Notice and Invitation
Oral Defense of Doctoral Dissertation
The Volgenau School of Engineering, George Mason University
Diploma of Engineering, Technical University of Crete, Greece, 2012
Master of Science, George Mason University, 2015
3D Model-Assisted Learning for Object Detection and Pose Estimation
Monday, February 10, 2020, 12:00 PM
Engineering Building, Room 2901
All are invited to attend.
Dr. Jana Kosecka, Chair
Dr. Zoran Duric
Dr. Jessica Lin
Dr. Daniel Lofaro
Supervised learning paradigm for training Deep Convolutional Neural Networks (DCNN) rests on the availability of large amounts of manually annotated images, which are necessary for training deep models with millions of parameters. In this thesis, we present novel techniques for mitigating the required manual annotation, by generating large object instance datasets through compositing textured 3D models onto commonly encountered background scenes to synthesize training images. The generated training data augmented with real world annotations outperforms models trained only on real data. Non-textured 3D models are subsequently used for keypoint learning and matching, and 3D object pose estimation from RGB images.
The proposed methods showcase promising results with regards to generalization on new and standard benchmark datasets. In the final part of the thesis, we investigate how these perception capabilities can be leveraged and encoded in a spatial map, in order to enable an agent to successfully navigate towards a target object.