Related
I am using a custom dataset for image segmentation. While visualizing some of the images and masks i found an error. The problem for me know is, how to find the name of the image. The code i use for the pytorch datasetset creation is:
class SegmentationDataset(Dataset):
def __init__(self, df, augmentations):
self.df = df
self.augmentations = augmentations
def __len__(self):
return len(self.df)
def __getitem__(self, idx):
row = self.df.iloc[idx]
image_path = DATA_DIR + row.images
mask_path = DATA_DIR + row.masks
image = skimage.io.imread(image_path)
mask = skimage.io.imread(mask_path)
mask = np.expand_dims(mask, axis = -1)
if self.augmentations:
data = self.augmentations(image = image, mask = mask)
image = data['image']
mask = data['mask']
image = np.transpose(image, (2, 0, 1)).astype(np.float32)
mask = np.transpose(mask, (2, 0, 1)).astype(np.float32)
image = torch.Tensor(image) / 255.0
mask = torch.round(torch.Tensor(mask) / 255.0)
return image, mask
trainset = SegmentationDataset(train_df, get_train_augs())
validset = SegmentationDataset(valid_df, get_valid_augs())
When i then print one specific image, i see that the mask is not available/wrong:
idx = 9
print('Drawn sample ID:', idx)
image, mask = validset[idx]
show_image(image, mask)
How do i now get the image name of this idx = 9?
I'd imagine you could print out one of the following, under this line image = skimage.io.imread(image_path), it should help lead you to your answer:
print(row)
print(row.images)
print(images)
print(image_path)
To get the file name after you have parsed the fully quaified path above:
my_str = '/my/data/path/images/wallpaper.jpg'
result = my_str.rsplit('/', 1)[1]
print(result) # 'wallpaper.jpg'
with_slash = '/' + my_str.rsplit('/', 1)[1]
print(with_slash) # '/wallpaper.jpg'
['/my/data/path/images/', 'wallpaper.jpg']
print(my_str.rsplit('/', 1)[1])
i want to build 3d scanner with stereo camera and LED Projector. I calibrated the stereo camera and created the mechanical system. I project gray code and capture them with two camera. I decoded the images and take correspondence image. But i can't triangulate the decoded points. This is my reference project for generate pattern and decode them.
Reference Github project
And this is my code
import numpy as np
import cv2
import structuredlight as sl
def generate_rectify_data(calib_data, size):
XML_File = cv2.FileStorage(calib_data, cv2.FILE_STORAGE_READ)
M1 = XML_File.getNode('Camera_Matrix_Left').mat()
M2 = XML_File.getNode('Camera_Matrix_Right').mat()
d1 = XML_File.getNode('Camera_Distortion_Left').mat()
d2 = XML_File.getNode('Camera_Distortion_Right').mat()
R = XML_File.getNode('Rotation_Matrix').mat()
t = XML_File.getNode('Translation_Matrix').mat()
flag = cv2.CALIB_ZERO_DISPARITY
R1, R2, P1, P2, Q = cv2.stereoRectify(cameraMatrix1=M1, cameraMatrix2=M2,
distCoeffs1=d1, distCoeffs2=d2, R=R, T=t, flags=flag, alpha=-1, imageSize=size,
newImageSize=size)[0:5]
map_x_l, map_y_l = cv2.initUndistortRectifyMap(M1, d1, R1, P1, size, cv2.CV_32FC1)
map_x_r, map_y_r = cv2.initUndistortRectifyMap(M2, d2, R2, P2, size, cv2.CV_32FC1)
return map_x_l, map_y_l, map_x_r, map_y_r, P1, P2,Q
def rectify(img, map_x, map_y):
res = cv2.remap(img, map_x, map_y, cv2.INTER_LINEAR, cv2.BORDER_CONSTANT)
return res
"""
