liu.seSearch for publications in DiVA
Change search
ReferencesLink to record
Permanent link

Direct link
Synthetic Ground Truth for Feature Trackers
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, The Institute of Technology.ORCID iD: 0000-0002-5698-5983
2008 (English)In: Swedish Symposium on Image Analysis 2008, 2008Conference paper (Other academic)
Abstract [en]

Good data sets for evaluation of computer visionalgorithms are important for the continuedprogress of the field. There exist good evaluationsets for many applications, but there are othersfor which good evaluation sets are harder to comeby. One such example is feature tracking, wherethere is an obvious difficulty in the collection ofdata. Good evaluation data is important both forcomparisons of different algorithms, and to detectweaknesses in a specific method.All image data is a result of light interactingwith its environment. These interactions are sowell modelled in rendering software that sometimesnot even the sharpest human eye can tell the differencebetween reality and simulation. In this paperwe thus propose to use a high quality renderingsystem to create evaluation data for sparse pointcorrespondence trackers.

Place, publisher, year, edition, pages
National Category
Engineering and Technology
URN: urn:nbn:se:liu:diva-58548OAI: diva2:343534
Swedish Symposium on Image Analysis 2008, 13-14 Marsh, Lund, Sweden
Available from: 2010-08-18 Created: 2010-08-13 Last updated: 2015-12-10Bibliographically approved
In thesis
1. Pose Estimation and Structure Analysisof Image Sequences
Open this publication in new window or tab >>Pose Estimation and Structure Analysisof Image Sequences
2009 (English)Licentiate thesis, comprehensive summary (Other academic)
Abstract [en]

Autonomous navigation for ground vehicles has many challenges. Autonomous systems must be able to self-localise, avoid obstacles and determine navigable surfaces. This thesis studies several aspects of autonomous navigation with a particular emphasis on vision, motivated by it being a primary component for navigation in many high-level biological organisms.  The key problem of self-localisation or pose estimation can be solved through analysis of the changes in appearance of rigid objects observed from different view points. We therefore describe a system for structure and motion estimation for real-time navigation and obstacle avoidance. With the explicit assumption of a calibrated camera, we have studied several schemes for increasing accuracy and speed of the estimation.The basis of most structure and motion pose estimation algorithms is a good point tracker. However point tracking is computationally expensive and can occupy a large portion of the CPU resources. In thisthesis we show how a point tracker can be implemented efficiently on the graphics processor, which results in faster tracking of points and the CPU being available to carry out additional processing tasks.In addition we propose a novel view interpolation approach, that can be used effectively for pose estimation given previously seen views. In this way, a vehicle will be able to estimate its location by interpolating previously seen data.Navigation and obstacle avoidance may be carried out efficiently using structure and motion, but only whitin a limited range from the camera. In order to increase this effective range, additional information needs to be incorporated, more specifically the location of objects in the image. For this, we propose a real-time object recognition method, which uses P-channel matching, which may be used for improving navigation accuracy at distances where structure estimation is unreliable.

Place, publisher, year, edition, pages
Linköping: Linköping University Electronic Press, 2009. 28 p.
Linköping Studies in Science and Technology. Thesis, ISSN 0280-7971 ; 1418
KLT, GPU, structure from motion, stereo, pose estimation
National Category
Engineering and Technology Computer Vision and Robotics (Autonomous Systems) Signal Processing
urn:nbn:se:liu:diva-58706 (URN)LiU-TEK-LIC-2009:26 (Local ID)978-91-7393-516-6 (ISBN)LiU-TEK-LIC-2009:26 (Archive number)LiU-TEK-LIC-2009:26 (OAI)
Available from: 2011-01-25 Created: 2010-08-23 Last updated: 2016-05-04Bibliographically approved

Open Access in DiVA

fulltext(921 kB)292 downloads
File information
File name FULLTEXT01.pdfFile size 921 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Hedborg, JohanForssén, Per-Erik
By organisation
Computer VisionThe Institute of Technology
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 292 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: 170 hits
ReferencesLink to record
Permanent link

Direct link