Computer Vision BAI515A

Computer Vision BAI515A

Computer Vision BAI515A

Course Code: BAI515A

Credits: 03

CIE Marks: 50

SEE Marks: 50

Total Marks: 100

Exam Hours: 03

Total Hours of Pedagogy: 40H

Teaching Hours/Weeks: [L:T:P:S] 3:0:0:0

Radiometry – Measuring Light: Light in Space, Light Surfaces, Important Special Cases. Sources, Shadows.

Shading: Qualitative Radiometry, Sources and Their Effects, Local Shading Models.

Application: Photometric Stereo, Interreflections: Global Shading.

Color: The Physics of Color, Human Color Perception, Representing Color, A Model for Image Color, Surface Color from finite dimensional linear models.

Linear Filters: Linear Filters and Convolution, Shift Invariant Linear Systems, Spatial Frequency and Fourier Transforms, Sampling and Aliasing, Filters as Templates.

Edge Detection: Noise, Estimating Derivatives.

Texture: Representing Texture, Analysis (and Synthesis) Using Oriented Pyramids.

Application: Synthesis by Sampling Local Models.

The Geometry of Multiple Views: Two Views.

Stereopsis: Reconstruction, Human Stereopsis- Binocular Fusion, Using More Cameras, Using more cameras.

Segmentation by Clustering: Human Vision: Grouping and Gestalt.

Applications: Shot Boundary Detection and Background Subtraction, Image segmentation by Clustering Pixels.

Segmentation by Fitting a Model: The Hough Transform, Fitting Lines, Fitting Curves.

Segmentation and Fitting Using Probabilistic Methods: Missing Data Problems, Fitting, and Segmentation, The EM Algorithm in Practice.

Tracking With Linear Dynamic Models: Tracking as an Abstract Inference Problem, Linear Dynamic Models and Kalman Filtering.

Geometric Image features: Elements of differential geometry.

Geometric Camera Models: Elements of Analytical Euclidean Geometry, Geometric Camera Parameters.

Calibration Methods: A Linear Approach to Camera Calibration technique- Linear Least-Square methods, Taking Radial Distortion into Account, Analytical Photogrammetry technique- Nonlinear least squares methods.

Leave a Reply

Your email address will not be published. Required fields are marked *