So far we have seen how to install OpenCV and capture images from a video stream. Today we'll see how we can detect circles (or balls) in an image. Last year, the biggest challenge of PiWars was to be able to detect coloured balls kept on four corners of an arena and drive a robot towards it. Now I don't know if they will have the same challenge this year, however we can use this as a starting point to use a few more OpenCV tricks. Today we'll learn about how to use Hough transforms in OpenCV and how we can use it to detect balls in an image.

read more

In the introductory post we saw how to setup OpenCV on a Raspbian (Desktop) and run a small sample application to convert an image into greyscale. Today we'll see how easy it is to capture frames from a camera and write some text on to each frame and save them.

read more

I always wanted to learn OpenCV, because it was a massive step up from my Computer Graphics theory class back in the University days. Also I dream that all my the pictures I have ever taken will one day be collated, indexed and searchable with context like place, scene, people in the image so on and so forth. So learning OpenCV is the natural first step towards that (no, I will not use a my images as training material for some corporate AI engine, I wear a tin-foil-hat, sue me!). Of course everything had to run off (one or more) RaspberryPi!

read more

Finally managed to collate all the images from friends and family who had come along to PiWars 2018. Here's a glimpse of Team Pi-O-Steer's action packed day at PiWars 2018.

read more

This maybe a controversial topic and I fully expect to get panned for it, however, I thought I should write down what I spent on my PiWars bot (First time and in the Beginners category) for two reasons:

read more

In the last post I wrote what went right and wrong with the build. However, build is only a small part of the event preparation. Attending PiWars is a full scale project. To be successful you need to manage your team's time well and split the work up correctly for things to line up correctly for success. Work needs to be split up into Software, Hardware, Design, Fabrication and Integration.

read more