Planar Geometry estimation with deep learning
tarafından
 
Uzyıldırım, Furkan Eren, author.

Başlık
Planar Geometry estimation with deep learning

Yazar
Uzyıldırım, Furkan Eren, author.

Yazar Ek Girişi
Uzyıldırım, Furkan Eren, author.

Fiziksel Tanımlama
ix, 93 leaves: charts;+ 1 computer laser optical disc.

Özet
Understanding the geometric structure of any scene is one of the oldest problems in Computer Vision. Most scenes include planar regions that provide information about the geometric structure and their automatic detection and segmentation plays an important role in many computer vision applications. In recent years, convolutional neural network architectures have been introduced for piece-wise planar segmentation. They outperform the traditional approaches that generate plane candidates with 3D segmentation methods from the explicitly reconstructed 3D point cloud. However, most of the convolutional neural network architectures are not designed and trained for outdoor scenes, because they require manual annotation, which is a time-consuming task that results in a lack of training data. In this thesis,we propose and develop a deep learning based framework for piece-wise plane detection and segmentation of outdoor scenes without requiring manually annotated training data. We exploit a network trained on imagery with annotated targets and an automatically reconstructed point cloud from either Structure from Motion-Multi View Stereo pipeline or monocular depth estimation network to estimate the training ground truth on the outdoor images in an iterative energy minimization framework. We show that the resulting ground truth estimate of various sets of images in the outdoor domain is good enough to improve network weights of different architectures trained on ground truth annotated images. Moreover, we demonstrate that this transfer learning scheme can be repeated multiple times iteratively to further improve the accuracy of plane detection and segmentation on monocular images of outdoor scenes.

Konu Başlığı
Deep learning (Machine learning)
 
Machine learning
 
Computer vision

Yazar Ek Girişi
Özuysal, Mustafa,

Tüzel Kişi Ek Girişi
İzmir Institute of Technology. Computer Engineering.

Tek Biçim Eser Adı
Thesis (Doctoral)--İzmir Institute of Technology:Computer Engineering.
 
İzmir Institute of Technology: Computer Engineering--Thesis (Doctoral).

Elektronik Erişim
Access to Electronic Versiyon.


LibraryMateryal TürüDemirbaş NumarasıYer NumarasıDurumu/İade Tarihi
IYTE LibraryTezT002495Q325.73 .U99 2022Tez Koleksiyonu