willbrennan / imagestitching Goto Github PK
View Code? Open in Web Editor NEWConducts image stitching upon an input video to generate a panorama in 3D
Conducts image stitching upon an input video to generate a panorama in 3D
Hi Will, I am doing some testing with your project for a school project. You probably stopped developing it, but I was wondering if you could give me a clue about why the invisible images get blurred the more the process continues, and how it could be fixed if you know?
Attached is a picture of Frame 935 (example), that illustrates the issue:
Hey Will,
I tried to run the program by following your instructions, but there is no make file and I did output only one image when doing videos.
Can you please help?
Thanks,
my opencv version 2.4.11, numpy version python 1.12.1
exe: python image_stitching.py image/phantom3-ieu/ --display --save
then:
INFO:root:beginning sequential matching
('image_path', 'image/phantom3-ieu/')
OpenCV Error: Assertion failed (scn == 3 || scn == 4) in cvtColor, file /home/yi/opencv-2.4.11/modules/imgproc/src/color.cpp, line 3739
Traceback (most recent call last):
File "image_stitching.py", line 54, in
image_gray = cv2.cvtColor(image_colour, cv2.COLOR_RGB2GRAY)
cv2.error: /home/yi/opencv-2.4.11/modules/imgproc/src/color.cpp:3739: error: (-215) scn == 3 || scn == 4 in function cvtColor
video_stitching has a bug:
Traceback (most recent call last):
File "video_stitching.py", line 46, in
cap = cv2.VideoCapture(args.video_path)
TypeError: an integer is required
so I use image_stitching to stitch images captured from video, but I can't stitch 35 images at a time while stitch 34 images are fine. Also when stitching 80 images, No.1-34 disappear and No.35-80 are fine.
I run the program in both opencv2.4 and opencv3.2 and they have the same problem. Is there any limitation in the code? I'm not familiar with opencv so I can't find the limitation myself.
Currently I am running opencv 4.5.1. So when it checks for the version to call the appropriate sift function, it s throwing an error. Wjat do i do?
It is just going to the runtime exception error and stop execution without initializing sift
Hi Will,
I am attempting to stitch 2 image in path. Seems the stitching is starting, but the process does not finish. Here is what I see on the terminal.
python3 stitching.py testimages --display --save
WARNING:root:skipping .DS_Store...
INFO:root:displaying image 0
INFO:root:saving result image on result_0.jpg
I see the first image open in a window and the shown images is in result_0.jpg file. There is further terminal output indicating the stitching in progress or complete. I have the images named img1.jpeg and img2.jpeg in testimages directory. Any suggestions on resolving the issue is much appreciated. Thank you.
How to achieve
Longitudinal splicing
I want top create a panorama from a video by splitting it into frames and then stitch them using the conventional method of finding features.
This is my code for reference
import cv2
import numpy as np
import glob
import imutils
def draw_matches(img1, keypoints1, img2, keypoints2, matches):
r, c = img1.shape[:2]
r1, c1 = img2.shape[:2]
# Create a blank image with the size of the first image + second image
output_img = np.zeros((max([r, r1]), c + c1, 3), dtype='uint8')
output_img[:r, :c, :] = np.dstack([img1])
output_img[:r1, c:c + c1, :] = np.dstack([img2])
# Go over all of the matching points and extract them
for match in matches:
img1_idx = match.queryIdx
img2_idx = match.trainIdx
(x1, y1) = keypoints1[img1_idx].pt
(x2, y2) = keypoints2[img2_idx].pt
# Draw circles on the keypoints
cv2.circle(output_img, (int(x1), int(y1)), 4, (0, 255, 255), 1)
