15
color = cv2.putText(color, "{:.2f}".format(Temp_C), (10,30), cv2.FONT_HERSHEY_SIMPLEX, 0.45, cv2.LINE_AA)
print (Temp_C)
cv2.imshow("preview", cv2.resize(color, dsize=(640,480), interpolation=cv2.INTER_LINEAR))
key = cv2.waitKey(100)
if key == 27: # exit on ESC
break
Have a look here:
for i in range(frame.shape[0]):
for j in range(frame.shape[1]):
pixel = frame [i,j]
Temp_C = pixel/100 - 273.15
color = cv2.putText(color, "{:.2f}".format(Temp_C), (10,30), cv2.FONT_HERSHEY_SIMPLEX, 0.45, cv2.LINE_AA)
print (Temp_C)
You are basically looping through each pixel of the image, getting its temperature and writing the temperature on the image.
But you are writing every temperature at one location of the image; at (10, 30), so if there were 1000 pixels, you are writing 1000 temperatures on a single spot on the image.
It wouldn't be possible to spread out every temperature detected on the image with no overlapping, unless each text is only one pixel in size, which would cover the entire screen.
You could try something like this:
for i in range(0, frame.shape[0], 50):
for j in range(0, frame.shape[1], 50):
pixel = frame [i,j]
Temp_C = pixel/100 - 273.15
color = cv2.putText(color, "{:.2f}".format(Temp_C), (i,j), cv2.FONT_HERSHEY_SIMPLEX, 0.45, cv2.LINE_AA)
print (Temp_C)
Where the temperature of every next 50 pixels is displayed on the image.

pytesseract detects the wrong integer values

I'm trying to detects the numbers found in my sqares, and I thought I could use the libary pytesseract, but for some reason I read the wrong values.
This is the console output:
And here I have all my pictures (they are seperated, this is just to show them all)
import numpy as np
import cv2
import re
from PIL import Image
import pytesseract
pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract'
img = cv2.imread('gulRecNum.jpg')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# convert to HSV, since red and yellow are the lowest hue colors and come before green
hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
# create a binary thresholded image on hue between red and yellow
lower = (0,240,160)
upper = (30,255,255)
thresh = cv2.inRange(hsv, lower, upper)
# apply morphology
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (9,9))
clean = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel)
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (15,15))
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]
result1 = img.copy()
result2 = img.copy()
mask = np.zeros(result2.shape, dtype=np.uint8)
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
ROI_number = 0
for c in contours:
cv2.drawContours(result1,[c],0,(0,0,0),2)
# get rotated rectangle from contour
rot_rect = cv2.minAreaRect(c)
box = cv2.boxPoints(rot_rect)
box = np.int0(box)
# draw rotated rectangle on copy of img
cv2.drawContours(result2,[box],0,(0,0,0),2)
# Gør noget hvis arealet er større end 1.
# Whats the area of the component?
areal = cv2.contourArea(c)
if(areal > 1):
# get the center of mass
M = cv2.moments(c)
cx = int(M['m10']/M['m00'])
cy = int(M['m01']/M['m00'])
center = (cx, cy)
print("\nx: ",cx,"\ny: ",cy)
color = (0, 0, 255)
cv2.circle(result2, center, 3, color, -1)
cv2.putText(result2, "center", (int(cx) - 10, int(cy) - 20),
cv2.FONT_HERSHEY_SIMPLEX, 1.2, color, 2)
# LOOK AT THIS PART
x,y,w,h = cv2.boundingRect(c)
ROI = 255 - thresh[y:y+h, x:x+w]
cv2.drawContours(mask, [c], -1, (255,255,255), -1)
cv2.imwrite('ROI_{}.png'.format(ROI_number), ROI)
Number = pytesseract.image_to_string(ROI, config='--psm 13 --oem 3 -c tessedit_char_whitelist=0123456789')
print("Number ", Number)
ROI_number += 1
# save result
cv2.imwrite("4cubes_result2.png",result2)
# display result
imS = cv2.resize(result2, (600, 400))
cv2.imshow("result2", imS)
cv2.waitKey(0)
cv2.destroyAllWindows()
Thought I could write Number = pytesseract.image_to_string(ROI, config='--psm 13 --oem 3 -c tessedit_char_whitelist=0123456789') print(Number)
and then get the number from the image, but I don't, how can that be?
EDIT NEW ERROR
how do i solve it with this picture?
