Localization of Aerial Robot Based on Fisheye Cameras in a Virtual Lab

Abstract

This research represents localization of an aerial robot using fisheye cameras on walls in a simulation environment. The virtual testbed in this work is a quadrotor that is simulated in MATLAB Simulink. Subsequently, the simulation outputs as flight records are used in a virtual lab, which is developed in 3DsMAX. Then, the virtual fisheye cameras (here two) are installed in some different points on the walls and the related images from the cameras are received offline. The gathered images will be processed by OpenCV in a C++ environment. For external calibration, each fisheye camera takes an image from a known pattern consist of some lights placed in the virtual lab. We execute Perspective-n-Point method on the images to obtain pierce direction/position of the camera. For more, the aerial robot is localized by computing the nearest point between two lines of sight. In brief, the outcomes exhibit an accuracy of 4cm in the center of the virtual-room room.

Keywords

• virtual environment
• visual navigation
• fisheye calibration
• fisheye camera
• perspective-n-point
• aerial robot