Multi-modal people detection from aerial video

Abstract

Automatic people detection is a highly desirable capability for autonomous Unmanned Aerial Vehicles (UAV) operating in search and rescue missions. Here we present an approach for automatic people detection from aerial video using a combination of infrared and visible imagery. The results presented show that existing state of the art part-based people detection algorithms can be used with considerable success in aerial imagery. In a cluttered urban environment, the detection rate is approximately 80% over an entire flight pattern. We show that, by fusing visible and infrared imagery and tracking detections over time, the false positive rate is reduced to a minimum. © Springer International Publishing Switzerland 2013.