Philipp Waeltermann

Engineer and Developer

Category: Showcase

This category shows all posts that show work or projects I have done.

Image Style Transfer

As part of my DeepLearning Course at Georgia Tech, I use a Neural Network and two different loss functions to transfer the style from one image to another based on ”Image Style Transfer Using Convolutional Neural Networks” by Gatys et al. in 2015. The idea is to have two image, one that determines the content,
Read More

Video Slicing

This project is just for fun. Over the holidays, I felt like being creative. After a few minutes of trying to draw I remember how terrible I was at it. So I decided to switch my tools to a camera and a computer. I had the idea to taking a video, load it as a
Read More

Udacity Nanodegree

I successfully completed the Self-Driving Car Engineer Nanodegree from Udacity by submitting 9 Python-based projects: Project 1: Lane Finding Project 2: Advanced Lane Line Detection (ComputerVision) Project 3: Traffic Sign Classification (Training a ConvNet) Project 4: Behavioral Cloning (End-to-end Driving with Neural Net) Project 5: Sensor Fusion (Extended Kalman Filter) Project 6: Sparse Localization (Particle
Read More

Edison Award Winner!

For our capstone project we built a machine that can test diamond codings through automated and repeated impact. The tension loaded impact hammer is lifted through a Cam Follwer mechanism.The Cam is connected to a gear chain system which is powered by an electric motor.The whole machine is automated. One can set the number of
Read More

AutoDrive Challenge

I joined MSU’s AutoDrive Team in the fall of 2017, and have since then designed and implemented steering and torque controllers for our vehicle. In addition to that I helped develop pathplanning algorithms, and learned to work with ROS, use Gitlab, and program in the Linux environment. I was really excited to be one of
Read More

Machine Learning in Space

This project was done in cooperation with Professor Firas Khasawneh .The ultimate goal for this project is to use machine learning classifiers on objects detected in space based on their light reflection. The big challenge to train such a classifier is to gather enough training data. As it is unfeasable for me to gather real-world reflection data
Read More

Internship at dSPACE

During my internship at dSPACE I developed a Lane Centering and lane change decision making algorithm using dSPACE’s SIL tools. The controllers were developed in Simulink and tested with dSPACE MotionDesk, dSPACE VEOS, dSPACE ModelDesk, and dSPACE ControlDesk. The lane centering controller was based on an the Stanley Controller used by Stanford during the DARPA
Read More