from PIL import Image
from operator import itemgetter
import numpy as np
import easyocr
import cv2
import re
import imutils
import pytesseract
pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract'
reader = easyocr.Reader(['ch_sim','en']) # need to run only once to load model into memory
#Define empty array
Cubes = []
def getNumber(ROI):
img = cv2.imread(ROI)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
ret,thresh = cv2.threshold(gray,127,255,0)
#cv2.imshow(thresh)
#cv2.imshow('Thresholded original',thresh)
#cv2.waitKey(0)
## Get contours
contours,h = cv2.findContours(thresh,cv2.RETR_CCOMP, cv2.CHAIN_APPROX_SIMPLE)
## only draw contour that have big areas
imx = img.shape[0]
imy = img.shape[1]
lp_area = (imx * imy) / 10
tmp_img = img.copy()
for cnt in contours:
approx = cv2.approxPolyDP(cnt,0.01 * cv2.arcLength(cnt, True), True)
if cv2.contourArea(cnt) > lp_area:
# Draw box corners and minimum area rectangle
rect = cv2.minAreaRect(cnt)
box = cv2.boxPoints(rect)
box = np.int0(box)
#cv2.drawContours(tmp_img, [box], 0, (0, 50, 255), 3)
#cv2.circle(tmp_img, tuple(box[0]), 8, (0, 255, 0), -1)
#cv2.circle(tmp_img, tuple(box[1]), 8, (0, 255, 0), -1)
#cv2.circle(tmp_img, tuple(box[2]), 8, (0, 255, 0), -1)
#cv2.circle(tmp_img, tuple(box[3]), 8, (0, 255, 0), -1)
#cv2.imshow(tmp_img)
#cv2.imshow('Minimum Area Rectangle', tmp_img)
#cv2.waitKey(0)
## Correct orientation and crop
# Link, https://jdhao.github.io/2019/02/23/crop_rotated_rectangle_opencv/
width = int(rect[1][0])
height = int(rect[1][1])
src_pts = box.astype("float32")
dst_pts = np.array([[0, height-1],
[0, 0],
[width-1, 0],
[width-1, height-1]], dtype="float32")
M = cv2.getPerspectiveTransform(src_pts, dst_pts)
warped = cv2.warpPerspective(img, M, (width, height))
# Run OCR on cropped image
# If the predicted value is digit print else rotate first
result = reader.readtext(warped)
print(result)
predicted_digit = result[0][1]
if np.char.isdigit(predicted_digit) == True:
cv2.imshow("warped " + ROI,warped)
else:
rot_img = warped.copy()
for i in range(0, 3):
rotated_image = cv2.rotate(rot_img, cv2.cv2.ROTATE_90_CLOCKWISE)
result = reader.readtext(rotated_image)
#if np.array(result).size == 0:
# continue
if not result:
rot_img = rotated_image
continue
#if len(result) == 0:
# continue
predicted_digit = result[0][1]
#print(result)
#print(predicted_digit)
#cv2.imshow(rotated_image)
if np.char.isdigit(predicted_digit) == True:
cv2.imshow("Image " + ROI, rotated_image)
break
rot_img = rotated_image
return predicted_digit
def sortNumbers(Cubes):
Cubes = sorted(Cubes, key=lambda x: int(x[2]))
#Cubes.sort(key=itemgetter(2)) # In-place sorting
#Cubes = sorted(Cubes, key=itemgetter(2)) # Create a new list
return Cubes
#img = cv2.imread('gulRecNum.jpg')
img = cv2.imread('webcam7.png')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# convert to HSV, since red and yellow are the lowest hue colors and come before green
hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
# create a binary thresholded image on hue between red and yellow
#Change these if cube colours changes?
lower =(20, 100, 100)
upper = (30, 255, 255)
#lower = (0,240,160)
#upper = (30,255,255)
thresh = cv2.inRange(hsv, lower, upper)
# apply morphology
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (9,9))
clean = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel)
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (15,15))
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]
result2 = img.copy()
mask = np.zeros(result2.shape, dtype=np.uint8)
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
ROI_number = 0
for c in contours:
cv2.drawContours(result2,[c],0,(0,0,0),2)
# get rotated rectangle from contour
rot_rect = cv2.minAreaRect(c)
box = cv2.boxPoints(rot_rect)
box = np.int0(box)
# draw rotated rectangle on copy of img
cv2.drawContours(result2,[box],0,(0,0,0),2)
# Gør noget hvis arealet er større end 1.
# Whats the area of the component?
areal = cv2.contourArea(c)
if(areal > 1):
# get the center of mass
M = cv2.moments(c)
cx = int(M['m10']/M['m00'])
cy = int(M['m01']/M['m00'])
center = (cx, cy)
print("\nx: ",cx,"\ny: ",cy)
color = (0, 0, 255)
cv2.circle(result2, center, 3, color, -1)
cv2.putText(result2, "center", (int(cx) - 10, int(cy) - 20),
cv2.FONT_HERSHEY_SIMPLEX, 1.2, color, 2)
x,y,w,h = cv2.boundingRect(c)
ROI = 255 - thresh[y:y+h, x:x+w]
cv2.drawContours(mask, [c], -1, (255,255,255), -1)
cv2.imwrite('ROI_{}.png'.format(ROI_number), ROI)
#Read saved image (number)
result = getNumber('ROI_{}.png'.format(ROI_number))
print("ROI_number: ", result)
Cubes.append([cx, cy, result])
ROI_number += 1
# save result
cv2.imwrite("4cubes_result2.png",result2)
# display result
imS = cv2.resize(result2, (600, 400))
cv2.imshow("result2", imS)
#cv2.imshow('mask', mask)
#cv2.imshow('thresh', thresh)
SortedCubes = sortNumbers(Cubes)
print("\nFound array [x, y, Cube_num] = ", Cubes)
print("Sorted array [x, y, Cube_num] = ", SortedCubes)
cv2.waitKey(0)
cv2.destroyAllWindows()
I get the following error (it can't detect a number)
Traceback (most recent call last): File "c:/Users/Mads/OneDrive/Universitet/7. semester/ROB1/python/objectDetectiong.py", line 169, in <module> result = getNumber('ROI_{}.png'.format(ROI_number)) File "c:/Users/Mads/OneDrive/Universitet/7. semester/ROB1/python/objectDetectiong.py", line 70, in getNumber predicted_digit = result[0][1] IndexError: list index out of range
This is implementation of my comment. Since, I do not have individual images this code will work with given grid like processed image.
For OCR I used EasyOCR instead of Tesserect. You could also try pytesserect on each output cropped images. Instead of rotating 4 times by 90 degrees by confidence, I went with digit detection on OCR result. If a detection is not a number then only rotate and retry.
Tested on google colab. Replace cv2_imshow(...) with cv2.imshow(...) for working locally. Also remove from google.colab.patches import cv2_imshow import.
