000197849 001__ 197849
000197849 005__ 20190416055540.0
000197849 037__ $$aCONF
000197849 245__ $$aA new database of still and moving High Dynamic Range pictures
000197849 269__ $$a2014
000197849 260__ $$c2014
000197849 336__ $$aConference Papers
000197849 520__ $$aEmerging new imaging technologies, such as HDR (High Dynamic Range) or UHD (Ultra High Definition), have a significant impact in various applications. One of them, namely, visual privacy protection in video surveillance is an important and increasingly popular research topic. To evaluate the influence of new imaging technologies, a suitable dataset of images and video sequences is needed. However, there are only few datasets for testing performance of various algorithms on above mentioned applications, and moreover, a little to nothing exists for evaluation of visual privacy tools. Since surveillance and privacy protection have contradictory objectives, the design principles of corresponding evaluation datasets should differ too. In this paper, we present a new dataset of still and moving pictures considering the predefined principles for privacy evaluation in video surveillance applications. Annotations of various privacy related regions, such as face, hair, body silhouette, skin regions, accessories, and other personal information, including their description, are provided within the dataset. Presented dataset will serve for evaluation of privacy protection tools using both objective and subjective assessment, as well as for showing the importance of HDR imaging in video surveillance applications and its influence on the privacy-intelligibility trade-off.
000197849 6531_ $$aHDR
000197849 6531_ $$adataset
000197849 6531_ $$aprivacy evaluation
000197849 6531_ $$aprivacy filters
000197849 700__ $$0244457$$g206402$$aRerabek, Martin
000197849 700__ $$aEbrahimi, Touradj$$g105043$$0240223
000197849 7112_ $$dMarch 04-05, 2014$$cSarajevo, Bosnia and Herzegovina,$$aHDRi2014 -Second International Conference and SME Workshop on HDR imaging
000197849 8564_ $$uhttp://www.ic1005-hdri.com/node/95$$zURL
000197849 8564_ $$uhttps://infoscience.epfl.ch/record/197849/files/HDRiArticleFinal.pdf$$zPublisher's version$$s3644651$$yPublisher's version
000197849 909C0 $$0252077$$pMMSPL
000197849 909CO $$pSTI$$ooai:infoscience.tind.io:197849$$qGLOBAL_SET$$pconf
000197849 917Z8 $$x206402
000197849 937__ $$aEPFL-CONF-197849
000197849 973__ $$rNON-REVIEWED$$sPUBLISHED$$aEPFL
000197849 980__ $$aCONF