Computer Vision Lab

Nikolay Falaleev

Profile

Nikolay S. Falaleev

London, United Kingdom, nikolasent@gmail.com

Head of AI, Kaggle master

IT Skills and experience

Languages:   Python, C/C++, R, SQL
Tools:   PyTorch, TensorFlow, TFLite, ONNX, OpenCV, FFmpeg, Scikit-learn, NumPy, Docker, TensorRT, OpenVINO, MLflow, DeepStream, Gstreamer, FastAPI
Hardware:   Industrial cameras, Optics, LIDARs, IMU, DL Accelerators
Skills:   Artificial Neural Networks, Deep Learning, Computer Vision, Semantic Segmentation, Object Detection and Tracking, Depth Estimation, Video Event Detection, Sensor Fusion, Calibration, 3D Scene Reconstruction Localization and Pathplanning, Control, Numerical Methods, Optimization, MLOps, Research, Team Leader
Spare-time Projects:   Kaggle competitions, Real-time CPU person segmentation for privacy in video calls, Image Semantic Segmentation, Image Classification, Driver Behavioral Cloning with CNN, Lane Lines Detection with CV, Vehicles Detection and Tracking with CV, PID Controller, Model Predictive Control, Unscented Kalman Filter, Particle Filter.

Employment

10/2020 - present, Head of AI Sportlight Technology

Development of CV-based Analytics for elite football clubs.

Responsibilities:

  • Architect a Deep Learning system for match data capturing. Spearheaded the development of a real-time Deep Learning system to extract insights from visual and LIDAR data via object detection, tracking, segmentation, person re-identification, pose estimation, event detection, and multi-modal data fusion.
  • Led AI projects in cross-functional teams, e.g.: a project on transition to real-time data processing. Ensured adherence to best development practices and deep learning experimentation strategies to foster technological excellence.

Achievements:

  • Architected and executed an operational system deployed across the majority of the English Premier League stadiums, achieving industry-leading player tracking accuracy.
  • The results allowed 5x time cost reduction of the data processing and an order of magnitude upscale in operations.

08/2017 - 08/2020, Leading Computer Vision R&D Constanta/OSAI

R&D of applied CV systems for real-time Sports Analytics.

  • Proposed and executed the development of a DL-based system for real-time video analysis of sports events for MR broadcasting, sports analytics, and betting, including hardware design, computer vision R\&D, data management, and scalable deployment.
  • Led the implementation of production-ready inference pipelines and managed project life cycles from initial concept to commercial operation.
  • Pioneered a real-time spatio-temporal video processing ANN architecture, published in a CVPR 2020 paper. The system was showcased in high-profile events such as Tokyo 2020 Olympics, JOOLA North American Teams Championships and National Table Tennis Championship 2020, and has been deployed in numerous venues worldwide for 24/7 commercial operation.
  • Created a Computer Vision module for pool-9 real-time analysis from organizing data collection to product deployment. Video demo, Blog article [rus].

10/2014 - 07/2017 Junior Researcher Academic Research Institute

Constructing stable finite-difference schemes for transient heat conduction in 3D case.

Achievements:

  • 6 scientific papers and 3 conference reports were coauthored.

Education

09/2015 - 07/2017     Master of Science with Honours in Materials Science, Department of Materials Science
      Lomonosov Moscow State University (MSU)
09/2011 - 07/2015     Bachelor of Science in Materials Science, Department of Materials Science
      Lomonosov Moscow State University (MSU)

Continuing education

07/2021 - 08/2021     Oxford Machine Learning Summer School 2021
      Certificate
03/2021 - 08/2021     Intel Edge AI for IoT Developers Nanodegree
      Udacity, Certificate
01/2020 - 06/2020     C++ Nanodegree
      Udacity, Certificate
11/2016 - 10/2017     Self-Driving Car Engineer Nanodegree
      Udacity, Certificate, graduated with the first ever cohort
11/2012 - present     MOOCs >30 courses in computer and data sciences, robotics, computer vision and machine learning
      Coursera, Udacity, edX and etc.

