Change search
ReferencesLink to record
Permanent link

Direct link
Evaluation of the CNN Based Architectures on the Problem of Wide Baseline Stereo Matching
KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
2016 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
Utvärdering av system för stereomatchning som är baserade på neurala nätverk med faltning (Swedish)
Abstract [en]

Three-dimensional information is often used in robotics and 3D-mapping. There exist several ways to obtain a three-dimensional map. However, the time of flight used in the laser scanners or the structured light utilized by Kinect-like sensors sometimes are not sufficient. In this thesis, we investigate two CNN based stereo matching methods for obtaining 3D-information from a grayscaled pair of rectified images.While the state-of-the-art stereo matching method utilize a Siamese architecture, in this project a two-channel and a two stream network are trained in an attempt to outperform the state-of-the-art. A set of experiments were performed to achieve optimal hyperparameters. By changing one parameter at the time, the networks with architectures mentioned above are trained. After a completed training the networks are evaluated with two criteria, the error rate, and the runtime.Due to time limitations, we were not able to find optimal learning parameters. However, by using settings from [17] we train a two-channel network that performed almost on the same level as the state-of-the-art. The error rate on the test data for our best architecture is 2.64% while the error rate for the state-of-the-art Siamese network is 2.62%. We were not able to achieve better performance than the state-of-the-art, but we believe that it is possible to reduce the error rate further. On the other hand, the state-of-the-art Siamese stereo matching network is more efficient and faster during the disparity estimation. Therefore, if the time efficiency is prioritized, the Siamese based network should be considered.

Place, publisher, year, edition, pages
2016. , 51 p.
Keyword [en]
Stereo matching, Stereo Reconstruction, Computer Stereo Vision, CNN, Convolutional Neural Network, Disparity Estimation, 3D reconstruction, KITTI
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
URN: urn:nbn:se:kth:diva-192476OAI: oai:DiVA.org:kth-192476DiVA: diva2:968845
Educational program
Master of Science in Engineering - Electrical Engineering; Master of Science - Systems, Control and Robotics
Supervisors
Examiners
Available from: 2016-09-13 Created: 2016-09-13 Last updated: 2016-09-13Bibliographically approved

Open Access in DiVA

fulltext(9673 kB)11 downloads
File information
File name FULLTEXT01.pdfFile size 9673 kBChecksum SHA-512
be93c50861fc94b6ae8eca6d9827fdb050ecc674b4644187f1f66965972d32790e9a1549b74f119f99bf3f14cd0b6735b0cd925bf2ae84fd80cea53d1c57f593
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Li, Vladimir
By organisation
Computer Vision and Active Perception, CVAP
Computer Vision and Robotics (Autonomous Systems)

Search outside of DiVA

GoogleGoogle Scholar
Total: 11 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 5 hits
ReferencesLink to record
Permanent link

Direct link