So I was working on instance segmentation but now I am just able to segment 1 of the object from the image.
So I run the below codes to get my output:
image2 = mpimg.imread(path_to_new_image)
# Run object detection
print(len([image2]))
results = model.detect([image2], verbose=1)
# Display results
ax = get_ax(1)
r2 = results[0]
visualize.display_instances(image2, r2['rois'], r2['masks'], r2['class_ids'],
dataset.class_names, r2['scores'], ax=ax, title="Predictions3")
And the output I get is as followed:
1
Then I run the following codes to crop the image based on the mask, but I only able to crop one of it...
2
So how can I crop both of them, instead of 1 mask only?
the reason you are getting only one region cropped is because you're taking your index to be r2['scores'].argmax(). This will only consider that building which has the highest score, blue region in your case.
Change the code from:
idx = r2['scores'].argmax()
To:
for idx in range(len(r2['scores']):
And apply some small modifications to make it run.
Related
I'm trying to combine the two images based on the information from the mask. I'm using the color information from the background image if the mask is 0 and color information from foreground image if the mask is 1. Because the mask and both
Images are of the same size, I would like to use logical indexing of matrices to achieve this.
My attempt:
mask = imread('mask.png');
foreground = imread('fg.jpg');
background = imread('bg.jpg');
[r,c,~]=size(mask);
A = zeros(size(mask));
for i=1:r
for j=1:c
if mask(i,j) == 0
A(i,j,:) = background(i,j,:);
end
if mask(i,j) > 0
A(i,j,:) = foreground(i,j,:);
end
end
end
imshow(A);
The result looks like a flickering blue image, but I don't want that. Please help.
You can do this a bit more concisely:
f = double(foreground).*double(mask);
b = double(background).*double(~mask);
blend = f+b;
imshow(blend, []);
Using logical indexing you could also do
foreground(logical(mask)) = 0;
background(logical(~mask)) = 0;
blend = foreground+background;
The ISNOT operator '~' inverts your matrix in the second line, so you cut out the area you would like for background.
NOTE: This works for black and white (one channel). For coloured images see rayryeng's solution.
There are two problems with your code. The first problem is that you are trying to assign colour pixels to the output image A, yet this image is only two-dimensional. You want an image with three channels, not two. In addition, the output image type you are specifying is wrong. By default, the output image A is of type double, yet you are copying values into it that aren't double... most likely unsigned 8-bit integer.
As such, cast the image to the same type as the input images. Assuming both input images are the same type, initialize your A so that:
A = zeros(size(foreground), class(foreground));
This correctly makes a colour image with the same type as any of the inputs, assuming that they're both the same type.
Now, your for loop is fine, but it's better if you do this in one shot with logical indexing. If you want to use logical indexing, create a new image that's initially blank like what you've done, but then make sure your mask has three channels to match the number of channels the other images have. After, you simply need to index into each image and set the right locations accordingly:
mask = imread('mask.png');
foreground = imread('fg.jpg');
background = imread('bg.jpg');
[r,c,d]=size(mask); %// Change
%// If your mask isn't three channels, make it so
%// Change
if d ~= 3
mask = cat(3, mask, mask, mask);
end
A = zeros(size(foreground), class(foreground)); %// Change
A(mask) = foreground(mask); %// Assign pixels to foreground
A(~mask) = background(~mask); %// Assign pixels to background
imshow(A);
My project is to detect human activity through stored video clips.
I am successfully able to do the following:
Get the Motion History Image (MHI) from a video using OpenCV
Train and classify the set of images using Matlab
However, I want to use Matlab in order to get the Motion History Image (MHI). Is it possible, and if yes can someone guide me? Thank you.
I have attached a sample Motion History Image (MHI)
I have used the following code for MHI:
http://www.ece.iastate.edu/~alexs/classes/2007_Fall_401/code/09_MotionHistory/motempl.c
MHI is just a ways of implementing motion detection (and uses silhouettes as the basis of it).