Prizes and Awards

2023     SoccerNet Camera Calibration Challenge 2023, CVPR
      Top-1. DL approach to camera calibration from football broadcast videos. The challenges was held at CVPR 2023.
2018     Quick, Draw! Doodle Recognition Challenge, Kaggle
      Top-4% (50/1316). Application of deep neural networks to classification of users drawings into 300+ classes with 50M train samples
2018     TGS Salt Identification Challenge, Kaggle
      Top-0.5% (14/3234). The deep-learning based approach helps to segment seismic images which is crucial for oil and gas company drillers.
2018     Lyft Perception Challenge, Udacity
      Top-3% (4/155) and the fastest neural network pipeline. The solution is based on LinkNet34 for real-time multiclass semantic segmentation.
2018     IEEE’s Signal Processing Society - Camera Model Identification, Kaggle
      Top-3% (15/583). The solution is based on convolutional neural networks as classifiers for camera models captured a given image.
2016     Image-Based Localization Challenge, Udacity
      The 3d place. A deep learning approach based on GoogLeNet inception module was applied for “localization as classification” method for localization of an autonomous vehicle.
2015     ХХVII International Innovation Conference of Young Scientists and Students, Moscow, Russia
      Diploma for the best scientific report “Mathematical modeling and numerical calculations of particles and coatings heating during gas-dynamic spraying”.
2013     Mendeleev Prize for Young Chemists, Kazan, Russia
      The Second Prize for a report: “Properties of single wall carbon nanotubes encapsulated by inorganic compounds”

Patents

  • RU106765 “Device for producing 3D images by a single camera”. A special method for depth map calculation based on an image, produced by the device, was also developed and the gear is able to work as a range finder.

Publications

Deep Learning:

  1. Cioppa A., Giancola S., …, Falaleev N., et al. SoccerNet 2023 challenges results, // Sports Engineering, V. 27, 2024, DOI: 10.1007/s12283-024-00466-4
  2. Voeikov R., Falaleev N., Baikulov R. TTNet: Real-time temporal and spatial video analysis of table tennis. // The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2020, pp. 884-885, DOI: 10.1109/CVPRW50498.2020.00450

Nanotechnology:

  1. Eliseev Andrei A., Kumskov A.S., Falaleev N.S., Zhigalina V.S., Eliseev Artem A., Mitrofanov A.A., Petukhov D.I., Vasiliev A.L., Kisilev N.A. Mass Transport Through Defects in Graphene Layers // Journal of Physical Chemistry C, 2017, DOI: 10.1021/acs.jpcc.7b06100

  2. N. S. Falaleev, A.S. Kumskov, V.G. Zhigalina, I.I. Verbitskiy, A.L. Vasiliev, A. A. Makarova, D. V. Vyalikh, N.A. Kiselev, A.A. Eliseev. Capsulate structure effect on SWNTs doping in RbxAg1−xI@SWNT composites // CrystEngComm, 2017, DOI: 10.1039/c7ce00155j

  3. Andrei A. Eliseev, Nikolay S. Falaleev, Nikolay I. Verbitskiy, Andrei A. Volykhov, Lada V. Yashina, Andrei S. Kumskov, Victoria G. Zhigalina, Alexander L. Vasiliev, Alexey V. Lukashin, Jeremy Sloan, Nikolay A. Kiselev. Size-dependent structure relations between nanotube and encapsulated nanocrystal. // ACS Nano Letters, V. 17 I. 2, 2017, P. 805–810 DOI: 10.1021/acs.nanolett.6b04031

  4. N.A. Kiselev, A.S. Kumskov, V.G. Zhigalina, A.L. Vasiliev, J. Sloan, N.S. Falaleev, N.I. Verbitskiy, A.A. Eliseev. The structure and continuous stoichiometry change of 1DTbBrx@SWCNTs // Journal of Microscopy. V. 262, I. 1, April 2016, P. 92–101 DOI: 10.1111/jmi.12348

  5. Lukashin A.V., Falaleev N.S., Verbitskiy N.I., Volykhov A.A., Verbitskiy I.I., Yashna L.V., Kumskov A.S., Kiselev N.A., Eliseev A.A. Quasi free-standing one-dimensional nanocrystals of PbTe grown in 1.4 nm SWNTs. // Nanosystems: physics, chemistry, mathematics. V. 6, I. 6, 2015, P. 850-856 DOI: 10.17586/2220-8054-2015-6-6-850-856

Google Scholar profile

ResearchGate profile

Public Talks

11/2023     Computer Vision Summit London 2023
      Deploying unparalleled accuracy in athletes’ performance analysis with LIDAR and video data processing. Keynote presentation, 250+ attendees.
06/2023     CVPR, 9th International Workshop on Computer Vision in Sports
      Presentation on a DL approach to camera calibration.
07/2022     GSIG Solutions Showcase: Athlete tracking: AI, computer vision, machine learning
      LIDAR and visual data fusion for athlete tracking.

Clubs & Societies

Founded a non-commercial organization OniroAI (Github) for independent research and development in Computer Vision and Artificial Intelligence.

Interests

Self-Driving Cars, Deep Learning, Computer Vision, Robotics, Artificial Intelligence, Mathematical Modeling, UAVs