TopCoder Marathon Match / Data Science
2nd Place The US National Geospatial-Intelligence Agency (NGA) was seeking novel approaches for satellite imagery segmentation in order to detect, delineate, and describe circular shaped features. My final solution reached 92% on their secret dataset. NGA's announcement (PyTorch, OpenCV, GDAL)
TopCoder Marathon Match / Data Science
3nd Place The goal of this challenge was automatic detection and segmentation of faults (curved surfaces) in 3D seismic data. (C++, PCL, eigen, Docker)
TopCoder Development
1st Place The goal of this challenge was to fix the client's codebase and optimize its performance to be able to process very large datasets (several gigabytes of scan data).
TopCoder Development
2nd Place The goal of this challenge was to develop a new functionality of conversion of 3D meshes into polylines sticks and integrate it in the client C++ codebase. (C++, eigen, libigl, PCL)
TopCoder Development
2nd Place The goal of this challenge was to implement calculation of various auxiliary data on the detected geological faults and integrate it in the client C++ codebase. (C++, eigen, libigl, PCL)