Let suppose that the silhouette of the most recent object has been created. It also uses a timestamp to identify if the current silhouette is recent or not. The older silhouettes have to be compared with the current silhouette in order to achieve movement detection. Hence, earlier silhouettes are also saved in the image, with an earlier timestamp.
MHI describes the changes of some moving objects over the image sequence. Basically, you should only maintain an image where every pixel encodes a time information - whether the silhouette is recent or not or where the movement occurs at a given time.
Therefore the implementation of MHI is very simple e.g.:
function MHI = MHI(fg)
% Initialize the output, MHI a.k.a. H(x,y,t,T)
MHI = fg;
% Define MHI parameter T
T = 15; % # of frames being considered; maximal value of MHI.
% Load the first frame
frame1 = fg{1};
% Get dimensions of the frames
[y_max x_max] = size(frame1);
% Compute H(x,y,1,T) (the first MHI)
MHI{1} = fg{1} .* T;
% Start global loop for each frame
for frameIndex = 2:length(fg)
%Load current frame from image cell
frame = fg{frameIndex};
% Begin looping through each point
for y = 1:y_max
for x = 1:x_max
if (frame(y,x) == 255)
MHI{frameIndex}(y,x) = T;
else
if (MHI{frameIndex-1}(y,x) > 1)
MHI{frameIndex}(y,x) = MHI{frameIndex-1}(y,x) - 1;
else
MHI{frameIndex}(y,x) = 0;
end
end
end
end
end
Code from: https://searchcode.com/codesearch/view/8509149/
Update #1:
Try to draw it as follows:
% showMHI.m
% Input frame number and motion history vector to display normalized MHI
% at the specified frame.
function showMHI(n, motion_history)
frameDisp = motion_history{n};
frameDisp = double(frameDisp);
frameDisp = frameDisp ./ 15;
figure, imshow(frameDisp)
title('MHI Image');
Below is the current working code in python using PIL for highlighting the difference between the two images. But rest of the images is blacken.
Currently i want to show the background as well along with the highlighted image.
Is there anyway i can keep the show the background lighter and just highlight the differences.
from PIL import Image, ImageChops
point_table = ([0] + ([255] * 255))
def black_or_b(a, b):
diff = ImageChops.difference(a, b)
diff = diff.convert('L')
# diff = diff.point(point_table)
h,w=diff.size
new = diff.convert('RGB')
new.paste(b, mask=diff)
return new
a = Image.open('i1.png')
b = Image.open('i2.png')
c = black_or_b(a, b)
c.save('diff.png')
!https://drive.google.com/file/d/0BylgVQ7RN4ZhTUtUU1hmc1FUVlE/view?usp=sharing
PIL does have some handy image manipulation methods,
but also a lot of shortcomings when one wants
to start doing serious image processing -
Most Python lterature will recomend you to switch
to use NumPy over your pixel data, wich will give
you full control -
Other imaging libraries such as leptonica, gegl and vips
all have Python bindings and a range of nice function
for image composition/segmentation.
In this case, the thing is to imagine how one would
get to the desired output in an image manipulation program:
You'd have a black (or other color) shade to place over
the original image, and over this, paste the second image,
but using a threshold (i.e. a pixel either is equal or
is different - all intermediate values should be rounded
to "different) of the differences as a mask to the second image.
