Research Article
High Precision Extraction of UAV Tracking Image Information Based on Big Data Technology
@INPROCEEDINGS{10.1007/978-3-031-28787-9_7, author={Xiaobo Jiang and Wenda Xie}, title={High Precision Extraction of UAV Tracking Image Information Based on Big Data Technology}, proceedings={Advanced Hybrid Information Processing. 6th EAI International Conference, ADHIP 2022, Changsha, China, September 29-30, 2022, Proceedings, Part I}, proceedings_a={ADHIP}, year={2023}, month={3}, keywords={Big data technology UAV Image information Precision improvement}, doi={10.1007/978-3-031-28787-9_7} }- Xiaobo Jiang
Wenda Xie
Year: 2023
High Precision Extraction of UAV Tracking Image Information Based on Big Data Technology
ADHIP
Springer
DOI: 10.1007/978-3-031-28787-9_7
Abstract
The high-precision extraction of UAV tracking image information is of great significance to the development of UAV system, attitude control, real-time flight path planning and correction, accident analysis and payload. In order to improve the precision of UAV tracking image information extraction, a high precision UAV tracking image extraction method based on big data technology is proposed. Collect the tracking image information of UAV, and eliminate the spectral reflectance of ground objects through atmospheric correction; A multi viewpoint dense image matching method is used to generate a feature recognition model of image information; Creatively uses cubic convolution interpolation to establish image matrix; Calculate the world coordinates of the same feature point and the spatial direction of the wing line and symmetry axis to evaluate the image clarity of the UAV; The pyramid image matching strategy is used to automatically match and jointly adjust the points of the same name in each image layer; The size and direction of the key points are determined by fitting the three-dimensional quadratic function, and the gradient and direction of the key points are calculated respectively to achieve high-precision extraction of UAV tracking image information. Finally, the experiment results show that the method improves the precision of UAV tracking image information extraction, has high practicability and meets the requirements of the research.
