针对毫米波雷达人员目标稀疏点云的聚类算法

doi:10.3778/j.issn.1002-8331.2309-0286

摘要/Abstract

摘要： 毫米波雷达室内人员目标检测存在点云稀疏且有零散噪声点的问题，传统基于密度聚类算法受参数影响不能适应多变的目标点云数据，无法实现精准聚类。对此进行研究提出了一种针对人员目标稀疏点云的聚类算法。建立平均局部密度信息熵和邻域半径（Eps）的关系；利用DBSCAN算法识别零散噪声点并去除；利用每个点的局部密度和相对距离的乘积得到聚类中心权值，并画出降序图；在降序图中引入自适应指数衰减函数曲线，从而自动获得聚类中心，并完成聚类。通过实验验证，并与CFSFDP算法和DBSCAN算法进行对比，结果表明，提出的算法具有较高的ARI、AMI、NMI、FMI值，获得较好的聚类效果，适用于毫米波雷达室内检测场景。

关键词: 毫米波雷达, 点云聚类, 稀疏点云, 目标检测

Abstract: The indoor personnel target detection using millimeter-wave radar often encounters issues with sparse point clouds and scattered noise points. Traditional density-based clustering algorithms are sensitive to parameters and cannot adapt well to the varying target point cloud data, making precise clustering challenging. To address this, a clustering algorithm tailored for sparse point clouds of personnel targets is proposed in this research. Firstly, a relationship is established between the average local density information entropy and the neighborhood radius (Eps). Secondly, the DBSCAN algorithm is employed to identify and remove scattered noise points. Subsequently, the clustering center weight is calculated using the product of local density and relative distance of each point, and a descending graph is plotted. Then, an adaptive exponential decay function curve is introduced into the descending graph to automatically obtain cluster centers and complete the clustering process. Experimental validation is conducted, and comparisons are made with the CFSFDP algorithm and the DBSCAN algorithm. The results demonstrate that the proposed algorithm achieves higher ARI, AMI, NMI, and FMI values, indicating better clustering performance, and is suitable for millimeter-wave radar indoor detection scenarios.

Key words: millimeter-wave radar, point cloud clustering, sparse point cloud, target detection

杨冬, 曾春艳, 郝丹妮, 万相奎. 针对毫米波雷达人员目标稀疏点云的聚类算法[J]. 计算机工程与应用, 2025, 61(3): 359-366.

YANG Dong, ZENG Chunyan, HAO Danni, WAN Xiangkui. Clustering Algorithm for Sparse Point Clouds of Personnel Targets in Millimeter-Wave Radar[J]. Computer Engineering and Applications, 2025, 61(3): 359-366.

