In the past few posts (see 1 and 2) we briefly described some details on how we estimated a ship’s position, using a single video. This post will further detail our simplistic approach to object detection and tracking for this application. If you haven’t read the previous posts, I strongly...
[Read More]
Transforming coordinates from Blender to OpenCV
In our previous post about computer vision, we showed our pipeline to solve a specific problem, and it involved some steps inside Blender and others on OpenCV. Also, I mentioned that it was not something straightforward to go from one to the other. Here we will describe how we transposed...
[Read More]
Ship Position Estimation from Video using OpenCV
Recently we jump into a challenge to explore a specific application of computer vision:
how can we estimate a top-view position of a ship from a given video from a fixed perspective camera?
After some work we found our way, reaching what seems to be a quite reasonable result.
[Read More]
Using F1C100s SoCs with Linux with comparable cost as microcontrollers
What if you could use Linux in all your embedded projects? A good news is that cost is the most important factor to consider a microcontroller, then you should consider using a F1C100s SoC instead, with a price of less than $2 it is really competitive even in the microcontroller...
[Read More]
Case study: How Inlining and constant propagation helps software design
Performance is a big part of software design, and does have impact on
software architecture and API design. However, we will see how we can
leverage everyday optimizations such as inlining to accomplish
performance similar or better to hand-written software in extensible
and maintainable designs.
[Read More]