I modified your function to create such a composition -
from PIL import Image, ImageChops, ImageDraw
point_table = ([0] + ([255] * 255))
def new_gray(size, color):
img = Image.new('L',size)
dr = ImageDraw.Draw(img)
dr.rectangle((0,0) + size, color)
return img
def black_or_b(a, b, opacity=0.85):
diff = ImageChops.difference(a, b)
diff = diff.convert('L')
# Hack: there is no threshold in PILL,
# so we add the difference with itself to do
# a poor man's thresholding of the mask:
#(the values for equal pixels- 0 - don't add up)
thresholded_diff = diff
for repeat in range(3):
thresholded_diff = ImageChops.add(thresholded_diff, thresholded_diff)
h,w = size = diff.size
mask = new_gray(size, int(255 * (opacity)))
shade = new_gray(size, 0)
new = a.copy()
new.paste(shade, mask=mask)
# To have the original image show partially
# on the final result, simply put "diff" instead of thresholded_diff bellow
new.paste(b, mask=thresholded_diff)
return new
a = Image.open('a.png')
b = Image.open('b.png')
c = black_or_b(a, b)
c.save('c.png')
Here's a solution using libvips:
import sys
from gi.repository import Vips
a = Vips.Image.new_from_file(sys.argv[1], access = Vips.Access.SEQUENTIAL)
b = Vips.Image.new_from_file(sys.argv[2], access = Vips.Access.SEQUENTIAL)
# a != b makes an N-band image with 0/255 for false/true ... we have to OR the
# bands together to get a 1-band mask image which is true for pixels which
# differ in any band
mask = (a != b).bandbool("or")
# now pick pixels from a or b with the mask ... dim false pixels down
diff = mask.ifthenelse(a, b * 0.2)
diff.write_to_file(sys.argv[3])
With PNG images, most CPU time is spent in PNG read and write, so vips is only a bit faster than the PIL solution.
libvips does use a lot less memory, especially for large images. libvips is a streaming library: it can load, process and save the result all at the same time, it does not need to have the whole image loaded into memory before it can start work.
For a 10,000 x 10,000 RGB tif, libvips is about twice as fast and needs about 1/10th the memory.
If you're not wedded to the idea of using Python, there are a few really simple solutions using ImageMagick:
“Diff” an image using ImageMagick
I want to get only leaf from an image.
The background is a normal white paper(A4) and there is some shadow.
I apply some method (structure element,edge detection using filter) but I cannot find the general way which can apply all the image.
these are examples.
Are there better methods for this problem??
thank you
another example.
and the result I got is
By using
hsv_I = rgb2hsv(I);
Is = hsv_I(:,:,2);
Is_d = imdilate(Is,strel('diamond',4));
Is_e = imerode(Is,strel('diamond',2));
Is_de = imerode(Is_d,strel('disk',2));
Is_def = imfill(Is_de,'holes');
Is_defe = imerode(Is_def,strel('disk',5));
Then Is_defe is a mask to segment
But the method that i did is very specific. I cannot use this in general.
If you have the Image Processing Toolbox, you could do as follows:
The code below first estimates the threshold with the function graythresh, thresholds the image and fills holes with the imfill function. Suppose I is a cell containing your RGB images:
for k=1:length(I)
t=graythresh(rgb2gray(I{k}));
BW{k}=imfill(~im2bw(I{k}, t), 'holes');
subplot(length(I),1,k), imshow(BW{k});
end
I'm using Geometric mean filter to remove noise instead of median filter as image quality goes off in former case. code shown below is a part of m-file to remove noise.
fname = getappdata(0, 'fname');
[a, map] = imread(fname);
x = ind2rgb(a, map);
b = im2double(x);
w=fspecial('gaussian',[3,3]);
geom=exp(imfilter(log(b),ones(3,3),'replicate')).^(1/3/3);
fname=imfilter(b,w,'replicate');
axes(handles.axes1);
imshow(fname);
If i press push button which is named 'Remove Noise' above code get executed irrespective of image quality/property. In the sense even if no noise is present, image will be subjected to filter.
My question, is there any way to detect whether noise is present or not, so that the moment i pressed push button if no Noise in image it should display a message stating 'NO NOISE TO REMOVE' automatically.
There is no direct way to determine whether an image is noisy or not.
However, you can compare resulting image fname with the input image b in such a way that if their difference is lower than a certain threshold, then it can be decided that denoising operation has not changed image effectively and there is not much noise in the original image like:
threshold_ratio = 0.2; % to be decided experimentally
difference_ratio = sum(sum((fname - b).^2)) / sum(sum(b.^2));
if difference_ratio < threshold_ratio
disp('NO NOISE TO REMOVE');
end