The goal of this project was simple: to find boats and any floating means of transport for humans, categorize and draw a bonding box around it. However there were some limitations with the strategy we were allowed to follow: the use of deep learning was permitted but it should not be an end-to-end learning approach. Also the use of C++ was a must, although Python was allowed for the machine learning/deep learning part.
A detailed report is present in the cv_boat_detection_report.pdf file