Abstract

Persistent detection and tracking of moving vehicles in airborne imagery provide indispensable information for many traffic surveillance applications including traffic monitoring and management, navigation systems, activity recognition and event detection. This paper presents a col- laborative Spatial Pyramid Context-aware detection and Tracking system (SPCT) for moving vehicles in dense ur- ban aerial imagery. The proposed system is composed of one master tracker that usually relies on visual object fea- tures and two auxiliary trackers based on object temporal motion information that will be called dynamically to assist master tracker. SPCT utilizes image spatial context at dif- ferent level to make the video tracking system resistant to occlusion, background noise and improve target localiza- tion accuracy. We chose a pre-selected seven-channel com- plementary features including RGB color, intensity and spa- tial pyramid of HoG (PHoG) and exploit integral histogram as building block to meet the demands of real-time per- formance. The extensive experiments on ARGUS and ABQ wide aerial video and comparison with state-of-the-art sin- gle object trackers confirm that combining complementary tracking cues in an intelligent fusion framework is essential to address the challenges of persistent tracking in low frame rate Wide Aerial Motion Imagery (WAMI).