Attitude parameters extraction of UAV based on hybrid computer vision and improved artificial bee colony algorithm

In this paper, we proposed a hybrid method in extracting the attitude parameters of unmanned aerial vehicle (UAV), which is based on computer vision and improved artificial bee colony (ABC) algorithm. Horizon is used as a characteristic line, whose two parameters, Φ and σ are utilized to obtain UAV´s parameters: roll angle ψ and pitch angle θ. Defogging Algorithm is used to make the original pictures clearer and gain the transmission image for horizon abstraction. The UAV could obtain the horizon through improved ABC independently. We also analyzed the relationship between line parameters and UAV parameters and calculated the UAV parameters. Experimental results verified the feasibility and effectiveness of our presented approach.