A Bio-Inspired Computational Model for the 3D Motion Estimation

Stereoscopic motion perception is pivotal for human-world interaction and has sparked advancements in artificial vision technologies. We introduce the Stereo Motion Perception Model (SMPM), a bio-inspired computational model designed to emulate the process of stereoscopic motion perception inherent in the human visual system. The SMPM extracts temporal, spatial, and shape features from stereoscopic video stimuli, enabling accurate motion perception. The performance of SMPM is tested and compared with human perception. The results indicates that the SMPM effectively estimates target motion on both simplistic and complex scene, high consistency is shown with human stereo motion perception. Future implications of the bio-inspired model is discussed.