Spatiotemporal semantic video segmentation

Galmar, E; Athanasiadis, Th; Huet, B; Avrithis, Y

dc.contributor.author	Galmar, E	en
dc.contributor.author	Athanasiadis, Th	en
dc.contributor.author	Huet, B	en
dc.contributor.author	Avrithis, Y	en
dc.date.accessioned	2014-03-01T02:45:47Z
dc.date.available	2014-03-01T02:45:47Z
dc.date.issued	2008	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/32394
dc.subject	Image Segmentation	en
dc.subject	Semantic Annotation	en
dc.subject	Temporal Variation	en
dc.subject	Video Segmentation	en
dc.subject.other	Image processing	en
dc.subject.other	Image segmentation	en
dc.subject.other	Information theory	en
dc.subject.other	Labeling	en
dc.subject.other	Signal processing	en
dc.subject.other	Technical presentations	en
dc.subject.other	Video recording	en
dc.subject.other	Video signal processing	en
dc.subject.other	Computational costs	en
dc.subject.other	Graph structures	en
dc.subject.other	Object labeling	en
dc.subject.other	Real video sequences	en
dc.subject.other	Region labeling	en
dc.subject.other	Semantic annotations	en
dc.subject.other	Semantic properties	en
dc.subject.other	Semantic segmentations	en
dc.subject.other	Spatio temporals	en
dc.subject.other	Spatio-temporal segmentations	en
dc.subject.other	Spatiotemporal regions	en
dc.subject.other	Temporal variations	en
dc.subject.other	Two stages	en
dc.subject.other	Video segmentations	en
dc.subject.other	Video sequences	en
dc.subject.other	Video shots	en
dc.subject.other	Visual properties	en
dc.subject.other	Semantics	en
dc.title	Spatiotemporal semantic video segmentation	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/MMSP.2008.4665143	en
heal.identifier.secondary	http://dx.doi.org/10.1109/MMSP.2008.4665143	en
heal.identifier.secondary	4665143	en
heal.publicationDate	2008	en
heal.abstract	In this paper, we propose a framework to extend semantic labeling of images to video shot sequences and achieve efficient and semantic-aware spatiotemporal video segmentation. This task faces two major challenges, namely the temporal variations within a video sequence which affect image segmentation and labeling, and the computational cost of region labeling. Guided by these limitations, we design a method where spatiotemporal segmentation and object labeling are coupled to achieve semantic annotation of video shots. An internal graph structure that describes both visual and semantic properties of image and video regions is adopted. The process of spatiotemporal semantic segmentation is subdivided in two stages: Firstly, the video shot is split into small block of frames. Spatiotemporal regions (volumes) are extracted and labeled individually within each block. Then, we iteratively merge consecutive blocks by a matching procedure which considers both semantic and visual properties. Results on real video sequences show the potential of our approach. © 2008 IEEE.	en
heal.journalName	Proceedings of the 2008 IEEE 10th Workshop on Multimedia Signal Processing, MMSP 2008	en
dc.identifier.doi	10.1109/MMSP.2008.4665143	en
dc.identifier.spage	574	en
dc.identifier.epage	579	en