cv2.circle(output_img, (int(x2) + c, int(y2)), 4, (0, 255, 255), 1)
# Connect the same keypoints
cv2.line(output_img, (int(x1), int(y1)), (int(x2) + c, int(y2)), (0, 255, 255), 1)
return output_img
def warpImages(img1, img2, H):
rows1, cols1 = img1.shape[:2]
rows2, cols2 = img2.shape[:2]
list_of_points_1 = np.float32([[0, 0], [0, rows1], [cols1, rows1], [cols1, 0]]).reshape(-1, 1, 2)
temp_points = np.float32([[0, 0], [0, rows2], [cols2, rows2], [cols2, 0]]).reshape(-1, 1, 2)
# When we have established a homography we need to warp perspective
# Change field of view
list_of_points_2 = cv2.perspectiveTransform(temp_points, H)
list_of_points = np.concatenate((list_of_points_1, list_of_points_2), axis=0)
[x_min, y_min] = np.int32(list_of_points.min(axis=0).ravel() - 0.5)
[x_max, y_max] = np.int32(list_of_points.max(axis=0).ravel() + 0.5)
translation_dist = [-x_min, -y_min]
H_translation = np.array([[1, 0, translation_dist[0]], [0, 1, translation_dist[1]], [0, 0, 1]])
output_img = cv2.warpPerspective(img2, H_translation.dot(H), (x_max - x_min, y_max - y_min))
output_img[translation_dist[1]:rows1 + translation_dist[1], translation_dist[0]:cols1 + translation_dist[0]] = img1
# print(output_img)
return output_img
# Main program starts here
input_path = "/Users/akshayacharya/Desktop/Panorama/Bazinga/Test images for final/Highfps/*.jpg"
output_path = "Output/o4.jpg"
#input_path = "/Users/akshayacharya/Desktop/Panorama/Bazinga/Output/*.jpg"
#output_path = "Output/final.jpg"
input_img = glob.glob(input_path)
img_path = sorted(input_img)
print(img_path)
tmp = img_path[0]
flag = True
for i in range(1, len(img_path)):
if flag:
img1 = cv2.imread(tmp, cv2.COLOR_BGR2GRAY)
img2 = cv2.imread(img_path[i], cv2.COLOR_BGR2GRAY)
flag = False
img1 = cv2.resize(img1, (1080, 720), fx=1, fy=1)
img2 = cv2.imread(img_path[i], cv2.COLOR_BGR2GRAY)
img2 = cv2.resize(img2, (1080, 720), fx=1, fy=1)
orb = cv2.ORB_create(nfeatures=2000)
keypoints1, descriptors1 = orb.detectAndCompute(img1, None)
keypoints2, descriptors2 = orb.detectAndCompute(img2, None)
# cv2.imshow('1',cv2.drawKeypoints(img1, keypoints1, None, (255, 0, 255)))
# cv2.imshow('2',cv2.drawKeypoints(img2, keypoints2, None, (255,255, 255)))
# cv2.waitKey(0)
# Create a BFMatcher object.
# It will find all of the matching keypoints on two images
bf = cv2.BFMatcher_create(cv2.NORM_HAMMING)
# Find matching points
matches = bf.knnMatch(descriptors1, descriptors2, k=2)
# print("Descriptor of the first keypoint: ")
# print(descriptors1[0])
# print(type(matches))
all_matches = []
for m, n in matches:
all_matches.append(m)
img3 = draw_matches(img1, keypoints1, img2, keypoints2, all_matches[:])
# v2.imshow('Matches',img3)
# cv2.waitKey(0)
# Finding the best matches
good = []
for m, n in matches:
if m.distance < 0.9 * n.distance:
good.append(m)
# cv2.imshow('Final1',cv2.drawKeypoints(img1, [keypoints1[m.queryIdx] for m in good], None, (255, 0, 255)))
# cv2.imshow('Final2',cv2.drawKeypoints(img2, [keypoints2[m.queryIdx] for m in good], None, (255, 0, 255)))
# cv2.waitKey(0)
MIN_MATCH_COUNT = 10
if len(good) > MIN_MATCH_COUNT:
# Convert keypoints to an argument for findHomography
src_pts = np.float32([keypoints1[m.queryIdx].pt for m in good]).reshape(-1, 1, 2)
dst_pts = np.float32([keypoints2[m.trainIdx].pt for m in good]).reshape(-1, 1, 2)
# Establish a homography
M, _ = cv2.findHomography(src_pts, dst_pts, cv2.RANSAC, 5.0)
result = warpImages(img2, img1, M)
img1 = result
print(f"Succesfully stitched until image{i + 1}")
#writeStatus = cv2.imwrite(output_path, result)
#if writeStatus is True:
# print("image written")
#else:
