itlab_2022

low-level optimization of computer vision algorithms on ARM architectures

Objectives of this project:

• Study of classical computer vision algorithms, as well as work with artificial neural networks;
• Optimization of these algorithms on ARM architectures. The study of parallel programming. Using Vector instructions;
• Working with Raspberry PI devices in practice.

Software modules:

Data generating

A module for generating data/reading images and storing images. The Image class is independent when reading format images .bmp (OpenCV library is used for other formats).

Algorithms

The algorithms module. At the moment, it contains the following matrix multiplication algorithms: classical multiplication,multiplication using OpenMP and Neon_intrinsics

Tests

The test module. In development...

Benchmarks

The Benchmarks module. In development...

Clone the repo

git clone https://github.com/embedded-dev-research/itlab_2022.git