Bio-inspired Approach for the Recognition of Goal-Directed Hand Actions

The recognition of transitive, goal-directed actions requires a sensible balance between the representation of specific shape details of effector and goal object and robustness with respect to image transformations. We present a biologically-inspired architecture for the recognition of transitive actions from video sequences that integrates an appearancebased recognition approach with a simple neural mechanism for the representation of the effector-object relationship. A large degree of position invariance is obtained by nonlinear pooling in combination with an explicit representation of the relative positions of object and effector using neural population codes. The approach was tested on real videos, demonstrating successful invariant recognition of grip types on unsegmented video sequences. In addition, the algorithm reproduces and predicts the behavior action-selective neurons in parietal and prefrontal cortex.

• Type: Conference
• Year: 2009
• Where: CAIP
• Authors: Falk Fleischer, Antonino Casile, Martin A. Giese
• Keywords: Appearancebased Recognition Approach, CAIP 2009, Pattern Recognition, Successful Invariant Recognition, Video Sequences