Show simple item record

dc.contributorVaras González, David
dc.contributorMorros Rubió, Josep Ramon
dc.contributor.authorLlorca Queralt, Ramón
dc.date.accessioned2016-06-13T06:23:33Z
dc.date.issued2014-10-30
dc.identifier.urihttp://hdl.handle.net/2117/87911
dc.description.abstractAlong this thesis, a novel and robust approach for automatic human annotation in long video sequences is addressed. This work defines a fully automatic pipeline that is able to deal with different types of sequences. The proposed system has been both designed and implemented following a divide and conquer approach. First, a shot detector is used to divide the sequences in smaller ones. Then, humans are detected using a face detector based on the Viola & Jones algorithm. Once humans are detected, their faces are tracked using color-based particle filters and Local Binary Patterns (LBP). Several techniques and refinements have been implemented to improve the overall robustness of the system. Moreover, a track-by-detection technique is used to enhance the tracking accuracy. Finally, each human's track is annotated throughout every shot of the sequence. The performance of the global system is assessed in experiments with real sequences and compared against human made annotations. Furthermore, these annotated tracks set the groundwork for a future recognition system, that will complete the task of automatically annotating identities throughout sequences.
dc.language.isoeng
dc.publisherUniversitat Politècnica de Catalunya
dc.subjectÀrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeo
dc.subject.lcshVideo recording
dc.subject.lcshHuman face recognition (Computer science)
dc.subject.otherFace detection
dc.subject.otherface tracking
dc.subject.otherparticle filters
dc.subject.otherlocal binary patterns
dc.subject.otherViola & Jones
dc.subject.othershot boundary detection and tracking-by-detection
dc.subject.otherautomatic human annotation
dc.titleAutomatic human detection and tracking for robust video sequence annotation
dc.title.alternativeDetecció i seguiment automatic d'humans per una robusta anotació de seqüències de vídeo
dc.typeMaster thesis
dc.subject.lemacVídeo
dc.subject.lemacReconeixement facial (Informàtica)
dc.identifier.slugETSETB-230.104420
dc.rights.access120 months embargo
dc.date.lift2026-06-13T06:23:33Z
dc.date.updated2016-06-10T10:28:41Z
dc.audience.educationlevelMàster
dc.audience.mediatorEscola Tècnica Superior d'Enginyeria de Telecomunicació de Barcelona


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder