KinetiqVision
← Back to curriculum

Module 2 — Geometry & correspondence

Welcome to Module 2

How Module 2 builds on Module 1, coordinate frames in vision, what you will learn, and prerequisites for the stitching project.

~25 min read + exercises

Welcome to Module 2 — geometry & correspondence

Before we begin

Module 1 gave you pixels and filters. Module 2 asks: where did those pixels come from in the 3D world, and how do we match points between images?

You will learn pinhole projection, features, RANSAC, stereo depth, and build a panorama stitcher.

Figure

Module 2 at a glance

Module 2 — geometry pathWork top to bottom. Each lesson builds on the previous one.1Welcomeyou are here2Camerasprojection3Featuresmatching4Stereodepth5Quizself-check6Projectpanorama
Cameras, features, stereo, quiz, then panorama project.

What Module 2 covers

TopicWhat you will understand
Camera modelsIntrinsics K, extrinsics [R|t], distortion
FeaturesCorners, descriptors, matching
Robust estimationRANSAC, homography, epipolar geometry
StereoDisparity, depth, triangulation

Prerequisites

Complete Module 1 project or at minimum Lessons 1–2 (convolution intuition).

Install for project: pip install opencv-python numpy matplotlib

What's next

Lesson 1 — Camera models and projection