ML Application · Jupyter Notebook

FootballNet

a football ball-tracking functionality

Suceveanu Mircea Dan Sandu@MirceaDan · Atlas 56.8 · #9= builder

View on GitHub Open Suceveanu Mircea Dan Sandu's Atlas

What it is

FootballNet is a system for tracking a football in video, estimating its 3D trajectory, and producing an annotated output video and trajectory CSV. It implements multiple detection methods (classical computer vision, a custom deep learning model, and YOLO) and includes training code for the custom model.

Scored from the code at its last scan, 8 Oct 2026. How merit is scored

Where it counts

Computer Vision90%
Machine Learning70%
Data Science10%

How much of the project is about each field, as scoring counts it. It ranks in the field it is most about.

Around it on the Computer Vision board

Whole board

RankProjectBuilderFieldMerit

3fourcast-livive-netEducational Implementation · JavaScriptThe repository provides an interactive web application that compares four computer vision architectures (HOG+SVM, custom CNN, transfer learning, and vision foundation models) for cat vs dog classification. It includes code for dataset creation, model training (from-scratch…59.1/100AdvancedJarad PeckenpaughComputer Vision
04opencv-document-scannerOther AI Project · PythonThis repository provides a complete OpenCV-based document scanner that detects document boundaries in photos, applies perspective correction, and outputs enhanced scans in black-and-white, grayscale, or color modes. It includes a CLI, a reusable Python package, unit tests, and…54.1/100ImplementationPop AlexandruComputer Vision
05FootballNetML Application · Jupyter Notebook48.2/100ImplementationSuceveanu Mircea Dan SanduComputer Vision
06background-subtractionEducational Implementation · Jupyter NotebookThe repository provides a Jupyter notebook that demonstrates and compares three OpenCV background subtraction algorithms (MOG, MOG2, GMG) on a sample surveillance video, accompanied by explanatory text in the README.42.1/100ImplementationPop AlexandruComputer Vision
07Multi-Task-RailML Application · Jupyter NotebookThis repository provides a Jupyter notebook implementing a multi-task model for railway signal detection (using GERALD dataset) and scene segmentation (using RailSem19 dataset) with a shared ResNet50-FPN backbone and task-specific heads. The code includes data loaders, model…40.1/100ImplementationSuceveanu Mircea Dan SanduComputer Vision

What it is

Where it counts

Around it on the Computer Vision board

More from Suceveanu Mircea Dan Sandu