GrabCut-Based Human Segmentation in Video Sequences
AbstractIn this paper, we present a fully-automatic Spatio-Temporal GrabCut human segmentation methodology that combines tracking and segmentation. GrabCut initialization is performed by a HOG-based subject detection, face detection, and skin color model. Spatial information is included by Mean Shift clustering whereas temporal coherence is considered by the historical of Gaussian Mixture Models. Moreover, full face and pose recovery is obtained by combining human segmentation with Active Appearance Models and Conditional Random Fields. Results over public datasets and in a new Human Limb dataset show a robust segmentation and recovery of both face and pose using the presented methodology. View Full-Text
Share & Cite This Article
Hernández-Vela, A.; Reyes, M.; Ponce, V.; Escalera, S. GrabCut-Based Human Segmentation in Video Sequences. Sensors 2012, 12, 15376-15393.
Hernández-Vela A, Reyes M, Ponce V, Escalera S. GrabCut-Based Human Segmentation in Video Sequences. Sensors. 2012; 12(11):15376-15393.Chicago/Turabian Style
Hernández-Vela, Antonio; Reyes, Miguel; Ponce, Víctor; Escalera, Sergio. 2012. "GrabCut-Based Human Segmentation in Video Sequences." Sensors 12, no. 11: 15376-15393.