This is modified version of my answer on card orientation correction here, OpenCV: using Canny and Shi-Tomasi to detect round corners of a playing card. All previous code is left as comment.
Code
!pip install easyocr
import easyocr
reader = easyocr.Reader(['ch_sim','en']) # need to run only once to load model into memory
"""
Based on my answer of rotated card detection,
https://stackoverflow.com/questions/64860785/opencv-using-canny-and-shi-tomasi-to-detect-round-corners-of-a-playing-card/64862448#64862448
"""
import cv2
import numpy as np
from google.colab.patches import cv2_imshow
img = cv2.imread('1.jpg')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
ret,thresh = cv2.threshold(gray,127,255,0)
#cv2_imshow(thresh)
#cv2.imshow('Thresholded original',thresh)
#cv2.waitKey(0)
## Get contours
contours,h = cv2.findContours(thresh,cv2.RETR_CCOMP, cv2.CHAIN_APPROX_SIMPLE)
## only draw contour that have big areas
imx = img.shape[0]
imy = img.shape[1]
lp_area = (imx * imy) / 10
#################################################################
# Four point perspective transform
# https://www.pyimagesearch.com/2014/08/25/4-point-opencv-getperspective-transform-example/
#################################################################
def order_points(pts):
# initialzie a list of coordinates that will be ordered
# such that the first entry in the list is the top-left,
# the second entry is the top-right, the third is the
# bottom-right, and the fourth is the bottom-left
rect = np.zeros((4, 2), dtype = "float32")
# the top-left point will have the smallest sum, whereas
# the bottom-right point will have the largest sum
s = pts.sum(axis = 1)
rect[0] = pts[np.argmin(s)]
rect[2] = pts[np.argmax(s)]
# now, compute the difference between the points, the
# top-right point will have the smallest difference,
# whereas the bottom-left will have the largest difference
diff = np.diff(pts, axis = 1)
rect[1] = pts[np.argmin(diff)]
rect[3] = pts[np.argmax(diff)]
# return the ordered coordinates
return rect
def four_point_transform(image, pts):
# obtain a consistent order of the points and unpack them
# individually
rect = order_points(pts)
(tl, tr, br, bl) = rect
# compute the width of the new image, which will be the
# maximum distance between bottom-right and bottom-left
# x-coordiates or the top-right and top-left x-coordinates
widthA = np.sqrt(((br[0] - bl[0]) ** 2) + ((br[1] - bl[1]) ** 2))
widthB = np.sqrt(((tr[0] - tl[0]) ** 2) + ((tr[1] - tl[1]) ** 2))
maxWidth = max(int(widthA), int(widthB))
# compute the height of the new image, which will be the
# maximum distance between the top-right and bottom-right
# y-coordinates or the top-left and bottom-left y-coordinates
heightA = np.sqrt(((tr[0] - br[0]) ** 2) + ((tr[1] - br[1]) ** 2))
heightB = np.sqrt(((tl[0] - bl[0]) ** 2) + ((tl[1] - bl[1]) ** 2))
maxHeight = max(int(heightA), int(heightB))
# now that we have the dimensions of the new image, construct
# the set of destination points to obtain a "birds eye view",
# (i.e. top-down view) of the image, again specifying points
# in the top-left, top-right, bottom-right, and bottom-left
# order
dst = np.array([
[0, 0],
[maxWidth - 1, 0],
[maxWidth - 1, maxHeight - 1],
[0, maxHeight - 1]], dtype = "float32")
# compute the perspective transform matrix and then apply it
M = cv2.getPerspectiveTransform(rect, dst)
warped = cv2.warpPerspective(image, M, (maxWidth, maxHeight))
# return the warped image
return warped
#################################################################
#print(len(contours))
tmp_img = img.copy()
for cnt in contours:
approx = cv2.approxPolyDP(cnt,0.01 * cv2.arcLength(cnt, True), True)
## calculate number of vertices
#print(len(approx))
## Get the largest contours only
## Side count cannot be used since contours are not all rectangular
if cv2.contourArea(cnt) > lp_area:
#if len(approx) == 4 and cv2.contourArea(cnt) > lp_area:
# print("\n\n")
# print("#################################################")
# print("rectangle")
# print("#################################################")
# print("\n\n")
#tmp_img = img.copy()
#cv2.drawContours(tmp_img, [cnt], 0, (0, 255, 0), 6)
#cv2_imshow(tmp_img)
#cv2.imshow('Contour Borders', tmp_img)
#cv2.waitKey(0)
