A Multi-Task Learning Framework for Head Pose Estimation under Target Motion

A Multi-Task Learning Framework for Head Pose Estimation under Target Motion

Recently, head pose estimation (HPE) from low-resolution surveillance data has gained in importance. However, monocular and multi-view HPE approaches still work poorly under target motion, as facial appearance distorts owing to camera perspective and scale changes when a person moves around. To this...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 38(2016), 6 vom: 27. Juni, Seite 1070-83
1. Verfasser: Yan, Yan (VerfasserIn)
Weitere Verfasser: Ricci, Elisa, Subramanian, Ramanathan, Liu, Gaowen, Lanz, Oswald, Sebe, Nicu
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2016
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
LEADER 01000naa a22002652 4500
001 NLM252776488
003 DE-627
005 20231224164823.0
007 cr uuu---uuuuu
008 231224s2016 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2015.2477843  |2 doi 
028 5 2 |a pubmed24n0842.xml 
035 |a (DE-627)NLM252776488 
035 |a (NLM)26372209 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Yan, Yan  |e verfasserin  |4 aut 
245 1 2 |a A Multi-Task Learning Framework for Head Pose Estimation under Target Motion 
264 1 |c 2016 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Completed 07.05.2018 
500 |a Date Revised 02.12.2018 
500 |a published: Print-Electronic 
500 |a Citation Status MEDLINE 
520 |a Recently, head pose estimation (HPE) from low-resolution surveillance data has gained in importance. However, monocular and multi-view HPE approaches still work poorly under target motion, as facial appearance distorts owing to camera perspective and scale changes when a person moves around. To this end, we propose FEGA-MTL, a novel framework based on Multi-Task Learning (MTL) for classifying the head pose of a person who moves freely in an environment monitored by multiple, large field-of-view surveillance cameras. Upon partitioning the monitored scene into a dense uniform spatial grid, FEGA-MTL simultaneously clusters grid partitions into regions with similar facial appearance, while learning region-specific head pose classifiers. In the learning phase, guided by two graphs which a-priori model the similarity among (1) grid partitions based on camera geometry and (2) head pose classes, FEGA-MTL derives the optimal scene partitioning and associated pose classifiers. Upon determining the target's position using a person tracker at test time, the corresponding region-specific classifier is invoked for HPE. The FEGA-MTL framework naturally extends to a weakly supervised setting where the target's walking direction is employed as a proxy in lieu of head orientation. Experiments confirm that FEGA-MTL significantly outperforms competing single-task and multi-task learning methods in multi-view settings 
650 4 |a Journal Article 
700 1 |a Ricci, Elisa  |e verfasserin  |4 aut 
700 1 |a Subramanian, Ramanathan  |e verfasserin  |4 aut 
700 1 |a Liu, Gaowen  |e verfasserin  |4 aut 
700 1 |a Lanz, Oswald  |e verfasserin  |4 aut 
700 1 |a Sebe, Nicu  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 38(2016), 6 vom: 27. Juni, Seite 1070-83  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:38  |g year:2016  |g number:6  |g day:27  |g month:06  |g pages:1070-83 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2015.2477843  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 38  |j 2016  |e 6  |b 27  |c 06  |h 1070-83