***I generate pattern like this and capture them in another python script***
W = 240
H = 240
gray = sl.Gray()
imlist_posi_x_pat = gray.generate((W, H))
imlist_posi_y_pat = sl.transpose(gray.generate((H, W)))
"""
if __name__ == '__main__':
img_size = (1648, 1232)
map_x_l, map_y_l, map_x_r, map_y_r, P1, P2, Q = generate_rectify_data(
"C:/Users/XXX/PycharmProjects/Stereo_Structured_Light/Calibration_Data"
"/Calibration_Parameters_1.xml", size=(1648, 1232))
rect_list_l, rect_list_r = [], []
imlist_posi_x_cap_R = []
imlist_posi_y_cap_R = []
imlist_posi_x_cap_L = []
imlist_posi_y_cap_L = []
for i in range(0,16):
img_l = cv2.imread("C:/OxO_Scan/Images_1/Left_cam3/L_" + str(i) + ".png", 0)
img_r = cv2.imread("C:/OxO_Scan/Images_1/Right_cam3/R_" + str(i) + ".png", 0)
l_rect = rectify(img_l, map_x_l, map_y_l)
r_rect = rectify(img_r, map_x_r, map_y_r)
if i < 8: # 8 for the horizontal, 8 for the vertical pattern images
imlist_posi_x_cap_R.append(r_rect)
imlist_posi_x_cap_L.append(l_rect)
else:
imlist_posi_y_cap_R.append(r_rect)
imlist_posi_y_cap_L.append(l_rect)
W = 240
H = 240
gray = sl.Gray()
img_index_x_R = gray.decode(imlist_posi_x_cap_R, thresh=40)
img_index_x_L = gray.decode(imlist_posi_x_cap_L, thresh=40)
img_index_y_R = gray.decode(imlist_posi_y_cap_R, thresh=40)
img_index_y_L = gray.decode(imlist_posi_y_cap_L, thresh=40)
img_correspondence_x_r = cv2.merge([0.0 * np.zeros_like(img_index_x_R),
img_index_x_R / W, img_index_y_R / H])
img_correspondence_r = np.clip(img_correspondence_x_r * 255.0, 0,
255).astype(np.uint8)
img_correspondence_y_l = cv2.merge([0.0 * np.zeros_like(img_index_x_L),
img_index_x_L / W, img_index_y_L / H])
img_correspondence_l = np.clip(img_correspondence_y_l * 255.0, 0,
255).astype(np.uint8)
####################################
cv2.imshow("a", cv2.resize(img_correspondence_l, (640, 480)))
cv2.imshow("b", cv2.resize(img_correspondence_r, (640, 480)))
cv2.waitKey()
cv2.destroyAllWindows()
img_correspondence_L_2 = np.copy(img_correspondence_l)
img_correspondence_R_2 = np.copy(img_correspondence_r)
cam_pts_l, cam_pts_r = [], []
cam_pts_l2, cam_pts_r2 = [], []
for i in range(img_correspondence_l.shape[0]):
for j in range(img_correspondence_l.shape[1]):
if (img_correspondence_l[i][j] != 0).any():
qwert = img_index_x_L[i][j]
cam_pts_l.append([j, i])
cam_pts_r.append([j+qwert, i])
cam_pts_l = np.array(cam_pts_l, dtype=np.float32)
cam_pts_r = np.array(cam_pts_r, dtype=np.float32)
cam_pts_l = np.array(cam_pts_l)[:, np.newaxis, :]
cam_pts_r = np.array(cam_pts_r)[:, np.newaxis, :]
pts4D = cv2.triangulatePoints(P1, P2, np.float32(cam_pts_l),np.float32(cam_pts_r)).T
pts3D = (pts4D[:, :3] / pts4D[:, -1:])
I don't know what to do in code for loop "for i in range(img_correspondence_l.shape[0]):" For example, I cannot find where a point that I found using left correspondence image in the left camera image corresponds to in the right camera image. j+img_index_x_L[i][j] does not give correct results. What should i do here
Thanks for your answers
I've an issues to implement PixelRL. PixelRL github. I'd like to reading and saving an image to raw data with int16 ( -32768 ~ 32767 ). But I don't find how to make cv2.imwrite() support it. When using p = (p[0]*65535+0.5).astype(np.int16), saving 8bit images. Is there a way to write the image to int16 and raw data?
