Computer Vision for Everyone
Connect camera geometry, visual features, motion, detection, and evaluation in practical vision systems.
Before you start: Image Processing foundations and basic coordinate arithmetic.
Start Lesson 1
Your module quizzes
Five multiple-choice questions after each module. Get a percentage and feedback, review explanations, and retry anytime. Aim for 80%; quizzes never lock lessons.
Sign in to save your personal results, or practice as a guest.
20 modules, 80 lessons
Follow the modules in order, or open any lesson to review a specific concept. Every lesson includes reading, practice, a quick check, and a transcript. Published videos include optional English captions.
Cameras and Geometry
Lessons 1–4 · 4/4 videos available
Choose the Right Vision Task
A camera watches a parking lot with twelve marked spaces.
How a Camera Turns a Scene into Pixels
Look again at our parking-lot image.
Calibration and Lens Distortion
Straight building edges sometimes curve near the edge of a photograph.
Perspective Warps and Planar Maps
A photographed document looks like a trapezoid, but its page is approximately flat.
Module 1 quiz
5 questions · score and feedback · retry anytime
Features and Motion
Lessons 5–8 · 4/4 videos available
Corners, Features, and Descriptors
You recognize a building from another angle partly because distinctive details remain recognizable.
Match Images Without Trusting Every Match
Two photographs produce a web of lines between matched features.
Optical Flow: Motion in the Image
A ball moves across a video frame, and its pixels shift.
Tracking an Object Across Frames
A detector finds three cars in one frame and three in the next.
Module 2 quiz
5 questions · score and feedback · retry anytime
Depth, Recognition, and Evaluation
Lessons 9–12 · 4/4 videos available
Stereo Vision and Depth
Hold a finger in front of your face and alternate which eye is open.
Detection and Segmentation in Practice
A box around a tree includes branches, leaves, and plenty of background.
Overlap, Precision, and Recall
A predicted box looks close to the correct box, but how close is enough? Intersection over union, or IoU, compares the overlapping area with the total area covered by either box.
Build a Dataset That Tests Generalization
A model performs brilliantly on held-out video frames, then fails on a new camera.
Module 3 quiz
5 questions · score and feedback · retry anytime
Practical Vision Systems
Lessons 13–16 · 4/4 videos available
Make Vision Fast Enough for the Workflow
A model may predict quickly while the user still waits several seconds for a box.
Confidence, Uncertainty, and Human Review
A detection marked 0.9 can look reassuring, but that number is not automatically a 90 percent guarantee of correctness.
Design a Responsible Vision Workflow
A camera can capture more information than a project needs.
Capstone: A Parking-Occupancy Prototype
Let us build a practical parking-occupancy prototype.
Module 4 quiz
5 questions · score and feedback · retry anytime
Coordinate Frames and Projection
Lessons 17–20 · 4/4 videos available
Describe Points in Camera and World Coordinates
A point marked on the parking-lot floor has a different location in the camera image.
What Camera Intrinsics Mean
The same world point moves in the image after changing the lens.
Move a Camera with Extrinsics
A technician moves the parking camera to a new pole.
Check Projection Against Image Points
A projected space corner misses its observed pixel by several pixels.
Module 5 quiz
5 questions · score and feedback · retry anytime
Calibration and Measurement
Lessons 21–24 · 4/4 videos available
Capture Useful Calibration Views
The calibration board fills only the middle of every photograph.
Estimate Distortion from a Pattern
Straight board lines bow near the edge of a wide lens.
Read Reprojection Error Honestly
A report says the calibration error is 0.4 pixels.
Measure a Planar Region with a Homography
Parking spaces on a flat pavement have different image shapes.
Module 6 quiz
5 questions · score and feedback · retry anytime
Local Visual Features
Lessons 25–28 · 4/4 videos available
Why Corners Survive Small View Changes
The robot revisits a doorway from a slightly changed position.
Detect Useful Keypoints
Thousands of candidate points appear in one textured wall.
Describe a Patch for Matching
The same door corner appears at two nearby camera positions.
Handle Scale and Rotation Changes
A camera approaches the door and rotates slightly.
Module 7 quiz
5 questions · score and feedback · retry anytime
Robust Image Matching
Lessons 29–32 · 4/4 videos available
Filter Descriptor Matches
The panorama tool finds several matches on repeated windows.
Fit a Transform with RANSAC
A few false correspondences pull the fitted panorama sideways.
Stitch Images into a Panorama
Two overlapping square photographs need one wide view.
Recognize When a Match Is Geometrically Wrong
A stitched skyline looks plausible while the foreground doubles.
Module 8 quiz
5 questions · score and feedback · retry anytime
Multiple-View Geometry
Lessons 33–36 · 4/4 videos available
Two Cameras and the Epipolar Constraint
Two cameras view one point on the parking-lot pavement.
Find Corresponding Points Across Views
Many bricks look alike in the two camera images.
Triangulate a Point from Two Rays
The two cameras locate one corner in both views.
Watch for Small-Baseline Failure
Both cameras are almost in the same position.
Module 9 quiz
5 questions · score and feedback · retry anytime
Depth and Motion
Lessons 37–40 · 0/4 videos available
Convert Stereo Disparity to Depth
A stereo rig sees a nearby bollard shifted strongly between images.
