Vision-based Pedestrian Detection: will Ants Help?

This work presents the vision-based system for detecting pedestrians in road environments implemented on the ARGO prototype vehicle developed by the University of Parma. The system is aimed at the localization of pedestrians in various poses, positions and clothing, and is not limited to moving people. Initially, attentive vision techniques relying on the search for specific characteristics of pedestrians such as vertical symmetry and strong presence of edges, allow to select interesting regions likely to contain pedestrians. Then, such candidates areas are validated verifying the actual presence of pedestrians by means of an shape detection technique based on the application of autonomous agents. Keywords— pedestrian detection, machine vision, autonomous agents, symmetry, ants.