Analysing the quality of PlaneRCNN plane parameters using a structure from motion system
(2021) In Master's Theses in Mathematical Sciences FMAM05 20202Mathematics (Faculty of Engineering)
- Abstract
- This report aims to compare the plane parameters given by the PlaneRCNN network with those created by using a Structure from Motion (SfM) solution on the same data. Several datasets are used, and the results from PlaneRCNN are evaluated by using the camera matrices from the SfM solution and applying these along with scaling and coordinate transformations. We use and explain RANSAC, neural networks of different types, and general computer vision background material (such as methods of plane creation) required to understand the component parts of the report. A general analysis of the PlaneRCNN network is offered, using different performance metrics on varying sets of data, along with practical advice on how to best use it. The end result is... (More)
- This report aims to compare the plane parameters given by the PlaneRCNN network with those created by using a Structure from Motion (SfM) solution on the same data. Several datasets are used, and the results from PlaneRCNN are evaluated by using the camera matrices from the SfM solution and applying these along with scaling and coordinate transformations. We use and explain RANSAC, neural networks of different types, and general computer vision background material (such as methods of plane creation) required to understand the component parts of the report. A general analysis of the PlaneRCNN network is offered, using different performance metrics on varying sets of data, along with practical advice on how to best use it. The end result is that we find a good method for comparing the PlaneRCNN plane parameters to those generated by SfM systems. We also note under what conditions we found PlaneRCNN to give the best results. (Less)
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/student-papers/record/9050565
- author
- Österberg, Fredrik LU
- supervisor
-
- Karl Åström LU
- David Gillsjö LU
- organization
- course
- FMAM05 20202
- year
- 2021
- type
- H2 - Master's Degree (Two Years)
- subject
- keywords
- structure from motion, PlaneRCNN, neural network, sfm, computer vision, RANSAC, planes, room reconstruction
- publication/series
- Master's Theses in Mathematical Sciences
- report number
- LUTFMA-3442-2021
- ISSN
- 1404-6342
- other publication id
- 2021:E19
- language
- English
- id
- 9050565
- date added to LUP
- 2021-08-20 15:48:50
- date last changed
- 2021-08-20 15:48:50
@misc{9050565, abstract = {{This report aims to compare the plane parameters given by the PlaneRCNN network with those created by using a Structure from Motion (SfM) solution on the same data. Several datasets are used, and the results from PlaneRCNN are evaluated by using the camera matrices from the SfM solution and applying these along with scaling and coordinate transformations. We use and explain RANSAC, neural networks of different types, and general computer vision background material (such as methods of plane creation) required to understand the component parts of the report. A general analysis of the PlaneRCNN network is offered, using different performance metrics on varying sets of data, along with practical advice on how to best use it. The end result is that we find a good method for comparing the PlaneRCNN plane parameters to those generated by SfM systems. We also note under what conditions we found PlaneRCNN to give the best results.}}, author = {{Österberg, Fredrik}}, issn = {{1404-6342}}, language = {{eng}}, note = {{Student Paper}}, series = {{Master's Theses in Mathematical Sciences}}, title = {{Analysing the quality of PlaneRCNN plane parameters using a structure from motion system}}, year = {{2021}}, }