Hybrid Indirect-Direct Visual SLAM for Embedded Platforms
A hybrid indirect-direct monocular visual SLAM system designed for embedded and resource-constrained platforms. The work focuses on efficient direct photometric tracking using OpenGL ES compute shaders to make real-time SLAM feasible on commodity GPU-equipped devices.
Bayesian Multi-Object Tracking for ADAS
I developed a Bayesian multi-object tracking module from scratch for an ADAS perception pipeline and led its integration and testing with LiDAR and radar under real operational constraints. This work focused on building a robust tracking system that could operate reliably in a real perception stack rather than as a standalone prototype.
Early VR SLAM Prototyping
An early prototyping stage of the work that later became Mesh2SLAM in VR, a fast geometry-based SLAM framework for rapid prototyping in virtual reality applications. This project focused on building and testing the core tracking and mapping pipeline in C++ and OpenGL from the ground up.
Simulation and Training Systems
Development of VR-based simulation and training software for defense applications using real-time 3D engines. While project details are limited by NDA constraints, the work involved applied engineering for interactive and immersive training systems.
Invention: Pinch/Grab (2011–2013)
While at Softkinetic Systems, I co-invented and helped develop the pinch/grab interaction concept for depth and RGB-D camera systems. This work was later patented and became a widely adopted interaction paradigm in VR, AR, and smart glasses.