Person identification serves as a core supporting technology in public security, intelligent home applications, and person tracking in different environments. Achieving stable identity matching across environments and locations has become a critical research requirement. Single-modal identification technologies suffer from inherent limitations. The cross-modal fusion method based on millimeter-wave radar and video realizes the complementary advantages of the two modalities. It can effectively support person identification across scenarios, becoming a research hotspot in complex open scenarios. This paper systematically reviews the research progress and core technical systems in this field. Firstly, it sorts out the information extraction methods of millimeter-wave radar features and video visual features, summarizing the extraction ideas of key features such as range-Doppler, micro-Doppler, point cloud, and skeleton. Secondly, it summarizes three fusion strategies (data-level, feature-level, decision-level) and two core alignment methods (spatio-temporal alignment, feature distribution alignment). Then, it introduces typical applications, including intelligent security monitoring, human-computer interaction authentication, and multi-target tracking. It analyzes current challenges such as complex environmental interference, cross-location spatio-temporal alignment, feature distribution shift, and scarcity of large-scale data. Finally, it discusses future research directions, including scene-invariant feature learning, cross-domain alignment optimization, unified feature space construction, and few-shot generalization, providing a comprehensive reference for person identification research.
References
[1]
Yang, Q., Quan, Z., Li, J., Jiang, T., Deng, Z., Qiu, X., et al. (2025) A Survey of Pedestrian Re-Identification Based on Millimeter Wave Radar and Vision Fusion. Journal of Computer and Communications, 13, 64-80. https://doi.org/10.4236/jcc.2025.136005
[2]
Guo, J., Wei, J., Xiang, Y. and Han, C. (2024) Millimeter-Wave Radar-Based Identity Recognition Algorithm Built on Multimodal Fusion. Sensors, 24, Article 4051. https://doi.org/10.3390/s24134051
[3]
Cao, D., Liu, R., Li, H., Wang, S., Jiang, W. and Lu, C.X. (2022) Cross Vision-RF Gait Re-Identification with Low-Cost RGB-D Cameras and Mmwave Radars. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 6, 1-25. https://doi.org/10.1145/3550325
[4]
Shi, Y., Du, L., Chen, X., Liao, X., Yu, Z., Li, Z., et al. (2023) Robust Gait Recognition Based on Deep CNNs with Camera and Radar Sensor Fusion. IEEE Internet of Things Journal, 10, 10817-10832. https://doi.org/10.1109/jiot.2023.3242417
[5]
Wang, S., Mei, L., Liu, R., Jiang, W., Yin, Z., Deng, X., et al. (2025) Multi-Modal Fusion Sensing: A Comprehensive Review of Millimeter-Wave Radar and Its Integration with Other Modalities. IEEE Communications Surveys & Tutorials, 27, 322-352. https://doi.org/10.1109/comst.2024.3398004
[6]
Luo, Y., He, Y., Li, Y., Liu, H., Wang, J. and Gao, F. (2025) A Sliding Window-Based CNN-BiGRU Approach for Human Skeletal Pose Estimation Using Mmwave Radar. Sensors, 25, Article 1070. https://doi.org/10.3390/s25041070
[7]
Liu, R., Yao, T., Shi, R., Mei, L., Wang, S., Yin, Z., et al. (2024) Mission: mmWave Radar Person Identification with RGB Cameras. Proceedings of the 22nd ACM Conference on Embedded Networked Sensor Systems, Hangzhou, 4-7 November 2024, 309-321. https://doi.org/10.1145/3666025.3699340
