Git Product home page Git Product logo

Hi there πŸ‘‹

My name is Kirill Kolodiaznyi and I'm a software developer.

πŸ”¬ Research & Intersest

The research I’m working on now is the implementation of a robotic platform based on the NVIDIA Jetson Nano 2Gb device with monocular SLAM navigation. The main aim of this work is to improve feature matching algorithms used for camera positioning in a SLAM pipeline. The recent experiments are about using deep learning for SLAM, especially using the Local Feature Matching with Transformers for camera positioning.

Another topic of my interest is multi-threaded algorithms and using them for performance improvements in projects I’m working on. The result of this work is the library that represents higher-level, task-based parallelism. It’s based on the idea of the Intel TBB work-stealing threads management approach.

Also, I’m interested in learning and applying the C++ language for solving Machine Learning tasks. I wrote several articles and a book about the application of C++ to ML. Additionally, I made C++ implementations of popular object detection methods like Faster R-CNN and Mask R-CNN.

✍ Publications

πŸ”§ Technologies & Tools

Kirill's Projects

calib icon calib

camera calibration tool with gui

coarse_loftr_trt icon coarse_loftr_trt

Distilled coarse part of LoFTR adapted for compatibility with TensorRT and embedded divices

code2seq icon code2seq

Code for the model presented in the paper: "code2seq: Generating Sequences from Structured Representations of Code"

cppminer icon cppminer

cppminer produces a code2seq compatible datasets from C++ code bases.

cpptask icon cpptask

Lightweight approach to expressing task stealing and balanced parallelism in a C++ programs.

dicomtostl icon dicomtostl

Convert tomografy scan dicom files to 3D stl format

loftr icon loftr

Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021

loftr_trt icon loftr_trt

TensorRT adaptation of LoFTR: Detector-Free Local Feature Matching with Transformers

mlcpp icon mlcpp

Set of examples of ML approaches implemented in C++

mono_slam_framework icon mono_slam_framework

General purpose monocular SLAM framework based on ORB-SLAM pipeline, created to compare different feature matchers.

stereocam icon stereocam

Tool for stereo camera calibration, tuning and 3d points extraction

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    πŸ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. πŸ“ŠπŸ“ˆπŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❀️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.