# tmp_img = img.copy()
# cv2.drawContours(tmp_img, [cnt], 0, (255, 0, 255), -1)
# cv2_imshow(tmp_img)
# #cv2.imshow('Contour Filled', tmp_img)
# #cv2.waitKey(0)
# # Make a hull arround the contour and draw it on the original image
# tmp_img = img.copy()
# mask = np.zeros((img.shape[:2]), np.uint8)
# hull = cv2.convexHull(cnt)
# cv2.drawContours(mask, [hull], 0, (255, 255, 255), -1)
# cv2_imshow(mask)
# #cv2.imshow('Convex Hull Mask', mask)
# #cv2.waitKey(0)
# # Draw minimum area rectangle
# #tmp_img = img.copy()
# rect = cv2.minAreaRect(cnt)
# box = cv2.boxPoints(rect)
# box = np.int0(box)
# cv2.drawContours(tmp_img, [box], 0, (255, 0, 0), 2)
# #cv2_imshow(tmp_img)
# #cv2.imshow('Minimum Area Rectangle', tmp_img)
# #cv2.waitKey(0)
# Draw box corners and minimum area rectangle
#tmp_img = img.copy()
rect = cv2.minAreaRect(cnt)
box = cv2.boxPoints(rect)
box = np.int0(box)
#print(rect)
#print(box)
cv2.drawContours(tmp_img, [box], 0, (0, 50, 255), 3)
cv2.circle(tmp_img, tuple(box[0]), 8, (0, 255, 0), -1)
cv2.circle(tmp_img, tuple(box[1]), 8, (0, 255, 0), -1)
cv2.circle(tmp_img, tuple(box[2]), 8, (0, 255, 0), -1)
cv2.circle(tmp_img, tuple(box[3]), 8, (0, 255, 0), -1)
#cv2_imshow(tmp_img)
#cv2.imshow('Minimum Area Rectangle', tmp_img)
#cv2.waitKey(0)
## Correct orientation and crop
# Link, https://jdhao.github.io/2019/02/23/crop_rotated_rectangle_opencv/
width = int(rect[1][0])
height = int(rect[1][1])
src_pts = box.astype("float32")
dst_pts = np.array([[0, height-1],
[0, 0],
[width-1, 0],
[width-1, height-1]], dtype="float32")
M = cv2.getPerspectiveTransform(src_pts, dst_pts)
warped = cv2.warpPerspective(img, M, (width, height))
#cv2_imshow(warped)
# Run OCR on cropped image
# If the predicted value is digit print else rotate first
result = reader.readtext(warped)
predicted_digit = result[0][1]
print("Detected Text:")
if np.char.isdigit(predicted_digit) == True:
print(result)
print(predicted_digit)
cv2_imshow(warped)
else:
rot_img = warped.copy()
for i in range(0, 3):
rotated_image = cv2.rotate(rot_img, cv2.cv2.ROTATE_90_CLOCKWISE)
result = reader.readtext(rotated_image)
#if np.array(result).size == 0:
# continue
if not result:
rot_img = rotated_image
continue
#if len(result) == 0:
# continue
predicted_digit = result[0][1]
#print(result)
#print(predicted_digit)
#cv2_imshow(rotated_image)
if np.char.isdigit(predicted_digit) == True:
print(result)
print(predicted_digit)
cv2_imshow(rotated_image)
break
rot_img = rotated_image
# # Draw bounding rectangle
# #tmp_img = img.copy()
# x, y, w, h = cv2.boundingRect(cnt)
# cv2.rectangle(tmp_img, (x, y), (x + w, y + h), (255, 0, 0), 2)
# #cv2_imshow(tmp_img)
# #cv2.imshow('Bounding Rectangle', tmp_img)
# #cv2.waitKey(0)
# # Bounding Rectangle and Minimum Area Rectangle
# #tmp_img = img.copy()
# rect = cv2.minAreaRect(cnt)
# box = cv2.boxPoints(rect)
# box = np.int0(box)
# cv2.drawContours(tmp_img, [box], 0, (0, 0, 255), 2)
# x, y, w, h = cv2.boundingRect(cnt)
# cv2.rectangle(tmp_img, (x, y), (x + w, y + h), (0, 255, 0), 2)
# #cv2_imshow(tmp_img)
# #cv2.imshow('Bounding Rectangle', tmp_img)
# #cv2.waitKey(0)
# # determine the most extreme points along the contour
# # https://www.pyimagesearch.com/2016/04/11/finding-extreme-points-in-contours-with-opencv/
# tmp_img = img.copy()
# extLeft = tuple(cnt[cnt[:, :, 0].argmin()][0])
# extRight = tuple(cnt[cnt[:, :, 0].argmax()][0])
# extTop = tuple(cnt[cnt[:, :, 1].argmin()][0])
# extBot = tuple(cnt[cnt[:, :, 1].argmax()][0])
# cv2.drawContours(tmp_img, [cnt], -1, (0, 255, 255), 2)
# cv2.circle(tmp_img, extLeft, 8, (0, 0, 255), -1)
# cv2.circle(tmp_img, extRight, 8, (0, 255, 0), -1)
# cv2.circle(tmp_img, extTop, 8, (255, 0, 0), -1)
# cv2.circle(tmp_img, extBot, 8, (255, 255, 0), -1)
# print("Corner Points: ", extLeft, extRight, extTop, extBot)
# cv2_imshow(tmp_img)
# #cv2.imshow('img contour drawn', tmp_img)
# #cv2.waitKey(0)
# #cv2.destroyAllWindows()
# ## Perspective Transform
# tmp_img = img.copy()
# pts = np.array([extLeft, extRight, extTop, extBot])
# warped = four_point_transform(tmp_img, pts)
# cv2_imshow(tmp_img)
# #cv2.imshow("Warped", warped)
# #cv2.waitKey(0)
cv2_imshow(tmp_img)
#cv2.destroyAllWindows()
Output Prediction
Detected Text:
[([[85, 67], [131, 67], [131, 127], [85, 127]], '1', 0.9992043972015381)]
1
Detected Text:
[([[85, 65], [133, 65], [133, 125], [85, 125]], '2', 0.9991914629936218)]
2
Detected Text:
[([[96, 72], [144, 72], [144, 128], [96, 128]], '4', 0.9996564984321594)]
4
Detected Text:
[([[88, 76], [132, 76], [132, 132], [88, 132]], '3', 0.9973381161689758)]
3
White Region Detection With Corners
Alternate methods,
Try pretrained digit classification model trained from MNIST and others on each large contours exceeding certain area.
Use multitask object detection with rotation. One output of network will be detections another angle regression to predict orientation.
Use text detector like, East and run OCR on each detected text.

