Tutorials

The following links describe a set of kwiver tutorials. All the source code mentioned here is provided by the repository.

Visit the repository on how to get and build the KWIVER code base

As always, we would be happy to hear your comments and receive your contributions on any tutorial.

Fundamental Types and Algorithms

The following tutorials will demonstrate the basic functionality provided in kwiver. They will focus on the vital types available in kwiver and the various algorithm interfaces currelty supported. Each example highlights an area of functionality provied in KWIVER. The KWIVER examples directory contains executable code demonstrating the use of these types with various arrow implementations of the highligted algorithms.

Images Learn about the fundamental image types and some basic I/O and algorithms
Detection Focus on the data structures and algorithms used by object detection

Sprokit Pipelines

The following tutorials will use Sprokit pipeline files to chain together various algorithms to demonstrate applied examples. The KWIVER examples directory contains executable pipe files for each of the table entries below. In order to execute the provided pipeline file, follow the steps to set up KWIVER here

Numbers Flow A simple ‘Hello World’ pipeline that outputs numbers to a file
Image Display A pipe that loads and displays several images
Video Display A pipe that loads and displays a video file
Hough Detection Detect circles in images using a hough detector
Darknet Detection Object detection using the Darnket library
Image Stabilization Something cool that Matt Brown has done