参考文献

[1] NINOS A, HASCH J, HEIZMANN M, et al. Radar-based robust people tracking and consumer applications[J]. IEEE Sensors Journal, 2022, 22(4): 3726-3735.
[2] 李小柳. 车载4D毫米波雷达的目标检测关键技术研究[D]. 南京: 南京理工大学, 2021.
LI X L. Key technologies research on target detection of vehicle-mounted 4D millimeter-wave radar[D]. Nanjing: Nanjing University of Science and Technology, 2021.
[3] ZENG X, SHI Y, ZHOU A. Multi-HAR: human activity recognition in multi-person scenes based on mmWave sensing[C]//Proceedings of the 2022 IEEE 8th International Conference on Computer and Communications (ICCC), Chengdu, 2022: 1789-1793.
[4] HUANG T, LIU G, LI S, et al. RPCRS: human activity recognition using millimeter wave radar[C]//Proceedings of the 2022 IEEE 28th International Conference on Parallel and Distributed Systems (ICPADS), Nanjing, 2023: 122-129.
[5] WANG M, WANG F, LIU C, et al. DBSCAN clustering algorithm of millimeter wave radar based on multi frame joint[C]//Proceedings of the 2022 4th International Conference on Intelligent Control, Measurement and Signal Processing (ICMSP), Hangzhou, 2022: 1049-1053.
[6] SONG P, MEI L, CHENG H. Human semantic segmentation using millimeter-wave radar sparse point clouds[C]//Proceedings of the 2023 26th International Conference on Computer Supported Cooperative Work in Design (CSCWD), Rio de Janeiro, Brazil, 2023: 1275-1280.
[7] SHEN Z, NUNEZ-YANEZ J, DAHNOUN N. Multiple human tracking and fall detection real-time system using millimeter-wave radar and data fusion[C]//Proceedings of the 2023 12th Mediterranean Conference on Embedded Computing (MECO), Budva, Montenegro, 2023: 1-6.
[8] LI W, CHEN R, WU Y, et al. Indoor positioning system using a single-chip millimeter wave radar[J]. IEEE Sensors Journal, 2023, 23(5): 5232-5242.
[9] CHEN H, ZHAO C, ZHAO C, et al. LSS-target intelligent detection method suitable for complex geographical environment[C]//Proceedings of the 2022 3rd China International SAR Symposium (CISS), Shanghai, 2022: 1-5.
[10] ESTER M, KRIEGEL H P, SANDER J, et al. A density-based algorithm for discovering clusters in large spatial databases with noise[C]//Proceedings of the Second International Conference on Knowledge Discovery and Data Mining, 1996: 226-231.
[11] 龚伟. 基于毫米波雷达的人数统计、姿态识别及跟踪系统的设计和实现[D]. 武汉: 华中科技大学, 2020.
GONG W. Design and implementation of a people counting, pose recognition, and tracking system based on millimeter-wave radar[D]. Wuhan: Huazhong University of Science and Technology, 2020.
[12] ZHOU H, ZHANG G, KONG L, et al. Random forest based adaptive DBSCAN for reducing noise in mmwave radar point clouds[C]//Proceedings of the 2022 IEEE 21st International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC), Toronto, ON, Canada, 2022.
[13] 鞠夕强, 孟文, 孟祥印, 等. 一种改进的毫米波雷达聚类算法[J]. 科学技术与工程, 2021, 21(20): 8537-8543.
JU X Q, MENG W, MENG X Y, et al. An improved clustering algorithm for millimeter wave radar[J]. Science Technology and Engineering, 2021, 21(20): 8537-8543.
[14] RODRIGUEZ A, LAIO A. Clustering by fast search and find of density peaks[J]. Science, 2014, 344(6191): 1492-1496.
[15] 王军华, 李建军, 李俊山, 等. 自适应快速搜索密度峰值聚类算法[J]. 计算机工程与应用, 2019, 55(24): 122-127.
WANG J H, LI J J, LI J S, et al. Adaptive fast search density peak clustering algorithm[J]. Computer Engineering and Applications, 2019, 55(24): 122-127.
[16] 王芙银, 张德生, 张晓. 结合鲸鱼优化算法的自适应密度峰值聚类算法[J]. 计算机工程与应用, 2021, 57(3): 94-102.
WANG F Y, ZHANG D S, ZHANG X. Adaptive density peaks clustering algorithm combining with whale optimization algorithm[J]. Computer Engineering and Applications, 2021, 57(3): 94-102.
[17] DE VARGAS R R, BEDREGAL B R C. A way to obtain the quality of a partition by adjusted rand index[C]//Proceedings of the 2013 2nd Workshop-School on Theoretical Computer Science, Rio Grande, 2013: 67-71.
[18] 徐童童, 解滨, 张喜梅, 等. 自适应聚类中心策略优化的密度峰值聚类算法[J]. 计算机工程与应用, 2023, 59(21): 91-101.
XU T T, XIE B, ZHANG X M, et al. Density peak clustering algorithm optimized by adaptive clustering center strategy[J]. Computer Engineering and Applications, 2023, 59(21): 91-101.
[19] AMELIO A, PIZZUTI C. Is normalized mutual information a fair measure for comparing community detection methods?[C]//Proceedings of the 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, Paris France, 2015: 1584-1585.
[20] GUO B, TIAN L, ZHANG J, et al. A clustering algorithm based on joint kernel density for millimeter wave radio channels[C]//Proceedings of the 2019 13th European Conference on Antennas and Propagation (EuCAP), 2019: 1-5.