Pearson’s Correlation Coefficient: A More Realistic Threshold for Applications on Autonomous Robotics

Abstract

Many applications for control of autonomous platform are being developed and one important aspect is the excess of information, frequently redundant, that imposes a great computational cost in data processing. Taking into account the temporal coherence between consecutive frames, the PCC (Pearson's Correlation Coefficient) was proposed and applied as: discarding criteria methodology, dynamic power management solution, environment observer method which selects automatically only the regions-of-interest; and taking place in the obstacle avoidance context, as a method for collision risk estimation for vehicles in dynamic and unknown environments. Even if the PCC is a great tool to help the autonomous or semi-autonomous navigation, distortions in the imaging system, pixel noise, slight variations in the object's position relative to the camera, and other factors produce a false PCC threshold. Whereas there are homogeneous regions in the image, in order to obtain a more realistic Pearson's correlation, we propose to use some prior known environment information.