Claudio S. De Mutiis

Advanced Lane Finding

---

Built an advanced lane-finding algorithm using distortion correction, image rectification, color transforms, and gradient thresholding. Identified lane curvature and vehicle displacement. Overcame environmental challenges such as shadows and pavement changes.

• Skills: Python and OpenCV
• Source Code: GitHub

Close

Vehicle Detection and Tracking

---

Created a vehicle detection and tracking pipeline with OpenCV, histogram of oriented gradients (HOG), and support vector machines (SVM). Optimized and evaluated the model on video data from a automotive camera taken during highway driving.

• Skills: Python, OpenCV, Scikit-learn, Machine Learning, Histogram of Oriented Gradients and Support Vector Machines
• Source Code: GitHub

Close

Use Deep Learning to Clone Driving Behavior

---

Built and trained a convolutional neural network for end-to-end driving in a simulator, using TensorFlow and Keras. Used optimization techniques such as regularization and dropout to generalize the network for driving on multiple tracks.

• Skills: Python, Deep Learning, Keras, Convolutional Neural Networks and Scikit-learn
• Source Code: GitHub

Close

Traffic Sign Classification

---

Built and trained a deep neural network to classify traffic signs, using TensorFlow. Experimented with different network architectures. Performed image pre-processing and validation to guard against overfitting.

• Skills: Python, TensorFlow and Computer Vision
• Source Code: GitHub

Close

Local Odometry Techniques for a Differential Wheeled Robot

---

• Provided the MIRTO robot, designed and built by a team led by Dr. Franco Raimondi (F.Raimondi@mdx.ac.uk) at Middlesex University London, with autonomous navigation planning capabilities.
• Wrote a library of high-level odometrical functionalities (i.e. Java methods) to allow MIRTO to perform actions such as rotating, translating and moving towards a specific point in space while avoiding all obstacles on the way.
• Developed a navigation algorithm that only makes use of MIRTO's wheels' encoders and bumpers sensors.
• Used MIRTO to test the newly developed navigation algorithm.
• Discussed the results and observations in my MSc project's dissertation.

• Skills: Java, Mobile Robotics, Navigation
• Source Code: GitHub

Close

Predicting Boston Housing Prices

---

Built a model to predict the value of a given house in the Boston real estate market using various statistical analysis tools. Identified the best price that a client can sell their house utilizing machine learning.

• Skills: Python, Scikit-learn, Statistical Analysis, Metric Performance, Cross Validation, Bias/Underfitting & Variance/Overfitting and Learning Curves
• Source Code: GitHub

Close