Issue |
JNWPU
Volume 39, Number 5, October 2021
|
|
---|---|---|
Page(s) | 1022 - 1028 | |
DOI | https://doi.org/10.1051/jnwpu/20213951022 | |
Published online | 14 December 2021 |
Target integrity assessment based on image and track information
基于图像和航迹信息的目标完整性评估方法
School of Electronics and Information, Northwestern Polytechnical University, Xi’an 710072, China
Received:
25
June
2021
The rapid and accurate integrity assessment of targets can provide important guarantee and reference for the subsequent decision of the implementer. The current research on target integrity assessment mainly adopts single data source or complex probability model, which leads to inability to balance the needs of accuracy and real-time. In order to solve this problem, a new target integrity assessment method based on image and track information is proposed in this paper. Image texture, corner points and track parameters before and after the execution of the target are used to transform the integrity assessment issue into a classification issue, and a comprehensive assessment result is made by combining various classification results. The experimental results show that the assessment results based on both image and track information reached 97.5%, higher than the evaluation results from a single data source, and the evaluation time was controlled in milliseconds, which not only improved the accuracy rate but also ensured the real-time assessment.
摘要
快速而准确地对任务目标进行完整性评估,是执行者后续决策的重要情报保障和参考依据。针对当前目标完整性评估研究中多采用单一数据源或者复杂概率模型导致无法兼顾准确率和实时性两种需求的问题,提出了基于图像和航迹信息2种数据源的目标完整性评估新方法。通过目标任务执行前后图像纹理、角点以及航迹参数等特征的变化,将完整性评估问题转化为分类问题,并结合多种分类结果进行综合评估。实验结果证明基于图像和航迹信息2种数据源评估结果的准确率达到了97.5%,高于单一数据源评估结果,且评估用时控制在毫秒级,在提高准确率的同时保证了评估的实时性。
Key words: targets integrity assessment / KNN / texture feature / image classification / track information
关键字 : 目标完整性评估 / KNN / 纹理特征 / 图像分类 / 航迹信息
© 2021 Journal of Northwestern Polytechnical University. All rights reserved.
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.