Space environment monitoring method based on rocket telemetry video

Abstract

The invention discloses a space environment monitoring method based on a rocket telemetry video, and the method comprises the following steps of collecting a rocket telemetry video image, identifyingeach pixel point in each frame of the rocket telemetry video image as a background pixel point, a rocket body pixel point or a particulate matter pixel point based on Kmeans clustering of pixel values; using a Mask R-CNN target segmentation model obtained by training on a Cityscapes data set, labeling and counting a particulate matter pixel point set obtained by clustering according to the Mask R-CNN target segmentation model to obtain an unconnected region, and performing segmentation according to the unconnected region to obtain the particulate matter information; and obtaining the moving speed and the moving track of the particulate matters according to the particulate matter optical flow. According to the method, the particle atomization concentration and range, the particle number, the average movement speed and the radius of the surrounding environment of an engine can be effectively analyzed, and the satellite position can be dynamically and accurately tracked at a satellite-rocket separation stage.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and in particular relates to a space environment monitoring method based on rocket telemetry video. Background technique [0002] The telemetry video during the flight phase of the launch vehicle is an important way to observe the separation between the working state of the rocket engine and the satellite. The video image on the rocket can describe the health status of the engine in the most intuitive and accurate way, provide rich information for post-event analysis, and ensure the success of the flight. , Improving the analysis efficiency has an irreplaceable role. [0003] Traditional image analysis for telemetry video relies on the observation of technicians, and the analysis results vary from person to person, the records are not intuitive enough, and there are gaps in accuracy, and because there are no clear quantitative evaluation indicators, it is impossible to provide reasonable ...

AI Technical Summary

Problems solved by technology

Manual observation is difficult to effectively analyze the particle concentration and average particle size in the surrounding environment of the engine

At the same time, the overall automation of video analysis is very low, and the judgment process cannot be displayed and recorded intuitively, resulting in poor traceability of the overall video analysis work.

At present, according to the characteristics and requirements of rocket telemetry video analysis, there is no complete set of video analysis technology or core algorithm based on image recognition

Images