Joe Minichino - Learning OpenCV 3 Computer Vision with Python

Nandan Banerjee has a bachelor's degree in computer science and a master's in robotics engineering. He started working with Samsung Electronics right after graduation. He worked for a year at its R&D centre in Bangalore. He also worked in the WPI-CMU team on the Boston Dynamics' robot, Atlas, for the DARPA Robotics Challenge. He is currently working as a robotics software engineer in the technology organization at iRobot Corporation. He is an embedded systems and robotics enthusiast with an inclination toward computer vision and motion planning. He has experience in various languages, including C, C++, Python, Java, and Delphi. He also has a substantial experience in working with ROS, OpenRAVE, OpenCV, PCL, OpenGL, CUDA and the Android SDK.

I would like to thank the author and publisher for coming out with this wonderful book.

Tian Cao is pursuing his PhD in computer science at the University of North Carolina in Chapel Hill, USA, and working on projects related to image analysis, computer vision, and machine learning.

I dedicate this work to my parents and girlfriend.

Brandon Castellano is a student from Canada pursuing an MESc in electrical engineering at the University of Western Ontario, City of London, Canada. He received his BESc in the same subject in 2012. The focus of his research is in parallel processing and GPGPU/FPGA optimization for real-time implementations of image processing algorithms. Brandon also works for Eagle Vision Systems Inc., focusing on the use of real-time image processing for robotics applications.

While he has been using OpenCV and C++ for more than 5 years, he has also been advocating the use of Python frequently in his research, most notably, for its rapid speed of development, allowing low-level interfacing with complex systems. This is evident in his open source projects hosted on GitHub, for example, PySceneDetect, which is mostly written in Python. In addition to image/video processing, he has also worked on implementations of three-dimensional displays as well as the software tools to support the development of such displays.

In addition to posting technical articles and tutorials on his website (http://www.bcastell.com), he participates in a variety of both open and closed source projects and contributes to GitHub under the username Breakthrough (http://www.github.com/Breakthrough). He is an active member of the Super User and Stack Overflow communities (under the name Breakthrough), and can be contacted directly via his website.

I would like to thank all my friends and family for their patience during the past few years (especially my parents, Peter and Lori, and my brother, Mitchell). I could not have accomplished everything without their continued love and support. I can't ever thank everyone enough.

I would also like to extend a special thanks to all of the developers that contribute to open source software libraries, specifically OpenCV, which help bring the development of cutting-edge software technology closer to all the software developers around the world, free of cost. I would also like to thank those people who help write documentation, submit bug reports, and write tutorials/books (especially the author of this book!). Their contributions are vital to the success of any open source project, especially one that is as extensive and complex as OpenCV.

Haojian Jin is a software engineer/researcher at Yahoo! Labs, Sunnyvale, CA. He looks primarily at building new systems of what's possible on commodity mobile devices (or with minimum hardware changes). To create things that don't exist today, he spends large chunks of his time playing with signal processing, computer vision, machine learning, and natural language processing and using them in interesting ways. You can find more about him at http://shift-3.com/