Revision a1044ece416ec3f4bda107f9d4a54e552c220ba8 (click the page title to view the current version)
Changes from a1044ece416ec3f4bda107f9d4a54e552c220ba8 to 003df9f48baab68d2675692f80b285d795b96f1e
---
title: Lecture - Real World Reconstruction
---
**Reading** Ma 2004:Ch 11
# Overview
1. [Feature Detection](#fd)
2. [Feature Correspondence](#fc)
3. [Projective Reconstruction](#pr)
3. [Euclidean Reconstruction](#er)
# Feature Detection {#fd}
+ Harris Detector
+ Tiling
- divide the image into, say, $10\times10$ tiles
- select features per tile
+ Separation
- one feature may cause several pixels to be marked as a corner
- separation should be larger than the windows size used in detection
+ Sorting by strength
- sort first, and then select from top of the list
- enforce separation from previously selected features
# Feature Correspondence {#fc}
+ Small Baseline (motion video)
- feature tracking - calculate motion
+ Moderate Baseline (snapshots)
+ Wide Baseline -> use SIFT or similar methods
- the textbook is outdated on this point
## Multiscale iterative feature tracking
**TODO**
# Projective Reconstruction {#pr}
# Euclidean Reconstruction {#er}