How to confirm if a point is in a certain region

I'm making a program in OpenCV-Python that tracks an object of a certain color as it moves around the frame. I want the frame to be divided into four equal parts, with each part representing a different letter. For example, if the object is in quadrant 1, output A. My question is, how do I set up regions on the frame that, when the object is in that region, the program displays that region's letter on the frame. Like, how do I set up rectangles of regions using coordinate points?
Here's the code I have so far, and any help is appreciated.
# import the necessary packages
from collections import deque
from imutils.video import VideoStream
import numpy as np
import argparse
import cv2
import imutils
import time
# construct the argument parse and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-v", "--video",
help="path to the (optional) video file")
ap.add_argument("-b", "--buffer", type=int, default=32,
help="max buffer size")
args = vars(ap.parse_args())
# define the lower and upper boundaries of the "orange"
# fish in the HSV color space
orangeLower = (5, 50, 50)
orangeUpper = (15, 255, 255)
# initialize the list of tracked points, the frame counter,
# and the coordinate deltas
pts = deque(maxlen=args["buffer"])
counter = 0
(dX, dY) = (0, 0)
direction = ""
# if a video path was not supplied, grab the reference
# to the webcam
if not args.get("video", False):
vs = VideoStream(src=0).start()
# otherwise, grab a reference to the video file
else:
vs = cv2.VideoCapture(args["video"])
# allow the camera or video file to warm up
time.sleep(2.0)
# keep looping
while True:
# grab the current frame
frame = vs.read()
# handle the frame from VideoCapture or VideoStream
frame = frame[1] if args.get("video", False) else frame
# if we are viewing a video and we did not grab a frame,
# then we have reached the end of the video
if frame is None:
break
# resize the frame, blur it, and convert it to the HSV
# color space
frame = imutils.resize(frame, width=600)
blurred = cv2.GaussianBlur(frame, (11, 11), 0)
hsv = cv2.cvtColor(blurred, cv2.COLOR_BGR2HSV)
# construct a mask for the color "orange", then perform
# a series of dilations and erosions to remove any small
# blobs left in the mask
mask = cv2.inRange(hsv, orangeLower, orangeUpper)
mask = cv2.erode(mask, None, iterations=2)
mask = cv2.dilate(mask, None, iterations=2)
# find contours in the mask and initialize the current
# (x, y) center of the ball
cnts = cv2.findContours(mask.copy(), cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)
cnts = imutils.grab_contours(cnts)
center = None
# only proceed if at least one contour was found
if len(cnts) > 0:
# find the largest contour in the mask, then use
# it to compute the minimum enclosing circle and
# centroid
c = max(cnts, key=cv2.contourArea)
((x, y), radius) = cv2.minEnclosingCircle(c)
M = cv2.moments(c)
center = (int(M["m10"] / M["m00"]), int(M["m01"] / M["m00"]))
# only proceed if the radius meets a minimum size
if radius > 10:
# draw the circle and centroid on the frame,
# then update the list of tracked points
cv2.circle(frame, (int(x), int(y)), int(radius),
(0, 255, 255), 2)
cv2.circle(frame, center, 5, (0, 0, 255), -1)
pts.appendleft(center)
# loop over the set of tracked points
for i in np.arange(1, len(pts)):
# if either of the tracked points are None, ignore
# them
if pts[i - 1] is None or pts[i] is None:
continue
# check to see if enough points have been accumulated in
# the buffer
if counter >= 10 and i == 10 and pts[i-10] is not None:
# compute the difference between the x and y
# coordinates and re-initialize the direction
# text variables
dX = pts[i-10][0] - pts[i][0]
dY = pts[i-10][1] - pts[i][1]
(dirX, dirY) = ("", "")
# ensure there is significant movement in the
# x-direction
if np.abs(dX) > 20:
dirX = "East" if np.sign(dX) == 1 else "West"
# ensure there is significant movement in the
# y-direction
if np.abs(dY) > 20:
dirY = "South" if np.sign(dY) == 1 else "North"
# handle when both directions are non-empty
if dirX != "" and dirY != "":
direction = "{}-{}".format(dirY, dirX)
# otherwise, only one direction is non-empty
else:
direction = dirX if dirX != "" else dirY
# otherwise, compute the thickness of the line and
# draw the connecting lines
thickness = int(np.sqrt(args["buffer"] / float(i + 1)) * 2.5)
cv2.line(frame, pts[i - 1], pts[i], (0, 0, 255), thickness)
# show the movement deltas and the direction of movement on
# the frame
cv2.putText(frame, direction, (10, 30), cv2.FONT_HERSHEY_SIMPLEX,
0.65, (0, 0, 255), 3)
cv2.putText(frame, "dx: {}, dy: {}".format(dX, dY),
(10, frame.shape[0] - 10), cv2.FONT_HERSHEY_SIMPLEX,
0.35, (0, 0, 255), 1)
# show the frame to the screen and increment the frame counter
cv2.imshow("Frame", frame)
cv2.rectangle(img=frame, pt1=(0, 0), pt2=(300, 225), color=(0, 0, 0), thickness=3, lineType=8, shift=0)
cv2.rectangle(img=frame, pt1 = (300, 1), pt2 = (600, 225), color = (0, 0, 0), thickness = 3, lineType = 8, shift = 0)
cv2.rectangle(img=frame, pt1 = (0, 225), pt2 = (300, 550), color = (0, 0, 0), thickness = 3, lineType = 8, shift = 0)
cv2.rectangle(img=frame, pt1 = (300, 225), pt2 = (600, 550), color = (0, 0, 0), thickness = 3, lineType = 8, shift = 0)
cv2.imshow("Frame", frame)
key = cv2.waitKey(1) & 0xFF
counter += 1
# Set up contours
# if the 'q' key is pressed, stop the loop
if key == ord("q"):
break
# if we are not using a video file, stop the camera video stream
if not args.get("video", False):
vs.stop()
# otherwise, release the camera
else:
vs.release()
# close all windows
cv2.destroyAllWindows()

Video/image analysis to acquire distances between contours

New image: test image
I'm trying to quantify the distance between two contours in a video of a microvessel (see snapshot)
Image analysis structure
Right now I'm only able to select for one contour (which is outlined) and I'm acquiring dimensions from this outline, but what I'd like to select for is the top and bottom contour of the structure and measure the distance (labeled with an orange line and A in the snapshot).