Thank you.
class MiniBatchLoader(object):
def __init__(self, train_path, test_path, image_dir_path, crop_size):
# load data paths
self.training_path_infos = self.read_paths(train_path, image_dir_path)
self.testing_path_infos = self.read_paths(test_path, image_dir_path)
self.crop_size = crop_size
# test ok
#staticmethod
def path_label_generator(txt_path, src_path):
for line in open(txt_path):
line = line.strip()
src_full_path = os.path.join(src_path, line)
if os.path.isfile(src_full_path):
yield src_full_path
# test ok
#staticmethod
def count_paths(path):
c = 0
for _ in open(path):
c += 1
return c
# test ok
#staticmethod
def read_paths(txt_path, src_path):
cs = []
for pair in MiniBatchLoader.path_label_generator(txt_path, src_path):
cs.append(pair)
return cs
def load_training_data(self, indices):
return self.load_data(self.training_path_infos, indices, augment=True)
def load_testing_data(self, indices):
return self.load_data(self.testing_path_infos, indices)
# test ok
def load_data(self, path_infos, indices, augment=False):
mini_batch_size = len(indices)
in_channels = 1
if augment:
xs = np.zeros((mini_batch_size, in_channels, self.crop_size, self.crop_size)).astype(np.float32)
for i, index in enumerate(indices):
path = path_infos[index]
img = cv2.imread(path,0)
if img is None:
raise RuntimeError("invalid image: {i}".format(i=path))
h, w = img.shape
if np.random.rand() > 0.5:
img = np.fliplr(img)
if np.random.rand() > 0.5:
angle = 10*np.random.rand()
if np.random.rand() > 0.5:
angle *= -1
M = cv2.getRotationMatrix2D((w/2,h/2),angle,1)
img = cv2.warpAffine(img,M,(w,h))
rand_range_h = h-self.crop_size
rand_range_w = w-self.crop_size
x_offset = np.random.randint(rand_range_w)
y_offset = np.random.randint(rand_range_h)
img = img[y_offset:y_offset+self.crop_size, x_offset:x_offset+self.crop_size]
xs[i, 0, :, :] = (img/255).astype(np.float32)
elif mini_batch_size == 0:
for i, index in enumerate(indices):
path = path_infos[index]
img = cv2.imread(path,0)
if img is None:
raise RuntimeError("invalid image: {i}".format(i=path))
h, w = img.shape
xs = np.zeros((mini_batch_size, in_channels, h, w)).astype(np.float16)
xs[0, 0, :, :] = (img/255).astype(np.float16)
else:
raise RuntimeError("mini batch size must be 1 when testing")
return xs
def test(loader, agent, fout):
sum_psnr = 0
sum_reward = 0
test_data_size = MiniBatchLoader.count_paths(TESTING_DATA_PATH)
current_state = State.State((TEST_BATCH_SIZE,1,CROP_SIZE,CROP_SIZE), MOVE_RANGE)
for i in range(0, test_data_size, TEST_BATCH_SIZE):
raw_x = loader.load_testing_data(np.array(range(i, i+TEST_BATCH_SIZE)))
raw_n = np.random.normal(MEAN,SIGMA,raw_x.shape).astype(raw_x.dtype)/255
current_state.reset(raw_x,raw_n)
reward = cp.zeros(raw_x.shape, raw_x.dtype)*255
for t in range(0, EPISODE_LEN):
previous_image = current_state.image.copy()
action, inner_state = agent.act(current_state.tensor)
current_state.step(action, inner_state)
reward = np.square(raw_x - previous_image)*255 - np.square(raw_x - current_state.image)*255
sum_reward += cp.mean(reward)*cp.power(GAMMA,t)
agent.stop_episode()
p = np.maximum(0,current_state.image)
p = np.minimum(1,p)
p = (p[0]*65535+0.5).astype(np.int16)
p = cp.transpose(p,(1,2,0))
cv2.imwrite(output_save_path+'/'+str(i)+'.tiff',p)
is there a way ... ?
