Lectures

Lecture slides and supporting materials will be added here throughout the semester.

Each lecture is available as an interactive presentation and as a PDF for downloading, printing, or taking notes.

Lecture 01 — Introduction to Computer Vision

Course overview, computer vision applications, and important course logistics.

Lecture 02 — Image Formation and Digital Images

Images as signals, sampling, sensor arrays, resolution, quantization, image arrays, color images, and basic Python image representation.

Lecture 03 — Image Filtering

Local image filtering, correlation, convolution, Gaussian and Sobel filters, separability, template matching, and nonlinear median filtering.

Lecture 04 — Image Pyramids

Image downsampling, aliasing, anti-aliasing, Gaussian image pyramids, Laplacian image pyramids, and multiscale image representations.

Lecture 05 — Fourier Transform

Fourier series, spatial frequency, the discrete Fourier transform, frequency-domain visualization, filtering, convolution, and image sampling.

Lecture 06 — Edge Detection

Image edges, gradients, Gaussian derivatives, and Canny edge detection.

Lecture 07 — Feature Points

Feature detection, description, and matching; Harris corners and SIFT.

Lecture 08 — Hough Transform

Detecting lines and parametric shapes through voting in parameter space.

Lecture 09 — Color

Color perception, representation, and processing in computer vision.

Lecture 10 — Optical Flow

Estimating apparent motion between image frames.

Lecture 11 — Camera Geometry

Pinhole and lens cameras, perspective projection, homogeneous coordinates, transformations, and the camera matrix.

Lecture 12 — Camera Calibration

Camera calibration, intrinsic and extrinsic parameters, and lens distortion.

Lecture 13 — Two-View Geometry

Two-view geometry, epipolar constraints, and 3D reconstruction.

Lecture 14 — Stereo Vision

Stereo vision, disparity, and depth estimation.

Lecture 15 — Machine Learning for Computer Vision

Machine learning foundations for computer vision.

Lecture 16 — Classical Object Detection

Classical object detection methods for computer vision.

No matching items