Monitoring Human and Vehicle Activities Using Airborne Video

Ongoing work in Activity Monitoring (AM) for the Airborne Video Surveillance (AVS) project is described. The goal for AM is to recognize activities of interest involving humans and vehicles using airborne video. AM consists of three major components: (1) moving object detection, tracking, and classication; (2) image to site-model registration; (3) activity recognition. Detecting and tracking humans and vehicles from airborne video is a challenging problem due to image noise, low GSD, poor contrast, motion parallax, motion blur, and camera jitter. We use frame-to-frame ane-warping stabilization and temporally integrated intensity dierences to detect independent motion. Moving objects are initially tracked using nearest-neighbor correspondence, followed by a greedy method that favors long track lengths and assumes locally constant velocity. Object classication is based on object size, velocity, and periodicity of motion. Site-model registration uses GPS information and camera/airplane..