Any suggestions as to do this? My code for this video analysis is the following. Thanks for the help in advance!:
import cv2
import pandas as pd
import numpy as np
import imutils
from scipy.spatial import distance as dist
from imutils import perspective
from imutils import contours
videocapture = cv2.VideoCapture('RTMLV.mp4')
def safe_div(x,y):
if y==0: return 0
return x/y
def nothing(x):
pass
def rescale_frame(frame, percent=100): #make the video windows a bit smaller
width = int(frame.shape[1]*percent/100)
height = int(frame.shape[0]*percent/100)
dim = (width, height)
return cv2.resize(frame, dim, interpolation=cv2.INTER_AREA)
if not videocapture.isOpened():
print("Unable to open video")
exit()
windowName="Vessel Tracking"
cv2.namedWindow(windowName)
# Sliders to adjust image
cv2.createTrackbar("Threshold", windowName, 75, 255, nothing)
cv2.createTrackbar("Kernel", windowName, 5, 30, nothing)
cv2.createTrackbar("Iterations", windowName, 1, 10, nothing)
showLive=True
while(showLive):
ret, frame=videocapture.read()
frame_resize=rescale_frame(frame)
if not ret:
print("Cannot capture the frame")
exit()
thresh = cv2.getTrackbarPos("Threshold", windowName)
ret,thresh1 = cv2.threshold(frame_resize, thresh, 255, cv2.THRESH_BINARY)
kern = cv2.getTrackbarPos("Kernel", windowName)
kernel = np.ones((kern, kern), np.uint8) # square image kernel used for erosion
itera=cv2.getTrackbarPos("Iterations", windowName)
dilation = cv2.dilate(thresh1, kernel, iterations=itera)
erosion = cv2.erode(dilation, kernel, iterations=itera) #refines all edges in the binary image
opening = cv2.morphologyEx(erosion, cv2.MORPH_OPEN, kernel)
closing = cv2.morphologyEx(opening, cv2.MORPH_CLOSE, kernel)
closing = cv2.cvtColor(closing, cv2.COLOR_BGR2GRAY)
contours,hierarchy = cv2.findContours(closing,cv2.RETR_TREE,cv2.CHAIN_APPROX_NONE) # find contours with simple approximation cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE
closing = cv2.cvtColor(closing,cv2.COLOR_GRAY2RGB)
cv2.drawContours(closing, contours, -1, (128,255,0), 1)
# focus on only the largest outline by area
areas = [] #list to hold all areas
for contour in contours:
ar = cv2.contourArea(contour)
areas.append(ar)
max_area = max(areas)
max_area_index = areas.index(max_area) # index of the list element with largest area
cnt = contours[max_area_index - 1] # largest area contour is usually the viewing window itself, why?
cv2.drawContours(closing, [cnt], 0, (0,0,255), 1)
def midpoint(ptA, ptB):
return ((ptA[0] + ptB[0]) * 0.5, (ptA[1] + ptB[1]) * 0.5)
# compute the rotated bounding box of the contour
orig = frame_resize.copy()
box = cv2.minAreaRect(cnt)
box = cv2.cv.BoxPoints(box) if imutils.is_cv2() else cv2.boxPoints(box)
box = np.array(box, dtype="int")
# order the points in the contour such that they appear
# in top-left, top-right, bottom-right, and bottom-left
# order, then draw the outline of the rotated bounding
# box
box = perspective.order_points(box)
cv2.drawContours(orig, [box.astype("int")], -1, (0, 255, 0), 1)
# loop over the original points and draw them
for (x, y) in box:
cv2.circle(orig, (int(x), int(y)), 5, (0, 0, 255), -1)
# unpack the ordered bounding box, then compute the midpoint
# between the top-left and top-right coordinates, followed by
# the midpoint between bottom-left and bottom-right coordinates
(tl, tr, br, bl) = box
(tltrX, tltrY) = midpoint(tl, tr)
(blbrX, blbrY) = midpoint(bl, br)
# compute the midpoint between the top-left and top-right points,
# followed by the midpoint between the top-right and bottom-right
(tlblX, tlblY) = midpoint(tl, bl)
(trbrX, trbrY) = midpoint(tr, br)
# draw the midpoints on the image
cv2.circle(orig, (int(tltrX), int(tltrY)), 5, (255, 0, 0), -1)
cv2.circle(orig, (int(blbrX), int(blbrY)), 5, (255, 0, 0), -1)
cv2.circle(orig, (int(tlblX), int(tlblY)), 5, (255, 0, 0), -1)
cv2.circle(orig, (int(trbrX), int(trbrY)), 5, (255, 0, 0), -1)
# draw lines between the midpoints
cv2.line(orig, (int(tltrX), int(tltrY)), (int(blbrX), int(blbrY)),(255, 0, 255), 1)
cv2.line(orig, (int(tlblX), int(tlblY)), (int(trbrX), int(trbrY)),(255, 0, 255), 1)
cv2.drawContours(orig, [cnt], 0, (0,0,255), 1)
