hri_face_detect
- Software
- Perception
- Library
A ROS4HRI-compliant ROS node for fast face detection in camera images, using the YuNet detector at a distance and Mediapipe Face Mesh up close.
- Stale
Made by ROS4HRI.
Source on GitHub: github.com/ros4hri/hri_face_detect (opens in a new tab). Facts read at commit 599fde0 (opens in a new tab).
Licenses
- Code
- Apache-2.0 (opens in a new tab)
Read by Robotheca from LICENSE (opens in a new tab) (Apache-2.0) at commit 599fde0 (opens in a new tab), on 22 Oct 2026.
- Commercial use
- Yes
Labels
- StaleNo commit in 12 months: the newest is from 12 Sept 2025.
What it does
- Detects faces with the YuNet detector, which works well at greater distances and extracts 5 keypoints.
- Runs Mediapipe Face Mesh at close range to extract all ROS4HRI-defined facial landmarks.
- Publishes per-face region of interest, landmarks, cropped and aligned face images, and a tracked-faces topic.
- Filters the estimated face pose in a configurable reference frame, by default the camera optical frame.
- Can assign deterministic sequential face IDs or random five-letter IDs.
- Offers parameters for processing rate, image scale, confidence threshold, compressed image input, and a debug window.
Written by Robotheca from the project's README (opens in a new tab) at commit 599fde0.
Getting started
- Difficulty
- Intermediate
- How to start
- The project's README (opens in a new tab)
Maintenance
- Status
- Stale: no commit in 12 months
- Newest commit
- 12 Sept 2025 on humble-devel
- Latest release
- None published on GitHub
Checked on GitHub on 22 Oct 2026.
Links
Robots that can run it
No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.
Robotheca lists software as a reference: nothing is hosted or run here, and every fact links to where it was read.