OpenCV Computer Vision with Python, Notas de estudo de Computação Aplicada

Baixe OpenCV Computer Vision with Python e outras Notas de estudo em PDF para Computação Aplicada, somente na Docsity!

OpenCV Computer Vision with

Python

Learn to capture videos, manipulate images, and track

objects with Python using the OpenCV Library

Joseph Howse

BIRMINGHAM - MUMBAI

Credits

Author Joseph Howse

Reviewer(s) David Millán Escrivá Abid K.

Acquisition Editor Erol Staveley

Commissioning Editor Neha Nagvekar

Technical Editors Ankita Meshram Veena Pagare

Project Coordinator Sneha Modi

Proofreader Lauren Tobon

Indexer Rekha Nair

Production Coordinator Arvindkumar Gupta

Cover Work Arvindkumar Gupta

About the Author

Joseph Howse (Joe) is fanciful. So to him, the virtual world always seemed

to reach out into reality. One of his earliest memories is of watching an animated time-bomb on the screen of a Tandy Color Computer. The animation was programmed in BASIC by Joe's older brother, Sam, who explained, "I'm making a bomb. Get ready!" The bomb exploded in a rain of dots and a rumble of beeps as Joe and Sam ran to hide from the fallout.

Today, Joe still fancies that a computer program can blast a tunnel into reality. As a hobby, he likes looking at reality through the tunnel of a digital camera's lens. As a career, he develops augmented reality software, which uses cameras and other sensors to composite real and virtual scenes interactively in real time.

Joe holds a Master of Computer Science degree from Dalhousie University. He does research on software architecture as applied to augmented reality.

Joe works at Ad-Dispatch, an augmented reality company, where he develops applications for mobile devices, kiosks, and the Web.

Joe likes cats, kittens, oceans, and seas. Felines and saline water sustain him. He lives with his multi-species family in Halifax, on Canada's Atlantic coast.

I am able to write and to enjoy writing because I am constantly encouraged by the memory of Sam and by the companionship of Mom, Dad, and the cats. They are my fundamentals.

I am indebted to my editors and reviewers for guiding this book to completion. Their professionalism, courtesy, good judgment, and passion for books are much appreciated.

Abid K. is a student from India pursuing M.Tech in VLSI Design at National

Institute of Technology (Suratkal). He finished his B.Tech in Electronics & Communication. He is particularly interested in developing hardware architectures for image processing and speech processing algorithms.

He started using OpenCV Python in his college days as a hobby. The lack of learning resources on OpenCV Python at that time made him to create his own blog, www.opencvpython.blogspot.com, and he still maintains it. In his free time, he used to answer questions related to OpenCV Python at stackoverflow.com, and those discussions are reflected in his blog articles. He also works as a freelancer during college holidays and even helps school students grow their interest in OpenCV Python and computer vision.

Congrats to the author and all those who worked on this book. I think this might be the first book exclusively on OpenCV Python. And thanks to the editors and publishers who gave me a chance to work on the publication of this book.

Thanks to all my friends who introduced OpenCV to me and helped me learn it.

www.PacktPub.com

Support files, eBooks, discount offers and more

You might want to visit www.PacktPub.com for support files and downloads related to your book.

Did you know that Packt offers eBook versions of every book published, with PDF and ePub files available? You can upgrade to the eBook version at www.PacktPub. com and as a print book customer, you are entitled to a discount on the eBook copy. Get in touch with us at [email protected] for more details.

At www.PacktPub.com, you can also read a collection of free technical articles, sign up for a range of free newsletters and receive exclusive discounts and offers on Packt books and eBooks.

http://PacktLib.PacktPub.com

Do you need instant solutions to your IT questions? PacktLib is Packt's online digital book library. Here, you can access, read and search across Packt's entire library of books.

Why Subscribe?

• Fully searchable across every book published by Packt
• Copy and paste, print and bookmark content
• On demand and accessible via web browser

Free Access for Packt account holders

If you have an account with Packt at www.PacktPub.com, you can use this to access PacktLib today and view nine entirely free books. Simply use your login credentials for immediate access.

Table of Contents

Table of Contents

Preface

This book will show you how to use OpenCV's Python bindings to capture video, manipulate images, and track objects with either a normal webcam or a specialized depth sensor, such as the Microsoft Kinect. OpenCV is an open source, cross-platform library that provides building blocks for computer vision experiments and applications. It provides high-level interfaces for capturing, processing, and presenting image data. For example, it abstracts details about camera hardware and array allocation. OpenCV is widely used in both academia and industry.

