250 likes | 395 Views
Recognition, Analysis and Synthesis of Gesture Expressivity. George Caridakis IVML-ICCS. Overview. Corpus Image processing module Gesture Recognition Expressivity Analysis Expressivity Synthesis Applications. Overview. Corpus mint-IVML. 7 subjects 7 gesture classes
E N D
Recognition, Analysis and Synthesis of Gesture Expressivity George Caridakis IVML-ICCS
Overview • Corpus • Image processing module • Gesture Recognition • Expressivity Analysis • Expressivity Synthesis • Applications
Corpus mint-IVML • 7 subjects • 7 gesture classes • 20 gesture variations (3 quadrants) • 20’ minutes – 30000 frames
Head detection • Detect candidate facial areas • Validate using skin probability • Conclude on number of persons
Hand Detection • Skin probability • Thresholding & Morphology Operations • Distance Transform • Frame difference
Tracking • Scoring system based on: • Skin region size • Distance wrt the previous position • Optical flow alignment • Spatial constraints • Thresholding scores • Periodical re-initialization
HMM parameters for gestures • States are head and hands coordinates • XL-XR XH-XR XH-XL YL-YR YH-YR YH-YL • 6 output states • Bakis left-to-right models • Continuous output distribution • 3 Gaussian mixtures • Arbitrary training initial estimation of transition probabilities
Recognition via HMM (Why HMMs?) • Stochastic models fit the nature of the gestures • Fast convergence due to effective training algorithms • Sufficient modeling of the temporal aspect of gestures • Continuous HMMs suitable for gesture-level classification
Expressivity features analysis • Overall activation • Spatial extent • Temporal • Fluidity • Power/Energy • Repetitivity
Overall activation • Considered as the quantity of movement during a conversational turn • Computed as the sum of the motion vectors’ norm
Spatial extent • Modeled by expanding or condensing the entire space in front of the agent that is used for gesturing • Calculated as the maximum Euclidean distance of the position of the two hands • The average spatial extent is also calculated for normalization reasons
Temporal • The temporal parameter of the gesture determines the speed of the arm movement of a gesture’s meaning carrying stroke phase and also signifies the duration of movements (e.g., quick versus sustained actions)
Fluidity • Differentiates smooth/graceful from sudden/jerky ones. This concept seeks to capture the continuity between movements, the arms’ trajectory paths as well as the acceleration and deceleration of the limbs • To extract this feature from the input image sequences we calculate the sum of the variance of the norms of the motion vectors
Power/Energy • The power is actually identical with the first derivative of the motion vectors calculated in the first steps
Results of expressivity analysis Spatial Extent EF variation Overall Activation Temporal Fluidity Power/Energy
Expressive synthesis • A system that mimics user’s behaviour through the analysis of facial and gesture signals and expressivity
Synthesis • Greta Platform • BAP calculation • Plane assumption • Inverse kinematics • Manual adaptation • Expressivity features variations implemented in Greta’s BAP interpolation