No.
https://docs.opencv.org/3.4/d4/da8/group__imgcodecs.html#gabbc7ef1aa2edfaa87772f1202d67e0ce
In general, only 8-bit single-channel or 3-channel ... images can be saved using this function, with these exceptions:
16-bit unsigned (CV_16U) images can be saved ...
You might want to munge your signed 16-bit values into CV_16U format.
Alternatively, you might consider writing 32-bit images, and then invoking a post-processing program to shrink them to your favorite 16-bit format.
I have a little project with OpenCV (python) where one of my steps is to take an x-ray image from the human body and convert it to a binary image where white pixels represent where some bone is present and black means there is no bone there.
Since sometimes "bone parts" can be darker than "non-bone parts" from another region, simple thresholding won't work. I also tried adaptive threshold and I couldn't see much difference.
I came up with a simple algorithm that applies a simple threshold for each row.
Here is the code:
def threshhold(image, val):
image = image.copy()
for row_idx in range(image.shape[0]):
max_row = image[row_idx].max()
min_row = image[row_idx].min()
tresh = np.median(image[row_idx]) + (val * (max_row - min_row))
# Or use np.mean instead of np.median
_, tresh = cv2.threshold(image[row_idx], tresh, 255, cv2.THRESH_BINARY)
image[row_idx] = tresh.ravel()
return image
And here is the code that does the same work but column-by-column instead of row-by-row:
def threshhold2(image, val):
image = image.copy()
for row_idx in range(image.shape[1]):
max_row = image[:, row_idx].max()
min_row = image[:, row_idx].min()
tresh = np.median(image[:, row_idx]) + (val * (max_row - min_row))
# Or use np.mean instead of np.median
_, tresh = cv2.threshold(image[:, row_idx], tresh, 255, cv2.THRESH_BINARY)
image[:, row_idx] = tresh.ravel()
return image
This method works pretty well with images like this:
Not quite well for this one but it is not that bad:
Very terrible:
Only the left half looks good
...
As you can see; this algorithm works well only for some images.
I will be glad to see more experienced people's ideas.
Images are not for me by the way.
Entire source code:
import os
import cv2
import numpy as np
files_to_see = os.listdir("data_set")
files_to_see.sort()
current_file = 0
print(files_to_see)
def slice(image, size):
out = []
x_count = image.shape[1] // size
y_count = image.shape[0] // size
for y_idx in range(y_count):
for x_idx in range(x_count):
out.append(
(
(y_idx, x_idx),
image[y_idx * size: (y_idx + 1) * size,
x_idx * size: (x_idx + 1) * size]
)
)
return y_count, x_count, out
def normalize(image):
image = image.copy()
min_pix = image.min()
max_pix = image.max()
for y in range(image.shape[0]):
for x in range(image.shape[1]):
val = image[y, x]
val -= min_pix
val *= 255 / (max_pix - min_pix)
image[y, x] = round(val)
# image -= min_pix
# image *= round(255 / (max_pix - min_pix))
return image
def threshhold(image, val, method):
image = image.copy()
for row_idx in range(image.shape[0]):
max_row = image[row_idx].max()
min_row = image[row_idx].min()
# tresh = np.median(image[row_idx]) + (val * (max_row - min_row))
tresh = method(image[row_idx]) + (val * (max_row - min_row))
_, tresh = cv2.threshold(image[row_idx], tresh, 255, cv2.THRESH_BINARY)
