Free interactive course · 14 lessons

Computer Vision I
from pixels to 3D worlds

Teach a computer to see, one algorithm at a time. Every lesson runs real OpenCV programs in Python right in your browser, shows the same program in C++, and lets you take each algorithm apart in a live image lab.

  • No install, no sign-up
  • Python & C++ with OpenCV
  • Live labs on real images

Python runs in your browser · progress saved locally

peppers.png original
computed in your browser
14Lessons
5Parts
2Languages per program
100%Free access
How it works

Read a little. See a lot.

Vision is learned by watching algorithms work on real images. Each lesson alternates short explanations with programs you run and labs where you move every parameter.

Short, concrete theory

One idea at a time, with the formula, the numbers and the pictures. Built from a university course on computer vision.

Run real OpenCV

Press Run and the Python program executes in your browser with OpenCV 4.10. Edit it, script key presses, see every window it opens.

Python and C++

Every program exists in both languages with the same windows and keys. Download either file and run it on your machine.

Live labs and quizzes

Drag sliders on real images, watch histograms, kernels and RANSAC update, then check yourself with an explained quiz and a practice task.

See it run

Two programs from the course

Both run in this page. Press Run on the Python tab, change a threshold, run again — or switch to C++ to see the same program built with g++.

05

Edges in one call

Lesson 5 · the Canny edge detector

13

Two photos, one panorama

Lesson 13 · features, RANSAC and a homography

Syllabus

Fourteen lessons, one continuous path

Five parts, each answering a question the previous part leaves open. Start at lesson 1 — every lesson assumes only the ones before it, plus basic Python.

Your progress 0 / 14
Start the course
What you get

Algorithms you can explain and rebuild

When you finish lesson 14 you will not just know which OpenCV function to call. You will know what it computes, which parameter breaks it, and how to write it yourself.

Process images with intent

Point operations, histograms, thresholds, convolution kernels, edges and morphology — and a change detector that finds people in a surveillance video.

Model the camera

The pinhole model x = K[R | t]X, lens distortion, calibration from a chessboard and camera pose from known points.

Match and fit robustly

Harris, SIFT and ORB features, ratio-test matching, optical flow, least squares and RANSAC — ending with a panorama stitcher.

Reason in 3D

Homographies, triangulation, two-view geometry, structure-from-motion and the volume rendering behind NeRF.

“Graphics turns a 3D world into pixels. Vision runs the film backwards — and every lesson in this course is one frame of that reversal.”

Computer Vision I · lesson 1
FAQ

Before you open the first image

The practical details.

Do I need to install anything?
No. The Python examples run in your browser with Pyodide, NumPy and OpenCV (about 30 MB, downloaded once on your first Run and then cached). To run the programs on your own machine: pip install opencv-python numpy scipy matplotlib for Python, and OpenCV 4 with g++ -std=c++17 file.cpp $(pkg-config --cflags --libs opencv4) for C++.
What do I need to know first?
Basic Python (variables, loops, functions, lists) and school algebra. NumPy arrays, matrices and the linear algebra of the later lessons are introduced as they are needed. C++ is optional — every program has a Python version; the Modern C++ course covers the language itself.
How do OpenCV windows and keys work in a browser?
Every imshow window becomes an image card under the code; video loops become a frame scrubber. waitKey() reads from a Keys box, so you can script +++ or {tab} presses, and mouse callbacks are driven by a scripted mouse path. On your machine the same programs open real windows.
Does the C++ code run in the browser too?
The C++ tab shows the output recorded when the exact program was compiled with g++ and OpenCV 4.5. If you edit the C++, the page gives you the command to build your version locally. Python is the language you can edit and re-run live.
Is my code or progress saved?
Your code runs inside your own browser and is never sent to a server. Completion marks and quiz results live in this browser's localStorage, so they survive a reload but not a different device.
How long does the course take?
About 13–15 hours: 40–65 minutes per lesson including the programs, labs, quiz and practice task.
Free interactive course

Your first image
is one array away.

Then fourteen lessons take you from pixels and filters through camera geometry and feature matching to 3D reconstruction. One idea, one program, one lab at a time.

Free · No sign-up · Real OpenCV output