Intel RealSense · computer vision

One camera. Six kinds of tracking. Real 3D.

BlinkPose.Track turns an Intel RealSense depth camera into a live tracking hub — ArUco markers, full-body pose down to the feet, both hands finger by finger, faces and circular markers, detected in a single pass and each pinned to a real-world 3D position. No suit, no gloves, no markers on the person. It streams straight to a browser dashboard, with a live video feed and an in-browser 3D view of everything it sees.

6 entry types · MJPEG video · in-browser 3D · real-time

localhost — BlinkPose.Track
BlinkPose.Track dashboard: live camera view, marker table and controls

Track dashboard — live camera feed, the detection table and the in-browser 3D view, all served from the module’s own process.

What it detects

Six trackers, one camera

Every detection runs on the same frame and lands in one live list — mix and match whatever your setup needs.

ArUco markers

Fiducial tags with a stable ID and a full 6-DOF pose — the workhorse for rigid objects and tools.

Human pose

A full-body skeleton of 26 points per person — heels and toes included — each with its own confidence. A joint whose depth cannot be trusted is sent without a 3D position rather than with a wrong one.

Hands

21 points per hand, every finger joint. A hand is followed from frame to frame once found, rather than searched for again in every picture.

Faces

Face detection per person, with the head's direction in degrees — turn, nod and tilt — and a simple expression read.

Face landmarks

35 points per face — eyes, brows, nose, mouth and jaw line — each with a position in space.

Circular markers

Round fiducials for quick, cheap targets where a full ArUco tag is overkill.

In motion

A person, measured thirty times a second

These plates are drawn from a real recording of the module's output — one person, one camera, nothing worn. The figure is the data: every dot is a point Track reported for that frame, and every line joins two of them. Nothing is drawn in that the module did not measure.

A tracked skeleton raising its arms, with joint angles and joint positions in metres updating beside it

Body tracking — 26 body points with both hands attached. Joint angles and positions are computed from the stream as it arrives; the blue traces are the wrists' last second of travel.

Two tracked hands with each finger in its own colour, and palm width, finger span and distance from the camera shown below

Hand tracking — 21 points per hand, a colour per finger. Because the points are in real units, a palm width or a finger span is a measurement in millimetres, not a guess in pixels.

A tracked face drawn from 35 points, turning and nodding, with the head's turn, nod and tilt in degrees beside it

Face tracking — 35 points per face and the head's direction as three angles: turn, nod and tilt. An eye is its two corner points; the orange line is where the nose is pointing.

What the points become

From a stream of points to a measurement

Track does not decide what the movement means — it delivers named points in metres, frame after frame, and leaves the question to the application built on it. The figures in the plates above are examples of what a few lines of arithmetic on that stream give.

Inside the dashboard

Everything on one screen

The whole camera is controllable from the browser — no separate app, no config files.

Not just pixels

Every detection carries a real 3D position

Because it's a depth camera, each marker and keypoint is deprojected into real-world coordinates — markers additionally get a full 6-DOF pose. Downstream tools get metres, not just pixels.

The same tracked person shown in 3D on a half-metre floor grid, viewed from a slowly moving angle, with the camera's position marked

Real 3D — the same recording, turned in space. The view moves; the person does not flatten, because each point carries its own distance from the camera.

6
detection types
6-DOF
pose per marker
3D
depth-deprojected xyz
68
points per person, hands included

Building on it

One message per frame, on your own machine

The dashboard is one client among many. Everything it shows arrives over plain local connections that any program can open.

Plainly stated

What one camera can and cannot do

A single depth camera sees one side of a scene. Knowing where that stops is part of using it well.