image[row_idx] = tresh.ravel()
return image
def threshhold2(image, val, method):
image = image.copy()
for row_idx in range(image.shape[1]):
max_row = image[:, row_idx].max()
min_row = image[:, row_idx].min()
tresh = method(image[:, row_idx]) + (val * (max_row - min_row))
_, tresh = cv2.threshold(image[:, row_idx], tresh, 255, cv2.THRESH_BINARY)
image[:, row_idx] = tresh.ravel()
return image
def recalculate_threshhold(v):
global original_current_image, thresh_current_image, y_c, x_c, slices
method = np.mean
if cv2.getTrackbarPos("method", "xb labeler") == 0:
method = np.median
thresh_current_image = threshhold2(original_current_image, cv2.getTrackbarPos("threshhold_value", "xb labeler") / 1000, method)
y_c, x_c, slices = slice(thresh_current_image, 128)
def thresh_current_image_mouse_event(event, x, y, flags, param):
if event == 1:
print(x // 128, y // 128)
cv2.imshow("slice", slices[(x // 128) + (y // 128) * x_c][1])
cv2.namedWindow("xb labeler")
cv2.createTrackbar("threshhold_value", "xb labeler", 0, 1000, recalculate_threshhold)
cv2.createTrackbar("method", "xb labeler", 0, 1, recalculate_threshhold)
cv2.namedWindow("thresh_current_image")
cv2.setMouseCallback("thresh_current_image", thresh_current_image_mouse_event)
def init():
global original_current_image, thresh_current_image, x_c, y_c, slices, files_to_see, current_file
original_current_image = cv2.imread("data_set/" + files_to_see[current_file], cv2.CV_8UC1)
original_current_image = cv2.resize(original_current_image, (512, 512))
original_current_image = normalize(original_current_image)
original_current_image = cv2.GaussianBlur(original_current_image, (5, 5), 10)
recalculate_threshhold(1)
y_c, x_c, slices = slice(thresh_current_image, 128)
init()
while True:
cv2.imshow("thresh_current_image", thresh_current_image)
cv2.imshow("xb labeler", original_current_image)
k = cv2.waitKey(1)
if k == ord('p'):
cv2.imwrite("ssq.png", thresh_current_image)
current_file += 1
init()
cv2.destroyAllWindows()
EDIT: Added original images:
I want to detect crop rows using aerial images(CRBD). I have done the necessary image processing like converting to grayscale, edge detection, skeletonization, Hough Transform(to identify and draw the lines), and I also set the accumulator angle to math.pi*4.0/180, which I varied time after time.
The algorithm works well at detection approximately 4 crop lines, I want to improve it so that it can detect variable number of crop rows, and it should be able to highlight this crop rows
Here is a link to the sample code I modified Here
import os
import os.path
import time
import cv2
import numpy as np
import math
### Setup ###
image_data_path = os.path.abspath('../8470p/CRBD/Images')
gt_data_path = os.path.abspath('../8470p/GT data')
image_out_path = os.path.abspath('../8470p/algorithm_1')
use_camera = False # whether or not to use the test images or camera
images_to_save = [2, 3, 4, 5] # which test images to save
timing = False # whether to time the test images
curr_image = 0 # global counter
HOUGH_RHO = 2 # Distance resolution of the accumulator in pixels
HOUGH_ANGLE = math.pi*4.0/18 # Angle resolution of the accumulator in radians
HOUGH_THRESH_MAX = 80 # Accumulator threshold parameter. Only those lines are
