OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Image & Video AI

AI Basketball Analysis

AI Basketball Analysis is a Python web application and REST API for analyzing basketball shots and shooting pose. It uses object detection to identify shot activity and OpenPose-derived body keypoints to examine player mechanics.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

AI Basketball Analysis — OpenViST project profile in Image & Video AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when exploring basketball shot analysis from uploaded footage or when prototyping an image-based detection workflow for a sports application.

Who it is for

  • Basketball analysts reviewing shot outcomes and shooting form.
  • Developers exploring computer-vision analysis of basketball images and footage.

Documented uses

  • Count shots and distinguish successful from missed attempts in video.
  • Review player elbow and knee angles, release angles and timing.
  • Submit an image to the detection endpoint and receive JSON keypoint data.
  • Inspect detection confidence and coordinate visualizations.
Before you choose

Requirements & limits

  • The project is implemented in Python and documents OpenPose, TensorFlow and a Faster R-CNN model trained on COCO.
  • Local setup uses requirements.txt and app.py; CUDA-capable GPU hardware is recommended for efficient OpenPose video processing.
  • The detection endpoint is documented for image POST requests at /detection_json; the README describes video upload through the app.
  • The README warns that TensorFlow workloads may time out on Heroku due to resource limits.
  • The project describes its use as noncommercial research because it uses OpenPose.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up the application locally

Prepare the repository and launch its local web application for basketball video or image analysis.

Before you start

  • Python environment with the project dependencies
  • GPU with CUDA support recommended for efficient OpenPose processing

Steps

  1. Clone the repository from GitHub.

  2. Install dependencies with pip install -r requirements.txt.

  3. Launch the application with python app.py.

Expected outcome

The README says the app launches locally and allows basketball videos or images to be uploaded for analysis.

Guide limitations

  • The README recommends CUDA-capable GPU hardware for efficient OpenPose video analysis; it does not guarantee performance on a particular system.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
chonyy/AI-basketball-analysis · Official homepage title · retained in its source language
How we review sourcesSuggest a correction