Enhancing object recognition for humanoid robots through time-awareness

Abstract

In this paper, we present a biologically-inspired object recognition system for humanoid robots. Our approach is based on a hierarchical model of the visual cortex for feature extraction and rapid scene categorization of natural images. We enhanced the model to be entropy-aware and real-time capable, to be able to realize object recognition over time. We integrate time in our system to model uncertainty in static object recognition by evaluating multiple recognition results of objects observed at different view-points over time using the camera system on a humanoid robot. The recognition responses are encoded as probability estimates over each trained object class. We apply a signal detection theory approach to describe the temporally and spatially distributed signals to gain a value of certainty about the object class. We show that our enhanced model outperforms the preceding model and that by integrating time as a variable we created a highly robust object recognition system.