# yinguobing/head-pose-estimation

Realtime human head pose estimation with ONNXRuntime and OpenCV.

Repository: https://github.com/yinguobing/head-pose-estimation
Canonical: https://ross.abutalabs.com/products/head-pose-estimation
Language: Python
License: MIT
License Family: permissive
Topics: deep-learning, opencv, tensorflow, facial-landmarks-detection, convolutional-neural-networks, onnxruntime
Last push: 2024-09-02T09:14:02+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3171, "days_push": 730, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1353, forks 295 (observed 2026-08-28T04:04:28.578948+00:00)

## What it is
A Python library for realtime human head pose estimation using ONNX Runtime and OpenCV. It combines face detection (SCRFD), 68-point facial landmark detection, and PnP-based pose calculation from pre-trained deep learning models.

## Use cases
- estimate head pose from a webcam in realtime
- get head orientation angles from a video file
- detect facial landmarks with a deep learning model
- build driver drowsiness or attention monitoring
- run face pose estimation without GPU with ONNX Runtime
- estimate 3D head rotation from 2D face images

## When to choose
- you need realtime head pose (pitch/yaw/roll) from webcam or video
- you want a lightweight CPU-friendly pipeline via ONNX Runtime
- you need facial landmarks plus pose in one ready-made solution

## When to avoid
- you need full 3D face reconstruction or dense mesh tracking
- you need a production web service with an API out of the box
- you require PyTorch-native training or inference (training lives in a separate repo)

## Facets
- artifact type: library
- maturity: stable
- function: computer-vision, image-processing, machine-learning, deep-learning
- domain: computer-vision, artificial-intelligence, deep-learning
- platform: python, cross-platform
- tags: head-pose-estimation, facial-landmarks, onnxruntime, opencv, pnp, realtime, face-detection, linux

## Member repositories
- yinguobing/head-pose-estimation (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:28.578948+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:42:07.312512+00:00, confidence not recorded.
  - readme: https://github.com/yinguobing/head-pose-estimation (fetched 2026-08-28T04:04:28.578948+00:00, sha 776a3d4923a4)
- Data as of 2026-08-30T08:39:29.467469+00:00.