# Threshold the HSV image to extract green color Hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV) import cv2ĭef show_result(winname, img, wait_time):ĭisp_img = cv2.resize(img, None, fx=scale, fy=scale) Then, we create a script named skull.py in the same directory with the images. Python3 -c "import cv2 print(cv2._version_)" For this, I have written a simple OpenCV Python code to demonstrate the results.įirst, we need to install OpenCV. We know that the background is green and is distinguishable from the object by its color, so I suggest using color thresholding. Graphics: GeForce GTX 970/PCIe/SSE2 (two of them).Processor: AMD® Ryzen 9 3900x 12-core processor × 24.Maybe this has something to do witch those errors that occur while processing?: convert-im6.q16: width or height exceeds limit `black' error/cache.c/OpenPixelCache/3911.Ĭonvert-im6.q16: ImageSequenceRequired `-composite' error/mogrify.c/MogrifyImageList/7995.Ĭonvert-im6.q16: no images defined `./GREENSCREEN.6799/lut.png' error/convert.c/ConvertImageCommand/3258.Ĭonvert-im6.q16: unable to open image `./GREENSCREEN.6799/lut.png': No such file or directory error/blob.c/OpenBlob/2874.Ĭonvert-im6.q16: ImageSequenceRequired `-clut' error/mogrify.c/MogrifyImageList/7870.Ĭonvert-im6.q16: profile 'icc': 'RGB ': RGB color space not permitted on grayscale PNG `mask.png' warning/png.c/MagickPNGWarningHandler/1667. greenscreen infile.jpg outfile.png and I am rather satisfied with the result.īut it takes around 40 seconds to process one image which results in a total 8 hours for all my images (although I have a rather power workstation, see specs below) I've just tried using this greenscreen script by fmw42 by running. So no Photoshop or After Effects! :)īut I am sure that there has to be a solution to this problem. I feel really dumb, that I cannot find a solution to such a simple problem myself. delete 0,1 -alpha extract -compose Multiply -composite \īut no matter how I tweak the numbers, the results are not perfect: \( -clone 1 -background none -fuzz 10% -transparent grey100 \) \ ![]() \( -clone 0 -background none -fuzz 3% +transparent grey43 \) \ for i in * do convert $i -colorspace HSV -separate +channel \ I found this post where the user used Imagemagick to achieve chroma keying. Here is the original image if you want to do tests: !0YJnzAJR!GRYI4oNWcsKztHGoK7e4uIv_GvXBjMvyry7cPmyRpRA I simply want to use the green screen to create a mask for each image that looks like this one here (the border should preferably be smoothed out a little bit): I have hundreds of images that all look similar to this one here:
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |