Name: Sanghoon Yoo
Type: User
Company: Hyundai Kia America Technical Center
Bio: I am a self driving car engineer who loves working on self driving car development. My latest projects are related to deep learning method using Python and C++.
Location: Ann Arbor Michigan
Blog: https://www.linkedin.com/in/sanghoonyoo/
Sanghoon Yoo's Projects
The goal of this project is to create software pipeline to identify lane boundaries from a video using OpenCV.
Leveraged deep neural networks and convolutional neural networks to clone driving behavior using Keras. Trained, validated and tested a model to output a steering angle to an autonomous vehicle. Data collection was done within a simulator environment. Used image data and steering angles to train a neural network and then used this model to drive the car autonomously around the track in a simulator.
Course Files for Complete Python 3 Bootcamp Course on Udemy
Simulates four elevators available to take passengers up and down a 100 floor building
Applied a extended Kalman filter in C++ with provided simulated lidar and rader measurements detecting bicycle that travels around the vehicle. Kalman filter tracks the bicycle's position and velocity from estimating the state of a moving object of interest with noisy lidar and radar measurements.
Train and Deploy Simple Machine Learning Model With Web Interface - Docker, PyTorch & Flask
DeepLab v3+ model in PyTorch. Support different backbones.
Semantic segmentation models, datasets and losses implemented in PyTorch.
Utilized deep neural networks and convolutional neural networks to classify traffic signs using TensorFlow. Trained and validated a model so it can classify traffic sign images using the German Traffic Sign Dataset. After the model is trained, tried out my model on images of German traffic signs that I found on the web, which was new test set.