Structure Fom Motion (

Course Objectives

This is an introductory course on computer vision and computational photography. This course will explore image formation, image features, image segmentation, image stitching, image recognition, motion estimation, 3D point clouds and will touch upon basics of augmented reality.


The following list of topics is very tentative. Depending on time, some topics may be added or dropped, and the order of topics may change.

What is Computer Vision? Ongoing Research and Application Areas
Image Formation:
Geometric aspects, Radiometric Aspects, Digital Images, The Human Eye, Camera parameters
Linear Filters and Convolution, Spatial Frequency and Fourier Transform, Sampling and Aliasing, Noise Reduction
Edge Detection:
Gradient based Edge Detectors, Laplacian, Parametric Models
Other Image Features:
Hough Transform, Ellipse fitting, Deformable contours
Lightness and Color:
Surface Reflectance, Recovering Lightness, The Physics of Color Human Color Perception, Color Representations
Camera Calibration:
Intrinsic Parameters, Extrinsic Parameters
Muliple View Geometry:
Stereo, The Correspondence Problem, Epipolar Geometry, 3D Reconstruction
The Image Motion Field, Estimation of 3D Motion and Structure, Segmentation on the basis of different Motion, Image Compression
Shape from Single Image Cues:
Surface Descriptions, Shape from Contours, Shape from Shading, Shape from Texture

  Return to CMSC 733 Home  —  The cool image at top of page is from the Structure From Motion by Princeton University's Vision and Robotics Group

Web Accessibility