Practical OpenCV is a hands-on project book that shows you how to get the best results from OpenCV, the open-source computer vision library.
Computer vision is key to technologies like object recognition, shape detection, and depth estimation. OpenCV is an open-source library with over 2500 algorithms that you can use to do all of these, as well as track moving objects, extract 3D models, and overlay augmented reality. It's used by major companies like Google (in its autonomous car), Intel, and Sony; and it is the backbone of the Robot Operating System's computer vision capability. In short, if you're working with computer vision at all, you need to know OpenCV.
With Practical OpenCV, you'll be able to:
Get OpenCV up and running on Windows or Linux.
Use OpenCV to control the camera board and run vision algorithms on Raspberry Pi.
Understand what goes on behind the scenes in computer vision applications like object detection, image stitching, filtering, stereo vision, and more.
Code complex computer vision projects for your class/hobby/robot/job, many of which can execute in real time on off-the-shelf processors.
Combine different modules that you develop to create your own interactive computer vision app.
What you'll learn
The ins and outs of OpenCV programming on Windows and Linux
Transforming and filtering images
Detecting corners, edges, lines, and circles in images and video
Detecting pre-trained objects in images and video
Making panoramas by stitching images together
Getting depth information by using stereo cameras
Basic machine learning techniques
BONUS: Learn how to run OpenCV on Raspberry Pi
Who this book is for
This book is for programmers and makers with little or no previous exposure to computer vision. Some proficiency with C++ is required.