I have started to use ARCH ( instead of Ubuntu Server ) in the GuarddoG onboard computer and thus some of the recent work has been finding pacman equivilents to apt-get packages , writing a new service starter that preloads v4l2 compatibility shared objects and some other environment/setup code ..

It is kind of weird to have “officially finished” with something that was such a big part of my everyday life for the last 4-5 years.. and I certainly want ( and probably will ) continue to actively develop it..! The truth though is that major work needs to be done , especially in the hardware/exterior part of the robot.

As always new commits can be found on github .. and due to the repository getting so big , I am thinking of “forking” a new one , probably RoboVisionNG or something like that to start off a fresh git history tree to reduce the size of the repo and remove obsolete history objects..
The RoboVision repository will still remain though..

Some issues remain with the table of contents and other typographic details but the fact of the matter is that the theory , ideas and details have now been passed from thoughts on my mind to paper and I am very happy .

Subjects analyzed for computer vision and robotics are camera calibration ( pinhole model , calibration , rectification ) , basic image processing, disparity mapping ( depth mapping by binocular stereoscopy ) , integral images , haar cascades , corner and feature detection , lukas kanade pyramid optical flow , ransac , A* Pathfinding and many others as well as lots of notes on implementing all these in a compact stack with serious performance considerations.

I hope that people around the web will find my work useful and it will help them understand and organize all those different concepts easier on their mind , since this is the goal of this work..

RoboVision
Mostly written in C
Very few source code comments
Only a single active developer
Estimated project cost: $1,312,081

Codebase for Logic Only
49,134 lines (est.)
12 person-years
Estimated Cost
$ 656,665

https://www.ohloh.net/p/RoboVision
https://www.ohloh.net/p/RoboVision/analyses/latest

Similar Projects

https://www.ohloh.net/p/mrpt
https://www.ohloh.net/p/ROSorg
https://www.ohloh.net/p/yarp
https://www.ohloh.net/p/6399

http://vxl.sourceforge.net/

Introduction: What is VXL?
VXL (the Vision-something-Libraries) is a collection of C++ libraries designed for computer vision research and implementation. It was created from TargetJr and the IUE with the aim of making a light, fast and consistent system. VXL is written in ANSI/ISO C++ and is designed to be portable over many platforms. The core libraries in VXL are:

vnl (numerics): Numerical containers and algorithms. e.g. matrices, vectors, decompositions, optimisers.
vil (imaging): Loading, saving and manipulating images in many common file formats, including very large images.
vgl (geometry): Geometry for points, curves and other elementary objects in 1, 2 or 3 dimensions.
vsl (streaming I/O), vbl (basic templates), vul (utilities): Miscellaneous platform-independent functionality.

As well as the core libraries, there are libraries covering numerical algorithms, image processing, co-ordinate systems, camera geometry, stereo, video manipulation, structure recovery from motion, probability modelling, GUI design, classification, robust estimation, feature tracking, topology, structure manipulation, 3d imaging, and much more.

Each core library is lightweight, and can be used without reference to the other core libraries. Similarly, the non-core libraries don’t depend on more than absolutely necessary, so you can compile and link just the libraries you really need.

For a more detailed description of the libraries see the VXL book.

VXL is developed and used by an international team from academia and industry, including some of the world’s leading computer vision experts.