Toward robust foveated wide field of view people detection

Abstract

We present foveated vision system for rapid and robust person detection. The system consists of an omidirectional camera for people detection in a wide field of view and a pan-tilt camera that can focus on a particular location. Combining the information from both cameras leads to more reliable people detection. The people detection is based on fast human body part detectors and a probabilistic model of the spatial arrangement of the parts. The model can be extended to multiple cameras. The representation is robust to partial occlusions, part detector false alarms and missed detections of body parts. We also show how to use the fact that the persons walk on a known ground plane to increase the efficiency and reliability of the detection. The detection does not rely on static background and the system is suitable for mobile platforms.