# print("problem") # or raise exception, handle problem, etc.
#result = cv2.resize(result)
cv2.imshow("Hi", result)
cv2.waitKey(0)
#writeStatus = cv2.imwrite(output_path, result)
stitched = img1
stitched = cv2.copyMakeBorder(stitched, 10, 10, 10, 10,
cv2.BORDER_CONSTANT, (0, 0, 0))
# convert the stitched image to grayscale and threshold it
# such that all pixels greater than zero are set to 255
# (foreground) while all others remain 0 (background)
gray = cv2.cvtColor(stitched, cv2.COLOR_BGR2GRAY)
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY)[1]
# find all external contours in the threshold image then find
# the *largest* contour which will be the contour/outline of
# the stitched image
cnts = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)
cnts = imutils.grab_contours(cnts)
c = max(cnts, key=cv2.contourArea)
# allocate memory for the mask which will contain the
# rectangular bounding box of the stitched image region
mask = np.zeros(thresh.shape, dtype="uint8")
(x, y, w, h) = cv2.boundingRect(c)
cv2.rectangle(mask, (x, y), (x + w, y + h), 255, -1)
# create two copies of the mask: one to serve as our actual
# minimum rectangular region and another to serve as a counter
# for how many pixels need to be removed to form the minimum
# rectangular region
minRect = mask.copy()
sub = mask.copy()
# keep looping until there are no non-zero pixels left in the
# subtracted image
while cv2.countNonZero(sub) > 0:
# erode the minimum rectangular mask and then subtract
# the thresholded image from the minimum rectangular mask
# so we can count if there are any non-zero pixels left
minRect = cv2.erode(minRect, None)
sub = cv2.subtract(minRect, thresh)
# find contours in the minimum rectangular mask and then
# extract the bounding box (x, y)-coordinates
cnts = cv2.findContours(minRect.copy(), cv2.RETR_EXTERNAL,
cv2.CHAIN_APPROX_SIMPLE)
cnts = imutils.grab_contours(cnts)
c = max(cnts, key=cv2.contourArea)
(x, y, w, h) = cv2.boundingRect(c)
# use the bounding box coordinates to extract the our final
# stitched image
stitched = stitched[y:y + h, x:x + w]
#cv2.imwrite("cropped.jpg", stitched)
#writeStatus = cv2.imwrite(output_path, stitched)
#if writeStatus is True:
# print("image written")
#else:
# print("problem") # or raise exception, handle problem, etc.
stitched = cv2.resize(stitched, (2000,1500))
cv2.imshow("cropped", stitched)
cv2.waitKey(0)
However, its not giving me the right output. I have attached the image for reference. Can you guide me as to how I could get the right panorama? The images for the source are obtained by splitting a video into frames and then using these as input images.
](url)
In the makefile pip tries to find requirements.txt, can you include it to the project or am I missing something?
Hi, I am using video_stitching.py, after a certain amount of frames my device freezes, I don't think it is because of hardware limitations as my ram and CPU both don't even reach 50% of load.
What it says on the tin. I googled the title and my best guess was this:
Springer: https://link.springer.com/article/10.1007/s11263-006-0002-3
ResearchGate: https://www.researchgate.net/publication/225133245_Automatic_Panoramic_Image_Stitching_using_Invariant_Features
There's an ACM link on google I think, but it's not really working for me (due to some reason unbeknownst to me), but I think this should suffice.
Should I put in a pull request?
When i execute the video stitch program from termincal , the following error comes. Wha should I do?
/usr/lib/python3/dist-packages/apport/report.py:13: DeprecationWarning: the imp module is deprecated in favour of importlib; see the module's documentation for alternative uses
import fnmatch, glob, traceback, errno, sys, atexit, locale, imp
Traceback (most recent call last):
File "image_stitching.py", line 12, in
import image_stitching
File "/home/akshay/VideoStitcher/image_stitching/init.py", line 5, in
from matching import *
AttributeError: module 'matching' has no attribute 'Matching'
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.