Master's thesis

Thesis by: Thomas Schmid
Advisor: Nassir Navab
Supervision by: Iro Laina, Federico Tombari
Due date: 15.12.2018

Abstract

The performance of AI-driven systems highly depends on training data which is (usually) manually generated and requires money and time whilst being human error-prone. This thesis will address the problem of automatic 3D object detection of pedestrians and cars in an autonomous driving setting. We will exploit deep 2D mask proposals from RGB data (e.g. Fast/Faster R-CNN). In combination with LiDAR^? data and classical depth completion and clustering, our goal is to bridge the gap to 3D allowing the generation of 3D bounding boxes in a weakly supervised setup.