Skip to content
Nat Lee

Keyboard shortcuts

Turn these off if they get in the way of a screen reader or voice control. The setting is saved in this browser.

1
Home
2
Projects
3
About
4
Experience
/
Search projects
?
Show this panel

Computer Vision

openpose-detect-hands-with-heatmap

Hand Detection with Visualization

Finds hands with OpenPose and draws a heatmap on top, so you can see exactly where the model thinks your hands are.

Role
Creator & Maintainer
Period
2020 – 2021
Status
Completed
Theme
AI, vision & medical imaging
openpose-detect-hands-with-heatmap, screenshot 1

Overview

An advanced computer vision application that leverages OpenPose for hand detection and provides intuitive heatmap visualizations. This tool is particularly useful for gesture analysis, motion studies, and interactive applications requiring hand tracking.

The problem

  • Real-time processing requirements
  • Accuracy in various lighting conditions
  • Multiple hand detection
  • Smooth visualization rendering

What I did

  • Optimized OpenPose model integration
  • Implemented adaptive thresholding
  • Built efficient tracking algorithms
  • Created smooth heatmap animations

Results

  • Achieved real-time hand tracking
  • High accuracy in various conditions
  • Smooth heatmap visualizations
  • Popular in research community

Features

  • Real-time hand detection
  • Heatmap visualization
  • Motion tracking
  • Multi-hand support
  • Customizable visualization parameters
  • AI, vision & medical imaging33 stars on GitHub

    QWOP with PPO

    A PyTorch PPO agent plays the real QWOP browser game through Playwright. Six evaluation races, six 100 m finishes. Grace was not part of the reward function.

    2019Completed
  • AI, vision & medical imaging4040 stars on GitHub

    Brain MRI Pipeline

    An end-to-end Nipype pipeline with FSL FAST, K-means and ANTs Atropos segmentation, tissue volumes, bias-correction metrics and an interactive 3D brain.

    2018Completed
  • AI, vision & medical imaging11 stars on GitHub

    Street Scene OCR

    Compare EasyOCR, RapidOCR and PaddleOCR on Traditional Chinese street signs, with text boxes, timings and a small public-domain benchmark.

    2026Completed