Book Image

Android Application Programming with OpenCV

By : Joseph Howse
Book Image

Android Application Programming with OpenCV

By: Joseph Howse

Overview of this book

Take a smartphone from your pocket, and within a few seconds, you can snap a photo, manipulate it, and share it with the world. You have just achieved mass production of image data. With a computer vision library such as OpenCV, you can analyze and transform copious amounts of image data in real time on a mobile device. The upshot to this is that you, as developers, can provide mobile users with many new kinds of images, constantly highlighting certain visual features that are of artistic or practical interest. Android is a convenient platform for such experiments because it uses a high-level language (Java), it provides standardized interfaces for sharing image data between applications, and it is mostly open source, so everyone can study its implementation. Android Application Programming with OpenCV is a practical, hands-on guide that covers the fundamental tasks of computer vision—capturing, filtering, and analyzing images-with step-by-step instructions for writing both an application and reusable library classes. Android Application Programming with OpenCV looks at OpenCV's Java bindings for Android and dispels mysteries such as which version of these bindings to use, how to integrate with standard Android functionality for layout, event handling, and data sharing, and how to integrate with OpenGL for rendering. By following the clear, concise, and modular examples provided in this book, you will develop an application that previews, captures, and shares photos with special effects based on color manipulation, edge detection, image tracking, and 3D rendering.Beneath the application layer, you will develop a small but extensible library that you can reuse in your future projects. This library will include filters for selectively modifying an image based on edge detection, 2D and 3D image trackers, and adapters to convert the Android system's camera specifications into OpenCV and OpenGL projection matrices. If you want a quick start in computer vision for Android, then this is the book for you. By the end of Android Application Programming with OpenCV, you will have developed a computer vision application that integrates OpenCV, Android SDK, and OpenGL.
Table of Contents (12 chapters)
Android Application Programming with OpenCV
Credits
About the Author
About the Reviewers
www.PacktPub.com
Preface
Index

Understanding image tracking


Imagine the following conversation:

Person A: I can't find my print of The Starry Night. Do you know where it is?

Person B: What does it look like?

For a computer, or for someone who is naive about Western art, Person B's question is quite reasonable. Before we can use our sense of sight (or other senses) to track something, we need to have sensed that thing before. (Failing that, we at least need a good description of what we will sense.) For computer vision, we must provide a reference image that will be compared with the live camera image or scene. If the target has complex geometry or moving parts, we might need to provide many reference images to account for different perspectives and poses. However, for our examples using famous paintings, we will assume that the target is rectangular and rigid.

For this chapter's purposes, let's say that the goal of tracking is to determine how our rectangular target is posed in 3D. With this information, we can draw an outline...