Name: Ian
Type: User
Company: National Defence
Bio: Mechanical Engineer with 17 years + automotive experience. Found a new love with computer vision, deep-learning for self-driving vehicles.
Twitter: silverwhere
Location: Ottawa, Ontario
Ian's Projects
Advanced computer vision techniques to identify lanes, the position of the vehicle within the lane, the radius of curvature of the lane.
I utilized end-to-end deep learning using convolutional neural networks (CNNs) to map the raw pixels from (3) front-facing cameras to the steering commands for a self-driving car.
Utilized an Extended Kalman Filter and Sensor Fusion to estimate the state of a moving object of interest with noisy lidar and radar measurements. The project involved utilzing lidar data (Point Cloud) for position and radar data (Doppler) for radial velocity.
Create a path planner that is able to navigate a car safely around a virtual highway
Class projects for the Udacity Intro to Self Driving Vehicles nanodegree - In this program, I applied Python skills, and C++, apply matrices and calculus in code, computer vision and machine learning. These concepts will be applied to solving self-driving car problems.
Utilizing data from initial GPS estimates and LIDAR data, I can use a particle filter based on the vehicle's reported observations of objects nearby to localize it and find it!
Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
Self Driving Car Nanodegree Offered By Udacity
Sensor Fusion for 3D Object Detection for Driverless Cars
Config files for my GitHub profile.
Self Driving Car Engineer Capstone Project
A detailed tutorial on how to build a traffic light classifier with TensorFlow for the capstone project of Udacity's Self-Driving Car Engineer Nanodegree Program.
I utilized deep neural networks and convolutional neural networks to classify traffic signs. I trained and validated a model so it can classify traffic sign images using the German Traffic Sign Dataset.