This project is focused on developing a web application that allows users to upload multiple images, stitch them together into a panoramic image, and apply various edge detection techniques to the stitched image. The techniques include Canny Edge Detection, and Difference of Gaussians (DoG) with a morphological operation. The application offers an interactive user interface to adjust parameters and visually compare the results of different edge detection techniques.
-
Image Stitching:
- Combine multiple images into a panoramic view.
-
Edge Detection:
- Canny Edge Detection: Identifies the edges in the stitched image.
- Difference of Gaussians (DoG): Highlights differences in pixel intensities, followed by morphological operations to clean the output.
- Adjustable kernel size for morphological operation through a UI slider.
-
AI-Based Human Detection:
- Uses a pre-trained AI model (e.g., YOLO or SSD) to detect human figures within the stitched image.
- Filters detections to show only those with confidence levels above 50%.
-
Frontend (React):
- ReactJS for the user interface.
- React components for image uploads, sliders, and displaying processed results.
-
Backend (Flask):
- Flask for backend API to handle image processing and edge detection.
- OpenCV for image stitching and edge detection algorithms.
- PyTorch/TensorFlow for AI-based human detection using a pre-trained model.
-
Libraries:
- OpenCV for image processing.
- PyTorch or TensorFlow for AI model integration.
-
Clone the repository:
git clone https://github.com/your-repo/ai-image-stitching-edge-detection.git
-
Backend Setup:
Navigate to the backend directory and install the required dependencies:
pip install -r requirements.txt
-
Run the Flask server:
python app.py
-
Frontend Setup:
Navigate to the frontend directory and install the dependencies:
npm install
-
Run the React app:
npm start
-
Access the Web Application:
Open your browser and go to
http://localhost:3000to start using the application.