电子测量与仪器学报

税翔,陈丹,张衡,赵沛岩.基于红外传感阵列的目标运动方向探测与识别研究[J].电子测量与仪器学报,2022,36(12):37-44

基于红外传感阵列的目标运动方向探测与识别研究

Research on target moving direction detection andrecognition based on infrared sensor array

DOI：

中文关键词: 红外传感器阵列 K-means 聚类算法目标运动方向 KNN 分类器机器人动态避障

英文关键词:infrared sensor array K-means clustering algorithm target motion direction KNN classifier robot dynamic avoidance

基金项目:榆林市科技计划(2019 146)、西安理工大学研究生培育项目(252051834)资助

作者	单位
税翔	1.西安理工大学自动化与信息工程学院
陈丹	1.西安理工大学自动化与信息工程学院
张衡	1.西安理工大学自动化与信息工程学院
赵沛岩	1.西安理工大学自动化与信息工程学院

Author	Institution
Shui Xiang	1.School of Automation and Information Engineering, Xi′an University of Technology
Chen Dan	1.School of Automation and Information Engineering, Xi′an University of Technology
Zhang Heng	1.School of Automation and Information Engineering, Xi′an University of Technology
Zhao Peiyan	1.School of Automation and Information Engineering, Xi′an University of Technology

摘要点击次数: 1513

全文下载次数: 1307

中文摘要:

针对单个红外传感器无法获取障碍物距离之外的其他信息,本文设计了红外传感器阵列检测系统,不仅能探测运动目标距离信息还能识别目标的运动方向。当运动目标通过红外阵列时,该系统检测到红外反射回波信号转换为目标距离信息后, 采用 K-means 聚类把运动目标信号从背景噪声中分离出来,再经过最小二乘拟合提取目标运动方向特征,最后通过分类器对 8 种不同运动方向进行有效感知分类。实验结果表明,该方法能够成功识别出目标的 8 种运动方向,当分类器参数 K 取值为 5 时,平均识别准确率达到 0. 83 以上,试验结果验证了本文提出的基于红外传感器阵列对目标运动方向进行准确探测与识别的可行性,为实现多模态融合机器人动态避障奠定了基础。

英文摘要:

As a single infrared sensor cannot obtain other information beyond the distance of obstacles, this paper designs an infrared sensor array detection system, which not only detects the distance information of moving targets, but also identifies the moving direction of the target. When the moving target passes through the infrared array, the system detects that the infrared reflected echo signal is converted into the target distance information, uses K-means clustering to separate the moving target signal from the background noise, and then extracts the target motion direction features through least square fitting. Finally, eight different motion directions are effectively perceived and classified through the classifier. The experimental results show that the method can successfully identify eight moving directions of the target. When the classifier parameter K is 5, the average recognition accuracy is more than 0. 83. The experimental results verify the feasibility of the proposed method based on infrared sensor array to accurately detect and identify the moving direction of the target, which lays a foundation for realizing dynamic obstacle avoidance of multimodal fusion robot.

查看全文查看/发表评论下载PDF阅读器