# compute the Euclidean distance between the midpoints
dA = dist.euclidean((tltrX, tltrY), (blbrX, blbrY))
dB = dist.euclidean((tlblX, tlblY), (trbrX, trbrY))
# compute the size of the object
P2M4x = 1.2
P2M10x = 3.2
P2M20x = 6
pixelsPerMetric = P2M10x # Pixel to micron conversion
dimA = dA / pixelsPerMetric
dimB = dB / pixelsPerMetric
dimensions = [dimA, dimB]
# draw the object sizes on the image
cv2.putText(orig, "{:.1f}um".format(dimA), (int(tltrX - 15), int(tltrY - 10)), cv2.FONT_HERSHEY_SIMPLEX, 0.65, (255, 255, 255), 2)
cv2.putText(orig, "{:.1f}um".format(dimB), (int(trbrX + 10), int(trbrY)), cv2.FONT_HERSHEY_SIMPLEX, 0.65, (255, 255, 255), 2)
# compute the center of the contour
M = cv2.moments(cnt)
cX = int(safe_div(M["m10"],M["m00"]))
cY = int(safe_div(M["m01"],M["m00"]))
# draw the contour and center of the shape on the image
cv2.circle(orig, (cX, cY), 5, (255, 255, 255), -1)
cv2.putText(orig, "center", (cX - 20, cY - 20), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 255, 255), 2)
cv2.imshow(windowName, orig)
cv2.imshow('', closing)
if cv2.waitKey(30)>=0:
showLive=False
videocapture.release()
cv2.destroyAllWindows()
Edits have been made to this answer in reponse to the new test image that was added to the post.
I was unable to segment the blood vessel in the test image using the code that you uploaded. I segmented the image by using manual annotation and the GrabCut algorithm.
This is the code that I used for the manual segmentation:
import cv2, os, numpy as np
import time
# Plot with Matplotlib
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
img_path = '/home/stephen/Desktop/0lszR.jpg'
img = cv2.imread(img_path)
img = img[420:1200, :]
h,w,_ = img.shape
mask = np.zeros((h,w), np.uint8)
mask[:] = 2
src = img.copy()
h,w,_ = img.shape
drawing = src.copy()
# Mouse callback function
global k, px, py
k = 0
px, py = 0,0
def callback(event, x, y, flags, param):
global k, px, py
print(x,y, k, px, py)
if k == 115: # 's' for sure background
if px+py!=0:
cv2.line(img, (x,y), (px, py), (255,255,0), 8)
cv2.line(mask, (x,y), (px, py), 0, 8)
if k == 116: # 't' for sure foreground
if px+py!=0:
cv2.line(img, (x,y), (px, py), (0,255,255), 8)
cv2.line(mask, (x,y), (px, py), 1, 8)
else: print(px, py)
px, py = x,y
#if k != 115 or 116: px, py = 0,0
cv2.namedWindow('img')
cv2.setMouseCallback('img', callback)
while k != 27:
cv2.imshow('img', img)
k_temp = cv2.waitKey(1)
if k_temp!=-1: k = k_temp
cv2.destroyAllWindows()
After I had found the segmented image, I used the function np.nonzero() to find the tops and bottoms of the columns:
This is the code that I used to find the width:
# Initialize parameters for the GrabCut algorithm
bgdModel = np.zeros((1,65),np.float64)
fgdModel = np.zeros((1,65),np.float64)
# Apply GrabCut
out_mask = mask.copy()
out_mask, _, _ = cv2.grabCut(src,out_mask,None,bgdModel,fgdModel,1,cv2.GC_INIT_WITH_MASK)
out_mask = np.where((out_mask==2)|(out_mask==0),0,1).astype('uint8')
# Open the mask to fill in the holes
out_img = src*out_mask[:,:,np.newaxis]
flip_mask = cv2.flip(out_mask, 0)
# Find the distances
distances = []
for col_num in range(src.shape[1]-1):
col = out_mask[:, col_num:col_num+1]
flip_col = flip_mask[:, col_num:col_num+1]
top = np.nonzero(col)[0][0]
bottom = h-np.nonzero(flip_col)[0][0]
if col_num % 12 == 0:
cv2.line(drawing, (col_num, top), (col_num, bottom), (234,345,34), 4)
distances.append(bottom-top)
f, axarr = plt.subplots(2,3, sharex=True)
axarr[0,0].imshow(src)
axarr[0,1].imshow(out_mask)
axarr[0,2].imshow(drawing)
axarr[1,0].imshow(img)
axarr[1,1].imshow(out_img)
axarr[1,2].plot(distances)
axarr[0,0].set_title("Source")
axarr[0,1].set_title('Mask from GrabCut')
axarr[0,2].set_title('Widths')
axarr[1,0].set_title('Manual Annotation')
axarr[1,1].set_title('GrabCut Mask')
axarr[1,2].set_title('Graph of Width')
axarr[0,0].axis('off')
axarr[0,1].axis('off')
axarr[1,0].axis('off')
axarr[1,1].axis('off')
axarr[1,2].axis('off')
axarr[0,2].axis('off')
plt.show()

Raspberry Pi OpenCV-2.4.X USB camera distance detection

newb question here... I have been following this guide to detect the distance between an object and the camera.
