# Basketball Shot Analyzer

## PhysTech 2025 Submission

### Project Title
Basketball Shot Analyzer: AI-Powered Feedback for Jump Shots

### Team Member
- Ayaan Kayastha
- United States of America
- Contact: [email protected]

---

## Project Summary

This project is an AI-powered web application that analyzes basketball jump shot videos and provides personalized, actionable feedback. Users upload a video of their shot, and the app uses computer vision (OpenCV, MediaPipe) and Python to identify key phases of the shot, the beginning, release, and landing. It then generates visualizations and detailed feedback to help users improve their shooting technique.

---

## How It Works

1. **Upload** your basketball jump shot video (MP4 format).
2. The app processes the video, detects key body landmarks using MediaPipe, and identifies three shot phases.
3. For each phase, the app creates annotated images and generates feedback based on biomechanics.
4. All feedback and images are stored in a Kintone database for history and trend analysis.
5. Users can view their past analyses and see trends in their performance.

---

## Technologies Used

- **Python** (Flask web server)
- **OpenCV** (video/image processing)
- **MediaPipe** (pose estimation)
- **Requests** (API communication)
- **Kintone** (cloud database)
- **HTML/CSS** (frontend)
- **Replit** (deployment platform)

---

## AI Assistance Disclosure

> This project was created with the assistance of AI tools (Perplexity, ChatGPT), as I am not that experienced in Python. All project ideas, design, and direction are my own.

---

## How to Run the Project

### Requirements

- Python 3.8+
- Required packages (install with `pip install -r requirements.txt`):
    - flask
    - opencv-python
    - mediapipe
    - requests
    - numpy

### Steps

1. **Clone or download** this repository and unzip if necessary.
2. Place your `main.py` and all relevant files in the same folder.

3. In your terminal, run:
    ```
    pip install -r requirements.txt
    python main.py
    ```
4. Open your browser and go to `http://localhost:81` (or the URL shown in your terminal).
5. Upload an MP4 basketball shot video to receive feedback.

---

---

## Project Files

- `main.py` — Main application code.
- `requirements.txt` — List of Python dependencies.
- `README.md` — This documentation.
- `static/` and `templates/` — Frontend assets (if included).

---

## Project Presentation

- **Presentation Title:** Basketball Shot Analyzer: AI-Powered Feedback for Jump Shots
- **Summary:** Analyzes basketball jump shot videos to give users visual and written feedback on their shooting form, helping them improve through computer vision and AI.
Contact: [email protected]
---

## Notes for Judges

- All code and design was completed during the PhysTech 2025 hackathon.
- AI tools were used to assist with coding, but all project direction and ideas are original.
- Please refer to the included `main.py` for the full application logic.
- For any issues running the app, please contact me at [email protected].

---