基于交互式多模型的目标跟踪算法研究
关键词：目标跟踪、交互式多模型、机动运动模型 、卡尔曼滤波
毕业论文设计说明书（论文）外文摘要
Title Research on target tracking algorithm based on IMM
Abstract
In recent years, the maneuvering target tracking has been one of the hotspots and difficulties in target tracking research. As a new data fusion algorithm, due to its excellent tracking effect and wide tracking bandwidth, the interacting multiple model (IMM) algorithm get a lot of attention in recent years. This paper introduces and analyzes for the IMM algorithm, and introduces the application of the most extensive maneuvering motion model, using multiple models to describe the movement of maneuvering targets, such as constant velocity (CV), constant acceleration (CA), constant rate turn (CT) and current statistics (CS) and many other models. The following experiments are carried out:(1) Based on "current" statistical model (CS) of the Kalman filter. (2) Based on the uniform (CV), constant acceleration (CA) model IMM Kalman filter. （3） Based on uniform (CV), "current" statistical (CS) model IMM Kalman filter. （4） Based on uniform (CV), constant rate turn (CT) model IMM Kalman filter. （5） Based on uniform (CV), constant acceleration (CA), constant rate turn(CT) model IMM Kalman filter. （6）Based on the uniform (CV), constant acceleration (CS), a constant rate of turn (CT) model IMM Kalman filter.
Keywords: Target tracking, interactive multi-model, motor sports model, Kalman filter
目 次
1 绪论 1
1.1 课题研究背景及意义 1
1.2 国内外研究现状 1
1.3 本文结构 2
2 目标跟踪模型及卡尔曼滤波 3
2.1 目标跟踪模型 3
2.2 目标跟踪卡尔曼滤波 8
3 交互式多模型（IMM）算法及IMM算法的参数设置 10
3.1 交互式多模型（IMM）算法 10
3.2 IMM算法的参数设置 12
4 仿真实验分析 14
4.1 IMMCVCA仿真实验结果 16
4.2 IMMCVCS与CS的计算结果比较 25
4.3 IMMCVCS与IMMCVCA的计算结果比较 31
4.4 IMMCVCS与IMMCVCT的计算结果比较 34
4.5 IMMCVCS与IMMCVCSCT的计算结果比较 37
4.6 IMMCVCSCT与IMMCVCACT的计算结果比较 38