Ilya Ovodov
Research CV Lead at SberDevices
Moscow Metropolitan Area Russia
Summary
👤
Senior🎓
Top SchoolIlya Ovodov is a research-driven computer vision lead with over a decade of experience translating academic ideas into production C++ systems for video analytics and sign language recognition. Currently heading research CV at SberDevices, he combines deep research credentials—including conference publications and patents—with hands-on engineering demonstrated by contributions to the widely used Darknet/YOL0 ecosystem. He founded and directs the Angelina Braille Reader project, an award-winning, multi-language service used by thousands that showcases his commitment to accessible AI and productizing novel algorithms. His background in ERP and automation gives him uncommon expertise in systems integration and operationalizing vision models in constrained environments. Colleagues know him for improving robustness on low-performance processors and for pragmatic innovations that reduce false alarms and make detection work reliably in the field.
8 years of coding experience
27 years of employment as a software developer
MSc, Applied mathematic and physics, MSc, Applied mathematic and physics at Moscow Institute of Physics and Technology (State University) (MIPT)
Russian, English
Stackoverflow
373reputation
10kreached
17answers
4questions
Github Skills (14)
neural-network10
c1710
object-detection10
computer-vision10
deep-learning10
c1110
image-processing10
data-augmentation9
yolov48
caffe6
pycaffe6
linked-list6
unique-ptr6
stackoverflow6
Programming languages (6)
Github contributions (5)
AlexeyAB/darknet
Apr 2018 - Jun 2018
YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )
Role in this project:
Backend Developer
Backend DeveloperContributions:8 commits, 7 PRs, 13 comments in 1 month
Contributions summary:Ilya primarily focused on modifying core functionalities related to data loading, image processing, and object detection within the Darknet framework. Their commits involved refactoring the data loading pipeline by adding a "flip" parameter to control data augmentation, enhancing the image drawing functions, and improving the output of detection results. Furthermore, the user addressed a bug related to drawing bounding boxes for images with small resolutions. These changes indicate a focus on improving the functionality and output of the object detection system.
dnncomputer-visionobject-detectiondeep-learning-tutorialdarknet
IlyaOvodov/darknet
Apr 2018 - May 2019
Windows and Linux version of Darknet Yolo v2 & v3 Neural Networks for object detection
Contributions:1 PR, 69 pushes, 30 branches in 1 year 1 month
windowsdeep-learningdarknet-yololinuxobject-detection
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.