Skip to content
generated from navdeep-G/samplemod

Using Computer Vision, ML, ESRGAN, and Image Processing to find the best sunsets across the ocean.

Notifications You must be signed in to change notification settings

grahamwaters/PySeas

Repository files navigation

PySeas

main

PySeas

PySeas Purpose

The world's oceans are an untapped wealth of information that we are only barely beginning to understand. More of the ocean has been untouched by man than any other place on earth.

temp_2

Using PySeas as a enVita Artist Agent

Our first application of this project is to create art with the images from these buoys, and use them to generate a tapestry of the beautiful oceans.

Previously, our code was written as shown below, as an outline for a class structure. We will keep the class structure, but we will be using a different approach to the project.

class BuoyImage:
    def __init__(self, location, weather_conditions, image_data):
        self.location = location
        self.weather_conditions = weather_conditions
        self.image_data = image_data

    def get_images(self):
        # Retrieve the images from the NOAA API
        pass

    def stitch_images(self):
        # Stitch the images together
        pass

    def blend_images(self):
        # Blend the images over time
        pass

# Create a GAN to generate images
class GAN:
    def __init__(self, image_data):
        self.image_data = image_data

    def generate_images(self):
        # Generate images using a GAN
        pass

    def blend_images(self):
        # Blend the images over time
        pass

class PanoramicImage:
    def __init__(self, stitched_image_data, horizon_line, time_lapse_data):
        self.stitched_image_data = stitched_image_data
        self.horizon_line = horizon_line
        self.time_lapse_data = time_lapse_data

    def blend_images(self):
        # Blend the images over time
        pass

    def detect_horizon(self):
        # Detect the horizon line
        pass

    def create_time_lapse(self):
        # Create a time-lapse animation
        pass

class Website:
    def __init__(self, layout, content):
        self.layout = layout
        self.content = content

    def generate_html(self):
        # Generate the HTML for the website
        pass

    def generate_css(self):
        # Generate the CSS for the website
        pass

    def generate_javascript(self):
        # Generate the JavaScript for the website
        pass

Phase One: Sunrise over the Sea

Create sunsets over the sea using the images from the NOAA API.

Phase Two: The Raging of the Storm

Find images of storms and hurricanes, and create a time-lapse of the storm.

PySeas

PySeas is a Python project aimed at analyzing buoy data. The project is structured into several directories, each serving a specific purpose in the data analysis pipeline.

Directories

src: This directory contains the main scripts of the project. It includes phase_one.py and phase_two.py, which perform initial data loading, cleaning, and visualization.

notebooks: This directory contains Jupyter notebooks that demonstrate the usage of the project modules. For example, PyBuoy.ipynb shows how to use the PyBuoy module to fetch and analyze buoy data.

utils: This directory typically contains utility scripts used across the project. These can include data processing functions, helper functions, and other reusable code snippets.

How to Run the Program

  • Clone the repository to your local machine.
  • Navigate to the project directory.
  • Install the required dependencies listed in the requirements.txt file. You can do this by running pip install -r requirements.txt in your terminal.
  • Run the scripts in the src directory. For example, you can run python src/phase_one.py to execute the first phase of the data analysis pipeline.

License

PySeas is licensed under the MIT License. See LICENSE for more information.

Contributing

Contributions are welcome! Please see CONTRIBUTING.md for more information.

Acknowledgements

The Sunset Tapestry

The Tapestry of the Ocean's Life

About

Using Computer Vision, ML, ESRGAN, and Image Processing to find the best sunsets across the ocean.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published