Unmanned plane all-weather carrier landing cooperation target robustness detection and coupling method

Abstract

The invention discloses an unmanned plane all-weather carrier landing cooperation target robustness detection and coupling method. The method includes a cooperation target image acquisition step including that an image acquisition device acquires the images of the carrier landing area, the acquired images include an image of a thermal infrared carrier landing cooperation target which is composed of five heating electric furnaces distributed on the same plane and in a cross shape; and a cooperation target image processing step including 201, image pre-processing; 202, image segmentation based on a significant area; 203, contour information extraction; 204, thermal infrared cooperation target detection and coupling and including the steps of distance constrain, shape constrain, and position constrain. The method is simple in step, reasonable in design, convenient to realize, high in detection precision, and good in use effect, and can carry out the accurate robustness detection and rapid coupling of the cooperation target for the long-distance and all-weather guiding of the unmanned plane carrier landing under a complex environment.

Description

technical field [0001] The invention belongs to the technical field of visual navigation, and in particular relates to a method for robust detection and matching of unmanned aerial vehicles' all-weather landing cooperative targets. Background technique [0002] Visual relative navigation has the advantages of strong autonomy, passiveness, and high guidance accuracy, making the technology of UAV landing based on vision guidance an important research field at home and abroad. At present, institutions engaged in research in this field include Rennes University, the U.S. Naval Research Institute, and Carnegie Mellon University abroad. The main domestic research institutions include Beihang University, China Southern Airlines University, Western Polytechnic University, and Tsinghua University. When using vision for relative navigation of ship landing, one of the most important parts is the design of cooperative target and its cooperative target detection algorithm. [0003] At p...

AI Technical Summary

Problems solved by technology

The cooperation target composed of black and white and the color cooperation target are mainly suitable for the situation where the visibility is good and the distance from the cooperation target is relatively good, and it cannot be used in the case of poor visibility such as night, rainy day and the distance from the cooperation target

Although the near-infrared ship landing cooperative target can guide the UAV at night, its detection distance is limited, and its ability to resist environmental interference is not strong

The cooperative targets composed of thermal infrared sources can realize all-weather and long-distance guidance of shipborne UAVs, but the thermal infrared cooperative targets currently designed adopt a fixed shape (such as H shape or T shape). When the UAV is far away from the thermal infrared cooperative target, due to the low contrast of the thermal infrared image and the poor ability to distinguish details, it is difficult to accurately extract and match the characteristic information (such as corner points) of the cooperative target.

Therefore, in the current research results, the cooperation target and the corresponding detection method with good real-time performance and high detection accuracy have not been found to meet the complex environment, long-distance, all-weather guided UAV landing use; and, in the accurate detection of cooperation After the target is detected, how to accurately match the feature points of the cooperative target detected in the image with the feature points of the pre-calibrated cooperative target is also a key issue.

Images