Synthetic Ground Truth for Feature Trackers
2008 (English)In: Swedish Symposium on Image Analysis 2008, 2008Conference paper (Other academic)
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
Engineering and Technology
IdentifiersURN: urn:nbn:se:liu:diva-58548OAI: oai:DiVA.org:liu-58548DiVA: diva2:343534
Swedish Symposium on Image Analysis 2008, 13-14 Marsh, Lund, Sweden