returned that get votes
HOUGH_THRESH_MIN = 10
HOUGH_THRESH_INCR = 1
NUMBER_OF_ROWS = 10 # how many crop rows to detect
THETA_SIM_THRESH = math.pi*(6.0/180) # How similar two rows can be
RHO_SIM_THRESH = 8 # How similar two rows can be
ANGLE_THRESH = math.pi*(30.0/180) # How steep angles the crop rows can be in
radians
def grayscale_transform(image_in):
'''Converts RGB to Grayscale and enhances green values'''
b, g, r = cv2.split(image_in)
return 2*g - r - b
def save_image(image_name, image_data):
'''Saves image if user requests before runtime'''
if curr_image in images_to_save:
image_name_new = os.path.join(image_out_path, "
{0}_{1}.jpg".format(image_name,
str(curr_image) ))
def skeletonize(image_in):
'''Inputs and grayscale image and outputs a binary skeleton image'''
size = np.size(image_in)
skel = np.zeros(image_in.shape, np.uint8)
ret, image_edit = cv2.threshold(image_in, 0, 255, cv2.THRESH_BINARY |
cv2.THRESH_OTSU)
element = cv2.getStructuringElement(cv2.MORPH_CROSS, (3,3))
done = False
while not done:
eroded = cv2.erode(image_edit, element)
temp = cv2.dilate(eroded, element)
temp = cv2.subtract(image_edit, temp)
skel = cv2.bitwise_or(skel, temp)
image_edit = eroded.copy()
zeros = size - cv2.countNonZero(image_edit)
if zeros == size:
done = True
return skel
def tuple_list_round(tuple_list, ndigits_1=0, ndigits_2=0):
'''Rounds each value in a list of tuples to the number of digits
specified
'''
new_list = []
for (value_1, value_2) in tuple_list:
new_list.append( (round(value_1, ndigits_1), round(value_2,
ndigits_2)) )
return new_list
def crop_point_hough(crop_points):
'''Iterates though Hough thresholds until optimal value found for
the desired number of crop rows. Also does filtering.
'''
height = len(crop_points)
width = len(crop_points[0])
hough_thresh = HOUGH_THRESH_MAX
rows_found = False
while hough_thresh > HOUGH_THRESH_MIN and not rows_found:
crop_line_data = cv2.HoughLines(crop_points, HOUGH_RHO, HOUGH_ANGLE,
hough_thresh)
crop_lines = np.zeros((height, width, 3), dtype=np.uint8)
crop_lines_hough = np.zeros((height, width, 3), dtype=np.uint8)
if crop_line_data is not None:
# get rid of duplicate lines. May become redundant if a similarity
threshold is done
crop_line_data_1 = tuple_list_round(crop_line_data[:,0,:],-1, 4)
crop_line_data_2 = []
x_offsets = []
crop_lines_hough = np.zeros((height, width, 3), dtype=np.uint8)
for (rho, theta) in crop_line_data_1:
a = math.cos(theta)
b = math.sin(theta)
x0 = a*rho
y0 = b*rho
point1 = (int(round(x0+1000*(-b))), int(round(y0+1000*(a))))
point2 = (int(round(x0-1000*(-b))), int(round(y0-1000*(a))))
cv2.line(crop_lines_hough, point1, point2, (0, 0, 255), 2)
for curr_index in range(len(crop_line_data_1)):
(rho, theta) = crop_line_data_1[curr_index]
is_faulty = False
if ((theta >= ANGLE_THRESH) and (theta <= math.pi-
ANGLE_THRESH)) or(theta <= 0.001):
is_faulty = True
else:
for (other_rho, other_theta) in
crop_line_data_1[curr_index+1:]:
if abs(theta - other_theta) < THETA_SIM_THRESH:
is_faulty = True
elif abs(rho - other_rho) < RHO_SIM_THRESH:
is_faulty = True
if not is_faulty:
crop_line_data_2.append( (rho, theta) )
for (rho, theta) in crop_line_data_2:
a = math.cos(theta)
b = math.sin(theta)
c = math.tan(theta)
x0 = a*rho
