All paths

Image processing on a thermal camera

Vision from raw sensor words on an Uno with 2 KB of RAM: images as grids, interpolation streamed a pixel at a time, thresholds, blobs, edges and tracking. Ends with a crew counter for a spaceship airlock.

Arduino Uno R3Free7 lessons6 h4 chapters2,766 XPCoding · Advanced+250 XP

0 of 7 done

What you will build

3 projects, built step by step

7 lessons in 4 chapters, about 6 hours on a simulated Arduino Uno R3. Free, in your browser, every step checked by the simulator.

Chapter 1 project

Interpolation

Turn the blocky 8x8 into a smooth 29x29 with bilinear interpolation in whole numbers, streamed a pixel at a time because the big picture would not fit in 2 KB, then compare nearest-pixel and change the scale.

Open it in the simulator
Chapter 2 project

Blobs

Count the crew in a mask with connected-component labeling: a flood fill with its own 64-byte stack, a test frame with a known answer, 4 against 8 neighbors, a size filter for noise, and a blob cut off by the edge.

Open it in the simulator
Chapter 3 project

Tracking

Follow each crew member from frame to frame: blob centers matched to tracks by distance, a direction from the motion, a gate that refuses a teleport, and patience for someone who drops out of view.

Open it in the simulator
The map

Chapter by chapter

Each lesson opens when the one before it is done, and each chapter ends in a project.

Chapter 1

Pictures made of numbers

An 8x8 frame in 128 bytes, then smooth it without the RAM to hold it.

  1. Open288 XP

    Images as grids

    A thermal camera sees sixty-four temperatures. Store them as quarter degrees in 128 bytes, find a pixel by row and column, shade the grid as text art, move the warm crew member, and mirror the picture.

    0 of 6 steps

  2. ProjectLocked576 XP

    Interpolation

    Turn the blocky 8x8 into a smooth 29x29 with bilinear interpolation in whole numbers, streamed a pixel at a time because the big picture would not fit in 2 KB, then compare nearest-pixel and change the scale.

    0 of 6 steps

5 questions, graded as you go.
Chapter 2

Find the crew

Thresholds that follow the room, then blobs you can count.

  1. Locked250 XP

    Thresholds

    Split the frame into crew and background: a fixed threshold, why it breaks when the airlock warms up, a threshold that follows the room, and a difference test that also finds a crew member in a cold suit.

    0 of 5 steps

  2. ProjectLocked500 XP

    Blobs

    Count the crew in a mask with connected-component labeling: a flood fill with its own 64-byte stack, a test frame with a known answer, 4 against 8 neighbors, a size filter for noise, and a blob cut off by the edge.

    0 of 5 steps

5 questions, graded as you go.
Chapter 3

Edges and motion

Where the picture changes, then who went where.

  1. Locked288 XP

    Edges

    Where the temperature changes: the Sobel filter in whole numbers, why the hottest pixel has no edge, why edges ignore the room temperature, an outline threshold, and a better cheap stand-in for the square root.

    0 of 6 steps

  2. ProjectLocked576 XP

    Tracking

    Follow each crew member from frame to frame: blob centers matched to tracks by distance, a direction from the motion, a gate that refuses a teleport, and patience for someone who drops out of view.

    0 of 6 steps

4 questions, graded as you go.
Chapter 4

Boss: the airlock counter

Count the crew in and out, and know when everyone is aboard.

  1. Locked288 XP

    Boss: a person counter

    The airlock crew counter: thresholds, blobs and tracks count crew in and out across a line, a dead band stops a hesitant crew member being counted three times, and the hatch knows when everyone is aboard.

    0 of 6 steps

3 questions, graded as you go.
Syllabus

Every lesson in the course

All 7 lessons, in order, each with what it covers. Any of them opens in the editor right away.

Chapter 1

Pictures made of numbers

  1. Images as gridsA thermal camera sees sixty-four temperatures. Store them as quarter degrees in 128 bytes, find a pixel by row and column, shade the grid as text art, move the warm crew member, and mirror the picture.
  2. InterpolationTurn the blocky 8x8 into a smooth 29x29 with bilinear interpolation in whole numbers, streamed a pixel at a time because the big picture would not fit in 2 KB, then compare nearest-pixel and change the scale.
Chapter 2

Find the crew

  1. ThresholdsSplit the frame into crew and background: a fixed threshold, why it breaks when the airlock warms up, a threshold that follows the room, and a difference test that also finds a crew member in a cold suit.
  2. BlobsCount the crew in a mask with connected-component labeling: a flood fill with its own 64-byte stack, a test frame with a known answer, 4 against 8 neighbors, a size filter for noise, and a blob cut off by the edge.
Chapter 3

Edges and motion

  1. EdgesWhere the temperature changes: the Sobel filter in whole numbers, why the hottest pixel has no edge, why edges ignore the room temperature, an outline threshold, and a better cheap stand-in for the square root.
  2. TrackingFollow each crew member from frame to frame: blob centers matched to tracks by distance, a direction from the motion, a gate that refuses a teleport, and patience for someone who drops out of view.
Chapter 4

Boss: the airlock counter

  1. Boss: a person counterThe airlock crew counter: thresholds, blobs and tracks count crew in and out across a line, a dead band stops a hesitant crew member being counted three times, and the hatch knows when everyone is aboard.
Kits

Build it on your bench too

Every lesson runs in the simulator with nothing to buy. When you want the real thing, these kits have the parts.

Have a kit already?

Find your kit

Pick the starter kit you own and run every lesson in its manual with the same parts on the same pins.

See every kit
Questions

About Image processing on a thermal camera

Is Image processing on a thermal camera free?

Yes. All 7 lessons of Image processing on a thermal camera are free and run in your browser, with nothing to install and no parts to buy before you start.

Do I need a real Arduino Uno R3?

No. Every lesson runs on a simulated Arduino Uno R3 with its parts on the canvas, and the simulator checks each step as you go. When you want to build it for real, the same wiring and code work on a real board.

How long does Image processing on a thermal camera take?

About 6 hours: 7 lessons in 4 chapters, each one a few short steps. Your progress is kept, so you can stop after any lesson and pick up where you left off.

What will I build?

Each chapter ends in a project that puts it together: Interpolation, Blobs and Tracking.

Where do I start?

With "Images as grids", and each lesson builds on the one before it. New to circuits? Electronics basics is the course that starts from zero.