Target Tracking and Grabbing of Cable-driven Aerial Manipulator Based on Binocular Vision
To improve the accuracy of target pose estimation on aerial manipulator platform,the aerial manipulator is equipped with a binocular vision system,and the cable-driven manipulator and the binocular camera are modeled.By the Camshift algorithm and with the geometric characteristics of the target,a lightweight target pose estimation algorithm is proposed,which can be used for real-time target tracking and pose estimating on aerial platform as well as for grasping experiment of aerial manipulator.Experiments show that the proposed pose estimation algorithm has good accuracy for target tracking and pose estimating,and can undertake grasping operation.