| 引用本文: | 黄黎斌， 许 红， 倪柳柳， 邢逸舟， 全英汇. 基于多维度体系和组合权重的雷达多目标跟踪评估模型[J]. 雷达科学与技术, 2024, 22(6): 657-671.[点击复制] |
| HUANG Libin, XU Hong, NI Liuliu, XING Yizhou, QUAN Yinghui. Radar Multiple⁃Object Tracking Performance Evaluation Model Based onMultiple⁃Dimensional System and Combined Weight[J]. Radar Science and Technology, 2024, 22(6): 657-671.[点击复制] |
|
| 摘要: |
| 针对目前雷达多目标跟踪的评估指标单一化、只能对特定类型关联算法进行评估和单一权重计算导致评估偏差等问题，本文提出了基于宏观和精细的多维度指标体系并结合主客观组合权重，构建雷达多目标跟踪评估模型。首先，分别从多目标跟踪的航迹整体维度与航迹中点迹的精细变化角度入手，提出宏观与精细两类指标对目标跟踪结果进行多维度的分析；然后，针对不同的数据关联方式采用软硬两种决策来对目标与实际航迹进行匹配并计算各指标值；最后，分别通过G1序列法和CRITIC法计算指标的主客观权重，再通过最小二乘法将主客观权重融合为组合权重，将其代入优化模型得到最终的多目标跟踪评估结果。实验结果表明，该模型可以在稀疏、密集等多目标复杂运动场景下对多目标跟踪做出灵活全面的评估。 |
| 关键词: 宏观与精细指标 组合权重 数据关联 软硬决策 |
| DOI：DOI:10.3969/j.issn.1672-2337.2024.06.009 |
| 分类号:TN953 |
| 基金项目:国家自然科学基金（No.62301408）； 博士后科学基金（No.2022M722503） |
|
| Radar Multiple⁃Object Tracking Performance Evaluation Model Based onMultiple⁃Dimensional System and Combined Weight |
|
HUANG Libin, XU Hong, NI Liuliu, XING Yizhou, QUAN Yinghui
|
|
1. Hangzhou Institute of Technology, Xidian University, Hangzhou 311231, China;2. Unit 95859 of PLA, Jiuquan 735018, China;3. Xidian University, Xi’an 710071, China
|
| Abstract: |
| Aiming to address issues such as the reliance on a single evaluation index for radar multi?target tracking and the bias caused by using only one specific type of association algorithm and weight calculation, a comprehensive radar multiple?object tracking evaluation model is proposed in this paper. The model is based on macro and fine multi?dimensional index system, and incorporates both subjective and objective weight. Firstly, two types of indexes are introduced to analyze the target tracking results from the perspectives of overall track dimension and fine changes in point tracks. Secondly, for different data association methods, soft and hard decisions are employed to match targets with actual tracks and calculate each index value accordingly. Finally, to ensure comprehensive evaluation results, subjective weights and objective weights for indicators are determined using G1 sequence method and CRITIC method respectively. Then, these weights are fused into combined weights through least square method before being applied in an optimization model to obtain final multiple?object tracking evaluation results. The experimental findings demonstrate that this model can flexibly and comprehensively evaluate multiple?object tracking performance across various scenarios including sparse and dense environments. |
| Key words: macro and fine indicators combined weight data association soft and hard decisions |
