analytics

Accurate Pose Tracking with openvino_movenet_multipose

Name: Accurate Pose Tracking with openvino_movenet_multipose
Author: geaxgx

Get precise multi-pose tracking for analytics with openvino_movenet_multipose, a tool.

81 stars17 forksPythonGuide quality 8/10Updated 8/22/2022100% free · open source

What it does

OpenVINO MoveNet MultiPose is a tool that enables precise multi-pose tracking for analytics, allowing startup founders to analyze human movement in videos or images.

When to use it

•When you need to track multiple people's movements in a video for sports analytics
•When analyzing customer behavior in a retail setting through video footage
•When developing fitness or dance applications that require accurate pose tracking

Ready-to-paste prompt

python demo.py --input video.mp4 --output tracked_video.mp4 --model movenet_multipose

Heads up: Ensure you have the necessary OpenVINO version installed and configured, as the tool is optimized for OpenVINO 2021.4 or later, and the model may not work correctly with earlier versions

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/openvino-movenet-multipose && curl -fsSL https://workflowstacks.com/api/skills/openvino-movenet-multipose/claude-skill -o ~/.claude/skills/openvino-movenet-multipose/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How Accurate Pose Tracking with openvino_movenet_multipose works

Codeflow

Free to inspect

Accurate Pose Tracking with openvino_movenet_multipose is a small Python project (~650 lines across 3 code files). Setup is light: installs like a normal app. Reading the code is optional. Last commit 49 months ago, MIT license, no tests found.

Size

Small codebase

~650 lines · 3 code files · 5 min skim

Setup

One-command install

Installs like a normal app. Reading the code is optional.

Runs on

Python

No API keys detected

Python 100%

Where to start reading

1
README.md
Start here — what it does and how to install it

What's in each folder

models/Data models & types14 files

img/Images & static assets7 files

READMENo tests foundThin docsNo CIMIT licenseLast update 49 mo ago