Multi-resolution Visual Positioning and Navigation Technique for Unmanned Aerial System Landing Assistance

Abstract

To achieve more accurate navigation performance in the landing process, a multi-resolution visual positioning technique is proposed for landing assistance of an Unmanned Aerial System (UAS). This technique uses a captured image of an artificial landmark (e.g. barcode) to provide relative positioning information in the X, Y and Z axes, and yaw, roll and pitch orientations. A multi-resolution coding algorithm is designed to ensure the UAS will not lose the detection of the landing target due to limited visual angles or camera resolution. Simulation and real world experiments prove the performance of the proposed technique in positioning accuracy, detection accuracy, and navigation effect. Two types of UAS are used to verify the generalisation of the proposed technique. Comparison experiments to state-of-the-art techniques are also included with the results analysis.

Research on the detection method of sensitive information of internet remote sensing image map

“…Plane position accuracy refers to the plane position accuracy of image map features provided by remote sensing image map data, that is, the plane position deviation of ground feature elements processed by geographic information confidentiality processing technology [6][7], which is an important index that needs to be met for the public release of remote sensing image maps.…”

A virtual environment for evaluation of computer vision algorithms under general airborne camera imperfections

“…For exact timeshift modelling, one should render frames in every timeshift (e.g., every row for rolling shutter) and then mix them, which is a non-real-time solution. Rendering a frame in this way may take up to tens of seconds (Huang et al., 2012; Zhang et al., 2014). An overview of motion blur generating methods is presented in Navarro et al.…”