Check Where Stereo Matching Fails
A stereo depth map gives scattered distances on the blank side of a van.
Interpret Optical Flow Under Camera Motion
A car appears to move while the parking camera shakes.
Separate Object Motion from Camera Motion
A swaying camera pole makes parked cars appear to move.
Module 10 quiz
5 questions · score and feedback · retry anytime
Video Tracking
Lessons 41–44 · 0/4 videos available
Detect Objects Frame by Frame
The parking system detects a car separately in each video frame.
Associate Detections Through Time
Two cars cross in the camera view.
Recover from Occlusion and Missed Frames
A delivery van hides a parked car for two frames.
Evaluate Tracks and Identity Switches
A tracker counts vehicles well but keeps swapping their names.
Module 11 quiz
5 questions · score and feedback · retry anytime
Image Search
Lessons 45–48 · 0/4 videos available
Turn an Image into a Search Representation
An operator searches an archive for signs with similar damage.
Index a Visual Collection
The archive grows to a million parking-sign photographs.
Rank Similar Images
A clean blue sign outranks a bent gray sign in damage search.
Verify Retrieval with Geometry
Two garages look similar but may not be the same place.
Module 12 quiz
5 questions · score and feedback · retry anytime
Image Classification
Lessons 49–52 · 0/4 videos available
Start with a Feature-Based Baseline
The team needs a transparent damaged-sign classifier.
Nearest-Neighbor Classification of Images
A damaged sign looks most similar to clean signs with the same paint.
Probabilistic and Margin-Based Alternatives
A nearest-photo rule struggles with bent signs and glare.
Inspect Confident Classification Mistakes
A classifier confidently calls a bent sign undamaged.
Module 13 quiz
5 questions · score and feedback · retry anytime
Object Detection
Lessons 53–56 · 0/4 videos available
Represent Boxes and Confidence
A street photograph contains two parking signs that need separate boxes.
Resolve Duplicate Boxes
One parking sign produces several overlapping boxes.
Read Precision-Recall for a Detector
A threshold misses distant signs while a lower one flags reflections.
Diagnose Small and Occluded Objects
Distant and partly hidden signs are both missed for different reasons.
Module 14 quiz
5 questions · score and feedback · retry anytime
Image Segmentation
Lessons 57–60 · 0/4 videos available
Semantic Labels for Every Pixel
The city needs a pixel-level map of roadside tree cover.
Separate Instances of the Same Class
Two tree canopies touch, but the city needs separate tree counts.
Measure Mask Overlap and Boundary Quality
A canopy mask has good area overlap but misses thin branches.
Audit Inconsistent Mask Annotations
Annotators disagree whether a tree shadow belongs in its mask.
Module 15 quiz
5 questions · score and feedback · retry anytime
Pose and Augmented Views
Lessons 61–64 · 0/4 videos available
Find a Planar Marker
A square marker beside an exhibit is visible in the guide camera.
Estimate Camera Pose from Geometry
A virtual caption should follow the exhibit as the camera moves.
Place Graphics in the Camera View
The virtual label floats away from the exhibit during a turn.
Test Pose Under Motion and Poor Light
Motion blur and dim lighting make the marker hard to find.
Module 16 quiz
5 questions · score and feedback · retry anytime
Document and Scene Understanding
Lessons 65–68 · 0/4 videos available
Locate Text in an Image
A scanned form contains text in several locations.
Recognize and Validate Text
The reader extracts a postal code from a blurred form.
Read a Form as Structured Fields
The same words appear under different labels on two forms.
Review Ambiguous Scene Predictions
A scene label is uncertain because a sign is partly hidden.
Module 17 quiz
5 questions · score and feedback · retry anytime
Vision Data and Evaluation
Lessons 69–72 · 0/4 videos available
Write an Annotation Guide
Annotators disagree whether a vehicle entering a space counts as parked.
Split by Camera, Time, and Scene
Frames from the same camera appear in both training and test sets.
Evaluate by Conditions and Subgroups
The system works by day but misses spaces at night.
Test a New Camera Domain
A new camera has a different angle and sensor.
Module 18 quiz
5 questions · score and feedback · retry anytime
Vision Deployment
Lessons 73–76 · 0/4 videos available
Measure End-to-End Latency
The camera captures a frame every second but the service responds too late.
Tune a Review Threshold
A doubtful space prediction could trigger an unnecessary warning.
Watch for Camera Drift
A camera slowly tilts after maintenance.
Plan Safe Updates to the Vision System
A revised model improves recall but breaks several night scenes.
Module 19 quiz
5 questions · score and feedback · retry anytime
Final Vision Project
Lessons 77–80 · 0/4 videos available
Define a Parking-Space Decision
The owner asks for a trustworthy count of free spaces.
Build the Camera-to-Output Pipeline
The team connects capture, space regions, predictions, and a count.
Test Occlusion, Night, and Empty Scenes
The first tests miss vehicles at night and flag shadows as cars.
Present Errors and Reproducible Results
A second team wants to reproduce the parking result.
Module 20 quiz
5 questions · score and feedback · retry anytime
References and further reading
These books guide the topic selection and provide deeper study. ToolsInVision's explanations, worked examples, and exercises are original teaching material; the books are not reproduced here.
Programming Computer Vision with Python — Jan Erik Solem. Further study of image handling, features, camera geometry, multiple views, and recognition.