Software engineer with experience in embedded systems, computer vision and machine…

• Long lasting pedestrian counting system

  Sep 2022

  Developing low power pedestrian counting in AI4CE lab for NYC Office of Technology&Innovation. Deployed on Coral Dev Micro. Using TensorFlow Lite (Deep Learning) model for pedestrian detection. Using Gaussian Process Regression (Machine Learning) model to predict pedestrian count during off duty cycle. Developing AWS back end and dashboard.

  See project

• 3D Face Reconstruction from singe RGB image

  Jan 2022 - May 2022

  Based on pervious published work, This project repeats the 3DMM paper experiment. We trained a neural network to get the αid, αexp ,αalb ,γk ,T , R parameters from the input image. Before getting all the coefficients from that Deep Neural Network, we extracted the landmarks from input dataset by a face alignment detector for later loss calculation. After obtained the coefficients, we used BFM to get all the matrices needed for 3D face rendering. Soft-Rasterizer used these matrices to compute…

  Based on pervious published work, This project repeats the 3DMM paper experiment. We trained a neural network to get the αid, αexp ,αalb ,γk ,T , R parameters from the input image. Before getting all the coefficients from that Deep Neural Network, we extracted the landmarks from input dataset by a face alignment detector for later loss calculation. After obtained the coefficients, we used BFM to get all the matrices needed for 3D face rendering. Soft-Rasterizer used these matrices to compute the mesh and render the mesh as a 2d image. We optimized the model by reducing the loss based on the output image and mesh.

  See project

• Dynamics modeling of a variable-stiffness soft robotics manipulator

  Jan 2021 - May 2021

  I worked on the structural modeling of a variable-stiffness soft robotics manipulator for my final year project with applications in surgical and marine robotics. The manipulator is tendon driven and uses bead jamming to vary its stiffness. Over the course of the project I also made a graphical user interface that allowed the user to test the model with different parameters like bead size, number of beads and friction coefficient. I used Matlab and Simulink.

  See project

• Retrofitted Parrot Mk5 to autonomously pick and place ball in course

  Sep 2020 - Dec 2020

  I was the systems engineer in a group of 8 engineers that retrofitted a Parrot Mambo UAV to autonomously move objects between points connected by curved and straight lines. I received an A in this course. This is a link to the projects final report drive.google.com/file/d/1Dnwfo3a35QA1M-PFyuEozz6kSl70oQhH/view?usp=sharing (Matlab, Simulink, Python)

  See project

• Traffic Light System

  Sep 2019 - Dec 2020

  I used C and Verilog to program an Artix-7 FPGA to make a traffic light system at an intersection with pedestrian crossing buttons and car detection. (C/C++, Verilog)

  See project

• Sustainable Energy Group Design Project

  Jan 2020 - May 2020

  I was part of a team of 4 engineers who were tasked with designing and building a 12-watt wind turbine. I was in charge of designing the generator and the embedded system that would control the speed of the turbine.

  See project

• Academic Scholarship

  NYU

  May 2021

  New York University Academic Scholarship

• 3rd place Edinburgh Innovations Data-Driven Innovation Cup

  Edinburugh Innovations

  Mar 2021

  3rd place Edinburgh Innovations Data-Driven Innovation Cup