Capstone Project: Automated Draft Reader

This capstone project involved the development of a prototype Automated Draft Reader, an Internet of Things (IoT) system designed to automatically measure a ship’s draft by reading the draft marks on the vessel’s hull. The system uses a camera mounted on a rail mechanism to capture short video recordings of the draft marks, which are processed locally using a computer vision and machine learning pipeline to detect the waterline and identify the numerical draft markings. A Jetson Nano processes the data on-board, while sensors such as an ultrasonic sensor assist with positioning and alignment of the camera. The extracted draft measurements are then transmitted via a GSM module to a cloud-based server for storage and visualization, enabling remote monitoring and trend analysis. The project aimed to reduce the need for manual draft readings, improving safety, accuracy, and data accessibility for vessels undergoing maintenance or operating in port environments.