Chapter 1: Introduction

KLT has been designed to be easy to use. It should take no more than a few minutes to learn how to select and track features, and store and use the results. For those who wish to maximize performance, however, the program allows the flexibility of tweaking nearly every parameter that governs the computation, as well as methods to improve speed.

This manual guides the user, in a tutorial fashion, through the essentials of KLT. Chapter 2 contains all that you need to select good features, track them from one image to the next, and write the results. When features are lost (due to their drifting out of bounds or a nearly singular matrix in the tracking equation, etc.), they can be replaced by finding features in the new image, a process which is described in Chapter 3. Chapter 4 explains a technique for speeding up the computation in the case of tracking through an image sequence. Chapter 5 describes an extension allowing the features from multiple frames to be stored in one data structure, which can then be saved to a file. Chapter 6 shows how to recall this structure and extract features from it. Finally, Chapter 7 shows how to customize the tracker by manually setting the various parameters.

Most of these chapters contain example code, which is also provided with the distribution of KLT. To compile your own code, simply put the line #include "klt.h" near the top of your file, and link with the KLT library as in this example: cc file.c -lklt.