Loading...
| Friend's email | |
| Your name | |
| Your email | |
| enter code | |
This page was sent successfuly
- Type of Document: M.Sc. Thesis
- Language: Farsi
- Document No: 57415 (02)
- University: Sharif University of Technology
- Department: Mathematical Sciences
- Advisor(s): Moghadasi, Reza
- Abstract:
- One of the important tasks in machine vision is 3D structure reconstruction or depth estimation. In recent decades, methods based on machine learning have been presented, which can be used to perform this costly task more optimally. For this purpose, two branches of supervised and unsupervised learning have been considered. In supervised learning, the available data is in the form of image-depth map pairs, such as the kitti dataset. The image is fed to the network and the output is made in the form of a depth map. The cost function of this network is obtained by comparing the generated depth map and the depth map in the data set calculated by laser. In unsupervised learning, there is no depth map information. A depth map is obtained by a network and the original image is reconstructed by another network according to the obtained depth map. The cost function of this method is obtained by comparing the input image and the reconstructed image. Recently, methods based on the mentioned board and algorithm (semi-supervised methods) have been considered. In this thesis, the problem of depth recovery is investigated using semi-supervised methods and a comparison between its results and the results of conventional methods is presented
- Keywords:
- Semi-Supervised Learning ; Computer Vision ; Depth Estimation ; Machine Learning ; Neural Network ; Image Retrieval
Digital Object List
-
محتواي کتاب
- view
Bookmark