Method and device for detecting aircraft in a scene by fusing ads-b trajectories and video

Abstract

The ADS-B trajectory and video fusion scene aircraft detection method and device can make full use of the complementarity of different monitoring sources, accurately detect targets that cannot be identified by a single monitoring source in a wide-area large scene airport monitoring video, and provide strong support for subsequent airport scene automatic monitoring and control. The method comprises: (1) conversion alignment and registration of airport cross-modal data, based on the correlation key indicators of the three data sources of airport scene monitoring ADS-B, monitoring video and flight plan, an alignment and registration framework is constructed, which comprises: initial screening matching pair construction, rough alignment segment acquisition, and frame-by-frame target point alignment; (2) according to the cross-modal data after registration, a feature set facing cross-modal cross attention is constructed, and a fusion model based on attention mechanism is designed; (3) input the cross-modal fusion result into a target detection model, and the target detection model detects targets that cannot be identified by a single image monitoring source.

Images