Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Automation and Machine Learning
  4. Vol 6, Issue 1, 2025

Micro motion detection system for traffic target classification

Download as PDF

DOI: 10.23977/autml.2025.060107 | Downloads: 9 | Views: 507

Author(s)

Zhangxiaoyu Wu 1, Jiacong Guo 1, Hang Zhou 1

Affiliation(s)

1 School of Mechanical and Electrical Engineering, Wuhan University of Technology, Wuhan, 430070, China

Corresponding Author

Zhangxiaoyu Wu

ABSTRACT

The main way of traffic monitoring is through cameras, but it is easily affected by external lighting. The ground is subject to various natural and human movements, which generate small vibration signals. Using micro motion signals to perceive the environment is a new detection technology. This research design consists of micro motion acquisition hardware, data processing and time-frequency domain feature extraction algorithms, and machine learning based object classification algorithms to achieve scene perception of people and vehicles in smart transportation, and can also be used for security detection. After collecting field data, the 2935 effective slices extracted by the algorithm were trained and tested. The average accuracies of the MLP, SVM, GBT, and RF models were 95.808%, 91.039%, 95.570%, and 95.468%, respectively. The MLP (Multi-Layer Perceptron) with shallow neural network structure is the optimal model, with the highest average recognition rate and the smallest standard deviation. The experimental results show that this system is not affected by environmental factors such as weather, light intensity, and electromagnetic fields. It is compact and easy to deploy, with strong concealment, small data volume, and high reliability.

KEYWORDS

Intelligent transportation, micro motion detection, time-frequency characteristics, multi-layer perceptron

CITE THIS PAPER

Zhangxiaoyu Wu, Jiacong Guo, Hang Zhou, Micro motion detection system for traffic target classification. Automation and Machine Learning (2025) Vol. 6: 58-66. DOI: http://dx.doi.org/10.23977/autml.2025.060107.

REFERENCES

[1] Xiaoyi W, Yunhua L, Zhongjun Y U, et al. Multi-channel radar target micro-motion feature classification method based on EfficientNet[J].Systems Engineering & Electronics, 2024, 46(9).DOI:10.12305/j.issn.1001-506X.2024.09.11.
[2] Richter Y, Balal N. High-Resolution Millimeter-Wave Radar for Real-Time Detection and Characterization of High-Speed Objects with Rapid Acceleration Capabilities[J].Electronics, 2024, 13(10):13.DOI:10.3390/electronics13101961.
[3] Ahmad B I, Harman S, Godsill S.A Bayesian track management scheme for improved multi‐target tracking and classification in drone surveillance radar[J].IET Radar, Sonar & Navigation (Wiley-Blackwell), 2024, 18(1). DOI:10.1049/rsn2.12458.
[4] Wang X, Zhang M, Li B.Fusion Network Based on Motion Learning and Image Feature Representation for Micro-Expression Recognition[C]//Chinese Conference on Pattern Recognition and Computer Vision, (PRCV).Springer, Singapore, 2025.DOI:10.1007/978-981-97-8795-1_37.
[5] Voronin V, Zhdanova M, Semenishchev E,et al.Action recognition algorithm from multimodal images for human-robot collaboration systems[J].Proceedings of SPIE, 2023, 12621(000):9.DOI:10.1117/12.2678112.
[6] Voronin V, Zhdanova M, Tokareva O,et al.A multimodal visual guided robot collaborative system based on the classification of multi-class human motion[J].Proceedings of SPIE, 2023, 12766(000):7.DOI:10.1117/12.2691154.
[7] Huan S, Wu L, Zhang Z Y C.Radar Human Activity Recognition with an Attention-Based Deep Learning Network[J].sensors, 2023, 23(6). DOI:10.3390/s23063185.
[8] Hassan S, Wang X, Ishtiaq S,et al.Human Activity Classification Based on Dual Micro-Motion Signatures Using Interferometric Radar[J].Remote Sensing, 2023, 15(7).DOI:10.3390/rs15071752.
[9] Ryu B, Kwak D.Site effects and micro-zonation 1 Development of Nonlinear Site Amplification Model Based on Average Shear-wave Velocity of Soil Layer and Bedrock Depth[J].Japanese Geotechnical Society Special Publication, 2024, 10(28):5.DOI:10.3208/jgssp.v10.OS-17-05.
[10] Ashkenazi I, Benady A, Zaken S B,et al.Radiological Comparison of Canal Fill between Collared and Non-Collared Femoral Stems: A Two-Year Follow-Up after Total Hip Arthroplasty[J].Journal of Imaging, 2024, 10(5). DOI:10. 3390/jimaging10050099.
[11] Ceylan N, Snmez E, Kaar S. Cost effective detection of uneven mounting fault in rotary wing drone motors with a CNN based method[J].Signal, Image and Video Processing, 2024, 18(11):8049-8059.DOI:10.1007/s11760-024-03450-4.
[12] Ahmad A, Li Z, Tariq I,et al.IDSSCNN-XgBoost: Improved Dual-Stream Shallow Convolutional Neural Network Based on Extreme Gradient Boosting Algorithm for Micro Expression Recognition[J].Computers, Materials & Continua, 2025, 82(1).DOI:10.32604/cmc.2024.055768.
[13] Chen W S, Chen X L,J. LiuQ.B. WangX.F. LuY.F. Huang.Detection and recognition of UA targets with multiple sensors[J].The Aeronautical journal, 2023, 127(Feb. TN.1308):167-192.DOI:10.1017/aer.2022.50.
[14] Ashkenazi I, Benady A, Zaken S B,et al. Radiological Comparison of Canal Fill between Collared and Non-Collared Femoral Stems: A Two-Year Follow-Up after Total Hip Arthroplasty[J]. Journal of Orthopaedic Surgery and Research, 2024.

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 3722
Visits: 166915

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.