frame-replace
Science Score: 44.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (4.0%) to scientific vocabulary
Repository
Basic Info
- Host: GitHub
- Owner: aminrabinia
- Language: Python
- Default Branch: master
- Size: 1.79 MB
Statistics
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
Pictuer Swap
This app will run inference on a Yolov8 Image Segmentation model, trained on a custom dataset, to segment pictures hanging on a wall. Once the frame on the wall is detected another picture can be selected to swap with the original picture.
After running an inference:
results = model.predict(input_image, imgsz=640, conf=conf, save=False, device='cpu')
results are parsed to extract boxes and masks. The coordinates then are used to capture the perspective and angles of a frame on the wall.
contours, hierarchy = cv2.findContours(img, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnt = sorted(contours, key=cv2.contourArea, reverse=True)[-1]
cv2.drawContours(canvas, cnt, -1, (255, 255, 0), 2)
The extracted coordinates then adjust the new picture.
pts2 = np.float32(new_corners)
M = cv2.getPerspectiveTransform(pts1,pts2)
dst = cv2.warpPerspective(img, M, (cols, rows), bg_img, borderMode=cv2.BORDER_TRANSPARENT)
Finally, a merge function with overlay the new picture on the original frame.
for c in range(3):
image[y1:y2, x1:x2, c] = alpha * img_pic[:, :, c]
Owner
- Name: Amin Rabinia
- Login: aminrabinia
- Kind: user
- Company: University of Maine
- Website: https://www.glissai.com
- Repositories: 2
- Profile: https://github.com/aminrabinia
Sr. AI Engineer Applied ML
Citation (CITATION.cff)
cff-version: 1.2.0
preferred-citation:
type: software
message: If you use this software, please cite it as below.
authors:
- family-names: Jocher
given-names: Glenn
orcid: "https://orcid.org/0000-0001-5950-6979"
- family-names: Chaurasia
given-names: Ayush
orcid: "https://orcid.org/0000-0002-7603-6750"
- family-names: Qiu
given-names: Jing
orcid: "https://orcid.org/0000-0003-3783-7069"
title: "YOLO by Ultralytics"
version: 8.0.0
# doi: 10.5281/zenodo.3908559 # TODO
date-released: 2023-1-10
license: GPL-3.0
url: "https://github.com/ultralytics/ultralytics"
GitHub Events
Total
Last Year
Dependencies
- ubuntu 20.04 build
- nvcr.io/nvidia/pytorch 23.01-py3 build
- Pillow >=7.1.2
- PyYAML >=5.3.1
- fastapi *
- gradio *
- ipython *
- matplotlib >=3.2.2
- numpy >=1.18.5
- opencv-python >=4.6.0
- pandas >=1.1.4
- psutil *
- requests >=2.23.0
- scipy >=1.4.1
- seaborn >=0.11.0
- tensorboard >=2.4.1
- thop >=0.1.1
- torch >=1.7.0
- torchvision >=0.8.1
- tqdm >=4.64.0
- uvicorn *