Today, computer vision can reach consumers in many contexts via webcams, camera phones, and gaming sensors such as the Kinect. For better or worse, people love to be on camera, and as developers, we face a demand for applications that capture images, change their appearance, and extract information from them. OpenCV's Python bindings can help us explore solutions to these requirements in a high-level language and in a standardized data format that is interoperable with scientific libraries such as NumPy and SciPy.

Although OpenCV is high-level and interoperable, it is not necessarily easy for new users. Depending on your needs, OpenCV's versatility may come at the cost of a complicated setup process and some uncertainty about how to translate the available functionality into organized and optimized application code. To help you with these problems, I have endeavored to deliver a concise book with an emphasis on clean setup, clean application design, and a simple understanding of each function's purpose. I hope you will learn from this book's project, outgrow it, and still be able to reuse the development environment and parts of the modular code that we have created together.

Preface

[ 3 ]

What you need for this book

This book provides setup instructions for all the relevant software, including package managers, build tools, Python, NumPy, SciPy, OpenCV, OpenNI, and SensorKinect. The setup instructions are tailored for Windows XP or later versions, Mac OS 10.6 (Snow Leopard) or later versions, and Ubuntu 12.04 or later versions. Other Unix-like operating systems should work too, if you are willing to do your own tailoring of the setup steps. You need a webcam for the core project described in the book. For additional features, some variants of the project use a second webcam or even an OpenNI-compatible depth camera, such as Microsoft Kinect or Asus Xtion PRO.

Who this book is for

This book is great for Python developers who are new to computer vision and who like to learn through application development. It is assumed that you have some previous experience in Python and the command line. A basic understanding of image data (for example, pixels and color channels) would also be helpful.

Conventions

In this book, you will find a number of styles of text that distinguish between different kinds of information. Here are some examples of these styles, and an explanation of their meaning.

Code words in text are shown as follows: "The two executables on Windows are called ONopencv_createsamples.exe and ONopencv_traincascade.exe."

A block of code is set as follows:

negative desc.txt images negative 0.png negative 1.png

Any command-line input or output is written as follows:

> cd negative

> forfiles /m images*.png /c "cmd /c echo @relpath" > desc.txt

Preface

[ 4 ]

New terms and important words are shown in bold. Words that you see on the screen, in menus or dialog boxes for example, appear in the text like this: "clicking the Next button moves you to the next screen".

Warnings or important notes appear in a box like this.

Tips and tricks appear like this.

Reader feedback

Feedback from our readers is always welcome. Let us know what you think about this book—what you liked or may have disliked. Reader feedback is important for us to develop titles that you really get the most out of.

To send us general feedback, simply send an e-mail to [email protected], and mention the book title via the subject of your message.

If there is a topic that you have expertise in and you are interested in either writing or contributing to a book, see our author guide on www.packtpub.com/authors.

Customer support

Now that you are the proud owner of a Packt book, we have a number of things to help you to get the most from your purchase.

Downloading the example code

You can download the example code files for all Packt books you have purchased from your account at http://www.packtpub.com. If you purchased this book elsewhere, you can visit http://www.packtpub.com/support and register to have the files e-mailed directly to you. The example code for this book is also available from the author's website at http://nummist.com/opencv/.

Setting up OpenCV

This chapter is a quick guide to setting up Python 2.7, OpenCV, and related libraries. After setup, we also look at OpenCV's Python sample scripts and documentation.

The following related libraries are covered:

• NumPy : This is a dependency of OpenCV's Python bindings. It provides numeric computing functionality, including efficient arrays.
• SciPy : This is a scientific computing library that is closely related to NumPy. It is not required by OpenCV but it is useful for manipulating the data in OpenCV images.
• OpenNI : This is an optional dependency of OpenCV. It adds support for certain depth cameras, such as Asus XtionPRO.
• SensorKinect : This is an OpenNI plugin and optional dependency of OpenCV. It adds support for the Microsoft Kinect depth camera.

For this book's purposes, OpenNI and SensorKinect can be considered optional. They are used throughout Chapter 5 , Separating Foreground/Background Regions Depth , but are not used in the other chapters or appendices.

At the time of writing, OpenCV 2.4.3 is the latest version. On some operating systems, it is easier to set up an earlier version (2.3.1). The differences between these versions should not affect the project that we are going to build in this book.

Some additional information, particularly about OpenCV's build options and their dependencies, is available in the OpenCV wiki at http://opencv.willowgarage. com/wiki/InstallGuide. However, at the time of writing, the wiki is not up-to-date with OpenCV 2.4.3.