- Wind Turbine Damage Detection ML- algorithm- Aerial 3D Point Cloud (Lidar) ML-algorithm- Renesas Electronics e-AI contest technical lead- IBM Watson Build 2018 software development lead

- Lead developer of the motion planning module for the robotic platform- Led several IRA (Integrated Research Assessments)- Collaborated with other teams - Vision (3D lidar), Control systems- Incharge of testing and benchmarking the performance of the motion planning module- Analysis of Kinodynamic path planning algorithms- Webite: http://eng.fsu.edu/ciscor/

Thesis: "Background Modeling Using Pan-Tilt Camera"Abstract: The use of autonomous pan-tilt cameras as opposed to static cameras can dramatically enhance the range and effectiveness of surveillance systems, but effective tracking in such pan-tilt scenarios remains a challenge.Existing approaches for constructing background models fails here since they are designed for static cameras. In this paper we estimate camera motion parameters, and use it to update the background model online in the presence of scene activity.Camera motion is estimated as the median learned over Flow matrix between consecutive frames.Foreground regions are detected as changes using single Gaussian model, and thus are skipped during background model construction.

Worked in the field of Information Hiding, Computer Security, and Network Optimization.

Worked on the project which involves collection of data from remote machines kept in harsh environment like ~1700c and control them using Siemens microcontroller (S7-1200). The microcontroller was programmed in STEP-7, and WinCC software.