[8]
Chen, Y. and Cheng, K. (2024) BiCLR: Radar-Camera-Based Cross-Modal Bi-Contrastive Learning for Human Motion Recognition. IEEE Sensors Journal, 24, 4102-4119. https://doi.org/10.1109/jsen.2023.3344789
[9]
Singh, A.D., Sandha, S.S., Garcia, L. and Srivastava, M. (2019) RadHAR: Human Activity Recognition from Point Clouds Generated through a Millimeter-Wave Radar. Proceedings of the 3rd ACM Workshop on Millimeter-Wave Networks and Sensing Systems, Los Cabos, 25 October 2019, 51-56. https://doi.org/10.1145/3349624.3356768
[10]
Li, Z., Le Kernec, J., Abbasi, Q., Fioranelli, F., Yang, S. and Romain, O. (2023) Radar-based Human Activity Recognition with Adaptive Thresholding towards Resource Constrained Platforms. Scientific Reports, 13, Article No. 3473. https://doi.org/10.1038/s41598-023-30631-x
[11]
Huang, T., Liu, G., Li, S. and Liu, J. (2023) RPCRS: Human Activity Recognition Using Millimeter Wave Radar. 2022 IEEE 28th International Conference on Parallel and Distributed Systems (ICPADS), Nanjing, 10-12 January 2023, 122-129. https://doi.org/10.1109/icpads56603.2022.00024
[12]
Shan, L., Zhang, R., Chilukoti, S.V., Zhang, X., Lee, I. and Hei, X. (2024) IdentityKD: Identity-Wise Cross-Modal Knowledge Distillation for Person Recognition via Mmwave Radar Sensors. Proceedings of the 6th ACM International Conference on Multimedia in Asia, Auckland, 3-6 December 2024, 1-7. https://doi.org/10.1145/3696409.3700254
[13]
Yang, Z. and Yang, Y. (2025) Wisk: A Lightweight Multimodal Human Activity Recognition Method Based on WiFi Channel State Information and Video Skeleton Images. Concurrency and Computation: Practice and Experience, 37, e70383. https://doi.org/10.1002/cpe.70383
[14]
Cao, P., Xia, W., Ye, M., Zhang, J. and Zhou, J. (2018) Radar‐ID: Human Identification Based on Radar Micro‐Doppler Signatures Using Deep Convolutional Neural Networks. IET Radar, Sonar & Navigation, 12, 729-734. https://doi.org/10.1049/iet-rsn.2017.0511
[15]
Hafner, F.M., Bhuiyan, A., Kooij, J.F.P. and Granger, E. (2019) RGB-Depth Cross-Modal Person Re-Identification. 2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), 18-21 September 2019, 1-8. https://doi.org/10.1109/avss.2019.8909838
[16]
Ahuja, K., Jiang, Y., Goel, M. and Harrison, C. (2021) Vid2Doppler: Synthesizing Doppler Radar Data from Videos for Training Privacy-Preserving Activity Recognition. Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems, Yokohama, 8-13 May 2021, 1-10. https://doi.org/10.1145/3411764.3445138
[17]
Xie, S., Wang, C., Yang, X., Wan, Y., Zeng, T. and Liu, Z. (2022) Millimeter-Wave Radar Target Detection Based on Inter-Frame DBSCAN Clustering. 2022 IEEE 22nd International Conference on Communication Technology (ICCT), Nanjing, 11-14 November 2022, 1703-1708. https://doi.org/10.1109/icct56141.2022.10072664
[18]
Shao, T., Du, Z., Li, C., Wu, T. and Wang, M. (2024) Fast Human Action Recognition via Millimeter Wave Radar Point Cloud Sequences Learning. Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, Boise, 21-25 October 2024, 2024-2033. https://doi.org/10.1145/3627673.3679787
[19]
Zong, M., Wu, J., Zhu, Z. and Ni, J. (2024) A Method for Target Detection Based on Mmw Radar and Vision Fusion. arXiv:2403.16476.