y0 = b*rho
point1 = (int(round(x0+1000*(-b))), int(round(y0+1000*(a))))
point2 = (int(round(x0-1000*(-b))), int(round(y0-1000*(a))))
cv2.line(crop_lines, point1, point2, (0, 0, 255), 2)
#cv2.circle(crop_lines, (np.clip(int(round(a*rho+c*
#(0.5*height))),0 ,239), 0), 4, (255,0,0), -1)
#cv2.circle(crop_lines, (np.clip(int(round(a*rho-c*
#(0.5*height))),0 ,239), height), 4, (255,0,0), -1)
cv2.circle(crop_lines, (np.clip(int(round(rho/a)),0 ,239), 0), 5,
(255,0,0), -1)
#cv2.circle(img,(447,63), 63, (0,0,255), -1)
x_offsets.append(np.clip(int(round(rho/a)),0 ,239))
cv2.line(crop_lines, point1, point2, (0, 0, 255), 2)
if len(crop_line_data_2) >= NUMBER_OF_ROWS:
rows_found = True
hough_thresh -= HOUGH_THRESH_INCR
if rows_found == False:
print(NUMBER_OF_ROWS, "rows_not_found")
x_offset = min (x_offsets)
width = max (x_offsets) - min (x_offsets)
return (crop_lines, crop_lines_hough, x_offset, width)
def crop_row_detect(image_in):
'''Inputs an image and outputs the lines'''
save_image('0_image_in', image_in)
### Grayscale Transform ###
image_edit = grayscale_transform(image_in)
save_image('1_image_gray', image_edit)
### Skeletonization ###
skeleton = skeletonize(image_edit)
save_image('2_image_skeleton', skeleton)
### Hough Transform ###
(crop_lines, crop_lines_hough, x_offset, width) =
crop_point_hough(skeleton)
save_image('3_image_hough',cv2.addWeighted(image_in, 1,
crop_lines_hough, 1, 0.0))
save_image('4_image_lines',cv2.addWeighted(image_in, 1,crop_lines,1,0.0))
return (crop_lines , x_offset, width)
def main():
if use_camera == False:
diff_times = []
for image_name in sorted(os.listdir(image_data_path)):
global curr_image
curr_image += 1
start_time = time.time()
image_path = os.path.join(image_data_path, image_name)
image_in = cv2.imread(image_path)
crop_lines = crop_row_detect(image_in)
if timing == False:
cv2.imshow(image_name, cv2.addWeighted(image_in, 1,
crop_lines, 1, 0.0))
print('Press any key to continue...')
cv2.waitKey()
cv2.destroyAllWindows()
### Timing ###
else:
diff_times.append(time.time() - start_time)
mean = 0
for diff_time in diff_times:
mean += diff_time
### Display Timing ###
print('max time = {0}'.format(max(diff_times)))
print('ave time = {0}'.format(1.0 * mean / len(diff_times)))
cv2.waitKey()
else: # use camera. Hasn't been tested on a farm.
capture = cv2.VideoCapture(0)
while cv2.waitKey(1) < 0:
_, image_in = capture.read()
(crop_lines, x_offset, width) = crop_row_detect(image_in)
cv2.imshow("Webcam", cv2.addWeighted(image_in, 1, crop_lines, 1,
0.0))
capture.release()
cv2.destroyAllWindows()
main()
Input Image
[![Input Image][1]][1]
Output Image
[![][4]][4]
Expected Output
[![Expected Output][5]][5]
I have tried thresholding with cv2.inRange() to find green lines, but am still not getting the desired out.
Also the algorithms seems to be only draw the crop_line_data_2 as shown in the Output Image, it doesn't draw the crop_line_data_1
def threshold_green(image_in):
hsv = cv2.cvtColor(image_in, cv2.COLOR_BGR2HSV)
## mask of green (36,25,25) ~ (86, 255,255)
# mask = cv2.inRange(hsv, (36, 25, 25), (86, 255,255))
mask = cv2.inRange(hsv, (36, 25, 25), (70, 255,255))
## slice the green
imask = mask>0
green = np.zeros_like(image_in, np.uint8)
green[imask] = image_in[imask]
return green