Home
Introduction
Basic Image Manipulation
Image Noise
Filtering
Linearity and Convolution
Boundary Issues
Filters as Templates
Edge Detection
Gradients
Two Dimensional Detection
From Gradients to Edges
Hough Transform
Line Fitting
Voting
Hough Transform
Polar Representation of Lines
Hough Algorithm
Extensions - Using the Gradient
Finding Circles
Generalization - Hough Table
Camera and Images
Camera
Blur
Lenses
Perspective Imaging
Homogeneous Coordinates
Geometry in Perspective
Orthographic Projection
Weak Perspective
Stereo Geometry
Basic Stereo Geometry
Epipolar Geometry
Stereo Correspondence
Better Stereo Correspondence
Geometric Camera Calibration
Extrinsic Parameters
Intrinsic Parameters
Combining Extrinsic and Intrinsic Calibration Parameters
Calibrating Cameras
Multiple Views
Image-to-Image Projections
The Power of Homographies
Projective Geometry
Essential Matrix
Fundamental Matrix
Feature Recognition
Introduction to Features
Finding Interest Points
Harris Corners
Scale Invariance (SIFT Detector)
Matching Interest Points
SIFT Descriptor
Matching Feature Points
Feature Points for Object Recognition
Feature-Based Alignment
Outlier Rejection
Error Functions
RANSAC
Motion
Motion Estimation
Lucas-Kanade
Motion Models
Known Motion Geometry
Geometric Motion Constraints
Layered Motion
Tracking
Tracking with Dynamics
Tracking as Inference
Tracking as Induction
Prediction
Correction
Kalman Filter
Problem Sets
Object Tracking and Pedestrian Detection
Published with GitBook
Matching Interest Points
Matching Interest Points
Descriptor
Describe the point in one image and find a matching description in the right image.
Invariant: they should be almost the same in both imae
Distinctive
results matching "
"
No results matching "
"