CNNObjectDetection

Chair for Computer Aided Medical Procedures & Augmented Reality
Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality

THIS WEBPAGE IS DEPRECATED - please visit our new website

DA/MA/BA Thesis: RGB-D Object Detection with Deep Learning

We offer a Master Thesis in the field of autonomous robotics that deals with the development of 3D object detection from RGB-D data using Deep Learning. In conjunction with the thesis activity, a hiwi position could also be offered to the student to support this activity. Upon successful completion of the work, a continuation in the form of a PhD? position might also be offered. The thesis is part of a project heavily supported by a worldwide leader in the automotive field.

Background

Detecting multiple 3D objects in a scene and estimating their 6DoF pose is a challenging task, especially in presence of clutter and heavy occlusions. Furthermore, scaling to many objects without increasing the runtime poses another challenging problem. With this thesis, we plan to advance the state of the art by developing a new 3D object detection approach based on the use of Convolutional Neural Networks (CNNs).

Requirements

We are looking for a highly qualified and motivated student, with passion towards both applied computer vision and basic research. The prospective student needs to have strong background in C++ and Python and should be familiar with Computer Vision techniques. Experience with Machine Learning (in particular Deep Learning libraries such as Caffe or Theano) and CUDA programming is a plus.

Contact

Mail to Federico Tombari, or drop by room 03.13.042


ProjectForm
Title: RGB-D Object Detection with Deep Learning
Abstract: Detecting multiple 3D objects in a scene and estimating their 6DoF pose is a challenging task, especially in presence of clutter and heavy occlusions. Furthermore, scaling to many objects without increasing the runtime poses another challenging problem. With this thesis, we plan to advance the state of the art by developing a new 3D object detection approach based on the use of Convolutional Neural Networks (CNNs).
Student:  
Director: Prof. Nassir Navab
Supervisor: Wadim Kehl, Federico Tombari
Type: DA/MA/BA
Area: Machine Learning, Computer Vision
Status: open
Start:  
Finish:  
Thesis (optional):  
Picture:  


Edit | Attach | Refresh | Diffs | More | Revision r1.2 - 12 Feb 2016 - 12:20 - FedericoTombari