Since long I’ve been thinking of creating an API which fellow developers could use over cloud. But I didn’t want it to be the traditional Hello World API or simple SQL Flask API — supporting the classical user name and email ID GET, PUT, POST, DELETE REST requests. Since AI and ML are so pervasive now, I thought of giving ML a try — and it is easy : )
Since everything’s on the cloud and the free versions I needed an AI/ML project with small, lightweight dependencies for the cloud. I forked a project named Img2vec that uses PyTorch to generate feature vectors for a dataset of images and then does a simple match(cosine similarity in sklearn) of a test image with others using pretrained models. …
While the current MR development revolves around hardware such as phones with depth sensors, Microsoft HoloLens, or HTC Vive, novices shouldn’t be undermined from the learning experience. Thanks to open source alternatives such as OpenCV and ArUco library, novices can develop AR apps using webcams for image input.
The official docs state,
ArUco: a minimal library for Augmented Reality applications based on OpenCV
Unlike recent libraries such as Unity, ARToolkit and SDK’s such as Google’s ARCore, ArUco offers easy setup and deployment. With just a few lines of code, one can develop an app for AR Marker detection and simple object rendering. …
The ArUco library for OpenCV is a lightweight C++ wrapper for Augmented Reality applications. Its simple, efficient and versatile enough to detect hundreds of unique AR markers.
The latest release package can be found on sourceforge. Now you need to extract and compile the source code using cmake(the instructions mentioned below work on linux; for windows you can use use cmake-GUI).
Note that the official documentation recommends installing it in a working directory, rather than with sudo or admin privileges. Supposing you downloaded it in Downloads, open terminal — note that ‘xxx’ is downloaded zip library…