Here is the code I am currently running:
# import the necessary packages
import numpy as np
import cv2
def find_marker(image):
# convert the image to grayscale, blur it, and detect edges
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
gray = cv2.GaussianBlur(gray, (5, 5), 0)
edged = cv2.Canny(gray, 35, 125)
# find the contours in the edged image and keep the largest one;
# we'll assume that this is our piece of paper in the image
(cnts, _) = cv2.findContours(edged.copy(), cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
c = max(cnts, key = cv2.contourArea)
# compute the bounding box of the of the paper region and return it
return cv2.minAreaRect(c)
def distance_to_camera(knownWidth, focalLength, perWidth):
# compute and return the distance from the maker to the camera
return (knownWidth * focalLength) / perWidth
# initialize the known distance from the camera to the object, which
# in this case is 24 inches
KNOWN_DISTANCE = 24.0
# initialize the known object width, which in this case, the piece of
# paper is 11 inches wide
KNOWN_WIDTH = 11.0
# initialize the list of images that we'll be using
IMAGE_PATHS = ["images/2ft.png", "images/3ft.png", "images/4ft.png"]
# load the furst image that contains an object that is KNOWN TO BE 2 feet
# from our camera, then find the paper marker in the image, and initialize
# the focal length
image = cv2.imread(IMAGE_PATHS[0])
marker = find_marker(image)
focalLength = (marker[1][0] * KNOWN_DISTANCE) / KNOWN_WIDTH
# loop over the images
for imagePath in IMAGE_PATHS:
# load the image, find the marker in the image, then compute the
# distance to the marker from the camera
image = cv2.imread(imagePath)
marker = find_marker(image)
inches = distance_to_camera(KNOWN_WIDTH, focalLength, marker[1][0])
# draw a bounding box around the image and display it
box = np.int0(cv2.cv.BoxPoints(marker))
cv2.drawContours(image, [box], -1, (0, 255, 0), 2)
cv2.putText(image, "%.2fft" % (inches / 12),
(image.shape[1] - 200, image.shape[0] - 20), cv2.FONT_HERSHEY_SIMPLEX,
2.0, (0, 255, 0), 3)
cv2.imshow("image", image)
cv2.waitKey(0)
It works. However, I am unsure as to how to use the code to detect distances between an object and the camera in real-time (video) instead of through a picture taken.
I currently am using a Tello drone with the same code. The difference is I use a video that interpolates contours into rectangles and tracks a model rocket launch. I think what you are looking for is the OpenCV code to understand the video frames. This youtube video uses the Tello video feed and OpenCV to calculate a countour box for a face: https://www.youtube.com/watch?v=LmEcyQnfpDA&t=7253s.
import cv2
from tracker import *
import math, time, numpy as np
# global variables
_w, _h = 0,0
pid = [.01,.01,0]
pError = 0
cap = cv2.VideoCapture("rocketVideo.mp4")
loop = True
rocketPositionList = []
rocketPositionListArea = []
# initialize the known distance from the camera to the object, which
# in this case is 24 inches
KNOWN_DISTANCE = 480
# initialize the known object width, which in this case, the piece of
# paper is 12 inches wide
KNOWN_WIDTH = 5
inches = 0
# distance tracker from Tracker.py
tracker = EuclideanDistTracker()
#object detector
object_detector = cv2.createBackgroundSubtractorMOG2(history=4000,varThreshold=330)
# calulate frame data to get rocket positions in frame
def getFrameCalculation(frame):
if len(rocketPositionListArea) != 0:
i = rocketPositionListArea.index(max(rocketPositionListArea))
return frame, [rocketPositionList[i], rocketPositionListArea[i]]
else:
return frame, [[0,0], 0]
def distance_to_camera(perWidth):
# compute and return the distance from the maker to the camera
return (KNOWN_WIDTH * focalLength) / perWidth
while loop:
# Start Reading OpenCV Video Frame
ret, frame = cap.read()
height, width, _ = frame.shape
w = width
h = height
#extract region of interst
roi = frame[0:1110,0:720]
#Object Detection
mask = object_detector.apply(roi)
contours, _ = cv2.findContours(mask, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
detections = []
for cnt in contours:
#Calcuate area and remove small elements
area = cv2.contourArea(cnt)
# Get Relative Area of Rocket Contour
if area > 100:
x,y,w,h = cv2.boundingRect(cnt)
if x > 210:
detections.append([x,y,w,h])
# update box ids from tracker->detections
boxes_ids = tracker.update(detections)
# create visual data for boxIds
for boxes_id in boxes_ids:
x,y,w,h, id = boxes_id
cv2.putText(roi,str(id),(x,y-15), cv2.FONT_HERSHEY_PLAIN, 1, (255,0,0),2)
cv2.rectangle(roi, (x, y), (x + w, y + h), (0, 255, 0), 3)
# get circle center and area
cx = x + w // 2
cy = y + h // 2
area = w * h
cv2.circle(roi,(cx,cy), 4, (0,0,255), cv2.FILLED)
rocketPositionList.append([cx,cy])
rocketPositionListArea.append(area)
# Get First Known Focal Length
focalLength = (rocketPositionListArea[0] * KNOWN_DISTANCE) / KNOWN_WIDTH
# calculate Img Frame in Video
frame, info = getFrameCalculation(frame)
feetOut = 0
if info[1] > 0:
# Get Inches from Distance to Camera
inches = distance_to_camera(info[1])
# give data to Tello to Operate Movement Action
feetOut = inches / 12
cv2.putText(roi,str(int(feetOut)) + "ft.",(50,50), cv2.FONT_HERSHEY_PLAIN, 4, (255,0,0),2)
# display cv2 videos
cv2.imshow("ROI",resizeR)
cv2.imshow("Mask",resizeM)
cv2.imshow("Frame", resizeF)
# clean up cv2 and exit
cap.release()
cv2.destroyAllWindows()
exit()

Categories