DocumentCode :
148248
Title :
Articulated human motion tracking with foreground learning
Author :
Aichun Zhu ; Snoussi, Hichem ; Cherouat, Abel
Author_Institution :
ICD - LM2S, Univ. de Technol. de Troyes (UTT), Troyes, France
fYear :
2014
fDate :
1-5 Sept. 2014
Firstpage :
366
Lastpage :
370
Abstract :
Tracking the articulated human body is a challenging computer vision problem because of changes in body poses and their appearance. Pictorial structure (PS) models are widely used in 2D human pose estimation. In this work, we extend the PS models for robust 3D pose estimation, which includes two stages: multi-view human body parts detection by foreground learning and pose states updating by annealed particle filter (APF) and detection. Moreover, the image dataset F-PARSE was built for foreground training and flexible mixture of parts (FMP) model was used for foreground learning. Experimental results demonstrate the effectiveness of our foreground learning-based method.
Keywords :
computer vision; image motion analysis; learning (artificial intelligence); object detection; object tracking; particle filtering (numerical methods); pose estimation; 2D human pose estimation; APF; FMP model; PS models; annealed particle filter; articulated human motion tracking; body poses; computer vision problem; flexible mixture of part model; foreground learning-based method; foreground training; image dataset F-PARSE; multiview human body part detection; pictorial structure model; pose states; robust 3D pose estimation; Annealing; Biological system modeling; Estimation; Solid modeling; Three-dimensional displays; Tracking; Vectors; Annealed particle filter; foreground learning; human motion tracking;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Signal Processing Conference (EUSIPCO), 2014 Proceedings of the 22nd European
Conference_Location :
Lisbon
Type :
conf
Filename :
6952072
Link To Document :
بازگشت