Scene matching based on spatial relation constraint in suitable-matching area

Abstract

Scene matching navigation system (SMNS) is one of the most effective ways of aided navigation for UAV. With anti-electronic interference and high resolution, SMN could be navigating and locating reliably and accurately. The navigational positioning ability with high reliability and high accuracy must be needed. For the complexity of the work environment of scene matching navigation on the platform of UAV, a multi-region scene matching algorithm for suitable-matching area based on the spatial relation constraint was proposed in this paper. This algorithm adopts parallel computing to improve the real-time performance of SMNS. The optimal allocation of coordinates of center point can be estimated ultimately by calculating the spatial relation of many match areas. So the precise location of real-time image center at the base map can be gotten. At last, a method based on previous navigation data was designed to check the location. To accomplish the on-line scene matching reliably and precisely, this algorithm only needs one real-time frame image to match base map every time. Experiments show that this algorithm meets the UAV navigation performance requirements such as real-time, robustness and high accuracy.