Computer Vision Lab

Nikolay Falaleev



A Robotics, Computer Vision and Machine Learning lab by Nikolay Falaleev. The main focus of the blog is application of Deep Learning for Computer Vision tasks, as well as other relevant topics: classical Computer Vision, Numerical Methods and Hardware.

Selected Projects

Cityscapes Semantic Segmentation

Deep Learning Computer Vision

Vehicle and Lane Lines Detection

Self-Driving Computer Vision

Image-Based Localization Challenge

Self-Driving Deep Learning

Selected Competitions

SoccerNet Camera Calibration Challenge 2023

Deep Learning Computer Vision CVPR

Kaggle: TGS Salt Identification Challenge

Deep Learning Computer Vision Kaggle

Lyft Perception Challenge

Deep Learning Computer Vision Self-Driving


Title img
20 Jun 2023

Top-1 solution of SoccerNet Camera Calibration Challenge 2023

An approach to generate camera calibration values from football broadcast videos.

10 mins read
Title img
30 Nov 2022

Four generations of Nvidia GPUs compared

Benchmark results of GTX 1080 TI, RTX 2080Ti, 3090 and 4090 on DL tasks.

5 mins read
Title img
29 Jun 2020

Multi-task learning loss balancing

Balancing temporal and spatial losses for simultenious training of multi-task neural networks for video processing and some data tips.

7 mins read
Title img
06 Nov 2018

Benchmarking RTX 2080 Ti vs Pascal GPUs vs Tesla V100 with DL tasks

Comparation of Nvidia RTX 2080 Ti with GTX 1080 Ti and 1070.

3 mins read
Title img
24 Oct 2018

Semantic Segmentation of Seismic Reflection Images

A gold medal solution of the TGS Salt Identification Challenge.

12 mins read
Title img
23 Oct 2018

About Kaggle TGS Salt Identification Challenge

Kaggle Challenge to segment salt deposits beneath the Earth's surface on seismic images.

1 min read
Title img
05 Jun 2018

Discussion of the Lyft Perception Challenge

How to increase inference speed on a semantic segmentation task and further ideas.

4 mins read
Title img
05 Jun 2018

Multiclass semantic segmentation with LinkNet34

A CNN approach used for multiclass semantic segmentation during the Lyft Perception Challenge.

6 mins read
Title img
31 May 2018

About Lyft Perception Challenge

A partnered Lyft and Udacity semantic segmentation challenge with synthetic images.

2 mins read
Title img
21 Feb 2018

An approach to predicted class balancing

An approach how to increase your position on a leaderpoard in a classification datascience competition by balancing predictions.

7 mins read
Title img
20 Feb 2018

Camera model identification with deep learning

Ideas and approach to the Kaggle IEEE's Signal Processing Society - Camera Model Identification challenge.

5 mins read
Title img
20 Oct 2017

How to run TensorFlow with CUDA 9 and cuDNN 7 in openSUSE on Ryzen

A set of instruction to run a modern version of the deep learning framework TensorFlow on AMD Ryzen.

5 mins read
Title img
21 Sep 2017

Neural network for multiclass image segmentation

VGG16-based fully convolutional networks for semantic segmentation of images on Cityscapes

3 mins read
Title img
01 Aug 2017

Image classification using SVM

Application of a linear SVM for image classification with HOG, binned color and color histogram features.

8 mins read
Title img
07 Jun 2017

Adaptive Virtual Sensors for Lane detection

Computer vision approach for road marking detection with adaptive thresholds and positions of virtual sensors.

6 mins read
Title img
07 May 2017

Bird's Eye View Transformation

Convert a normal image to a Bird's Eye view projection with OpenCV.

3 mins read
Title img
05 May 2017

Camera calibration with OpenCV

A simple way to calibrate an optical system with a chessboard pattern by means of the OpenCV to reduce distortion.

3 mins read
Title img
02 May 2017

Approximate equidistant curve for polynomials

An approximate approach to find an equidistant curve for a given polynomial.

13 mins read