[20]
Wang, K., He, R., Wang, W., Wang, L. and Tan, T. (2013) Learning Coupled Feature Spaces for Cross-Modal Matching. 2013 IEEE International Conference on Computer Vision, Sydney, 1-8 December 2013, 2088-2095. https://doi.org/10.1109/iccv.2013.261
[21]
Wei, J., Xu, X., Yang, Y., Ji, Y., Wang, Z. and Shen, H.T. (2020) Universal Weighting Metric Learning for Cross-Modal Matching. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, 13-19 June 2020, 6420-6429. https://doi.org/10.1109/cvpr42600.2020.01302
[22]
Yang, S., Xu, Z., Wang, K., You, Y., Yao, H., Liu, T., et al. (2023) BiCro: Noisy Correspondence Rectification for Multi-Modality Data via Bi-Directional Cross-Modal Similarity Consistency. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, 17-24 June 2023, 19883-19892. https://doi.org/10.1109/cvpr52729.2023.01904
[23]
Liong, V.E., Lu, J., Tan, Y. and Zhou, J. (2017) Deep Coupled Metric Learning for Cross-Modal Matching. IEEE Transactions on Multimedia, 19, 1234-1244. https://doi.org/10.1109/tmm.2016.2646180
[24]
Wei, J., Xu, X., Wang, Z. and Wang, G. (2021) Meta Self-Paced Learning for Cross-Modal Matching. Proceedings of the 29th ACM International Conference on Multimedia, Virtual Event, 20-24 October 2021, 1613-1621. https://doi.org/10.1145/3474085.3475451
[25]
Yao, Y., Zhang, H., Xia, P., Liu, C., Geng, F., Bai, Z., et al. (2023) Mmsignature: Semi-Supervised Human Identification System Based on Millimeter Wave Radar. Engineering Applications of Artificial Intelligence, 126, Article 106939. https://doi.org/10.1016/j.engappai.2023.106939
[26]
Deng, K., Zhao, D., Han, Q., Zhang, Z., Wang, S., Zhou, A., et al. (2023) Midas: Generating mmWave Radar Data from Videos for Training Pervasive and Privacy-Preserving Human Sensing Tasks. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 7, 1-26. https://doi.org/10.1145/3580872
[27]
Hafner, F.M., Bhuyian, A., Kooij, J.F.P. and Granger, E. (2022) Cross-Modal Distillation for RGB-Depth Person Re-Identification. Computer Vision and Image Understanding, 216, Article 103352. https://doi.org/10.1016/j.cviu.2021.103352
[28]
Janakaraj, P., Jakkala, K., Bhuyan, A., Sun, Z., Wang, P. and Lee, M. (2019) STAR: Simultaneous Tracking and Recognition through Millimeter Waves and Deep Learning. 2019 12th IFIP Wireless and Mobile Networking Conference (WMNC), Paris, 11-13 September 2019, 211-218. https://doi.org/10.23919/wmnc.2019.8881354
Vishwakarma, S., Li, W., Tang, C., Woodbridge, K., Adve, R. and Chetty, K. (2023) SimHumalator: An Open Source End-to-End Radar Simulator for Human Activity Recognition. IEEE Aerospace and Electronic Systems Magazine, 38, 2-21. https://doi.org/10.1109/MAES.2021.3138948
[31]
Chen, A., Wang, X., Shi, K., Huo, Y., Chen, J. and Ye, Q. (2025) Toward Weather-Robust 3D Human Body Reconstruction: Millimeter-Wave Radar-Based Dataset, Benchmark, and Multi-Modal Fusion. IEEE Transactions on Circuits and Systems for Video Technology, 35, 273-286. https://doi.org/10.1109/tcsvt.2024.3461960
[32]
Choi, J., Hor, S., Yang, S. and Arbabian, A. (2025) Mvdoppler-Pose: Multi-Modal Multi-View Mmwave Sensing for Long-Distance Self-Occluded Human Walking Pose Estimation. 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, 10-17 June 2025, 1-8. https://doi.org/10.1109/cvpr52734.2025.02584
[33]
Huan, S., Wang, Z., Wang, X., Wu, L., Yang, X., Huang, H., et al. (2023) A Lightweight Hybrid Vision Transformer Network for Radar-Based Human Activity Recognition. Scientific Reports, 13, Article No. 17996. https://doi.org/10.1038/s41598-023-45149-5
