6.801 Machine Vision

6.801 Machine Vision (Fall 2020, MIT OCW). Instructor: Prof. Berthold Horn. This course is an introduction to the process of generating a symbolic description of the environment from an image. It covers the physics of image formation, image analysis, binary image processing, and filtering. Machine vision has applications in robotics and the intelligent interaction of machines with their environment. Students taking the graduate version complete additional assignments. (from

Introduction to Machine Vision

Lecture 01 - Introduction to Machine Vision
Lecture 02 - Image Formation, Perspective Projection, Time Derivative, Motion Field
Lecture 03 - Time to Contact, Focus of Expansion, Direct Motion Vision Methods, Noise Gain
Lecture 04 - Fixed Optical Flow, Optical Mouse, Constant Brightness Assumption, Closed Form Solution
Lecture 05 - TCC and FOR MontiVision Demos, Vanishing Point, Use of VPs in Camera Calibration
Lecture 06 - Photometric Stereo, Noise Gain, Error Application, Eigenvalues and Eigenvectors Review
Lecture 07 - Gradient Space, Reflectance Map, Image Irradiance Equation, Gnomonic Projection
Lecture 08 - Shading, Special Cases, Lunar Surface, Scanning Electron Microscope, Green's Theorem
Lecture 09 - Shape from Shading, General Case - From First Order Nonlinear PDE to Five ODEs
Lecture 10 - Characteristic Strip Expansion, Shape from Shading, Iterative Solutions
Lecture 11 - Edge Detection, Subpixel Position, CORDIC, Line Detection (US 6,408,109)
Lecture 12 - Blob Analysis, Binary Image Processing, Green's Theorem, Derivative and Integral
Lecture 13 - Object Detection, Recognition and Pose Determination, PatQuick (US 7,016,539)
Lecture 14 - Inspection in PatQuick, Hough Transform, Homography, Position Determination, Multi-Scale
Lecture 15 - Alignment, PatMax, Distance Field, Filtering and Sub-Sampling (US 7,065,262)
Lecture 16 - Fast Convolution, Low Pass Filter Approximations, Integral Images (US 6,457,032)
Lecture 17 - Photogrammetry, Orientation, Axes of Inertia, Symmetry, Orientation
Lecture 18 - Rotation and How to Represent It, Unit Quaternions, the Space of Rotations
Lecture 19 - Absolute Orientation in Closed Form, Outliers and Robustness, RANSAC
Lecture 20 - Space of Rotations, Regular Tessellations, Critical Surfaces, Binocular Stereo
Lecture 21 - Relative Orientation, Binocular Stereo, Structure, Quadrics, Calibration, Reprojection
Lecture 22 - Exterior Orientation, Recovering Position and Orientation, Bundle Adjustment, Object Shape
Lecture 23 - Gaussian Image, Solids of Revolution, Direction Histograms, Regular Polyhedra

6.801 Machine Vision (Fall 2020)
Instructor: Prof. Berthold Horn. Lecture Notes. Assignments. This course is an introduction to the process of generating a symbolic description of the environment from an image.