Skip to main content
SpringerLink
Log in

Deep anomaly detection in expressway based on edge computing and deep learning

  • Original Research
  • Published:
Journal of Ambient Intelligence and Humanized Computing Aims and scope Submit manuscript

Abstract

In order to improve the real-time efficiency of expressway operation monitoring and management, the anomaly detection in intelligent monitoring network of expressway based on edge computing and deep learning is studied. The video data collected by the camera equipment in the intelligent monitoring network structure of the expressway is transmitted to the edge processing server for screening and then sent to the convolutional neural network. The convolutional neural network uses the multi-scale optical flow histogram method to preprocess the video data after the edge calculation to generate the training sample set and send it to the AlexNet model for feature extraction. SVM classifier model is used to train the feature data set and input the features of the test samples into the trained SVM classifier model to realize the anomaly detection in the intelligent monitoring network of expressway. The research method is used to detect the anomaly in an intelligent monitoring network of an expressway. The experimental results show that the method has better detection effect. The miss rate has reduced by 20.34% and 40.76% on average compared with machine learning method and small block learning method, respectively. The false positive rate has reduced by 27.67% and 21.77%, and the detection time is greatly shortened.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

Data availability

All data and material generated or analyzed during this study are included in this published article.

Code availability

All code generated or used during the study are available from the corresponding author by request.

References

  • Audebert N, Saux BL, Lefèvre S (2017) Segment-before-detect: vehicle detection and classification through semantic segmentation of aerial images. Remote Sens 9(4):368

    Article  Google Scholar 

  • Chen L, Ding Q, Zou Q, Chen Z, Li L (2020) DenseLightNet: a light-weight vehicle detection network for autonomous driving. IEEE Trans Ind Electron 99:1–1

    Google Scholar 

  • Daniel V, Uday K, Amarda S (2018) Deep learning improves antimicrobial peptide recognition. Bioinformatics 34(16):2740–2747

    Article  Google Scholar 

  • Deng Z, Sun H, Zhou S, Zhao J, Zou H (2017) Toward fast and accurate vehicle detection in aerial images using coupled region-based convolutional neural networks. IEEE J Sel Top Appl Earth Obs Remote Sens 10(8):3652–3664

    Article  Google Scholar 

  • Dong Z, Wang M, Wang Y, Zhu Y, Zhang Z (2020) Object detection in high resolution remote sensing imagery based on convolutional neural networks with suitable object scale features. IEEE Trans Geosci Remote Sens 58(3):2104–2114

    Article  Google Scholar 

  • Eric LF, Rishi R, Stefan BW (2016) Deep learning approach to passive monitoring of the underwater acoustic environment. J Acoust Soc Am 140(4):3351–3351

    Google Scholar 

  • Gao Z, Ji H, Mei T, Ramesh B, Liu X (2019) EOVNet: earth-observation image-based vehicle detection network. IEEE J Sel Top Appl Earth Observ Remote Sens 12(9):3552–3561

    Article  Google Scholar 

  • Harsha SS, Anne KR (2016) Gaussian mixture model and deep neural network based vehicle detection and classification. Int J Adv Comput Sci Appl 7(9):17–25

    Google Scholar 

  • Holden D, Saito J, Komura T (2016) A deep learning framework for character motion synthesis and editing. ACM Trans Graph 35(4):1–11

    Article  Google Scholar 

  • Ji Q, Lu Z, Chi R (2016) Real-time multi-feature based fire flame detection in video. IET Image Proc 11(1):31–37

    Google Scholar 

  • Jiang N, Chen J, Zhou R, Wu C, Chen H, Zheng J, Wan T (2020a) PAN: pipeline assisted neural networks model for data-to-text generation in social internet of things. Inf Sci 530:167–179

    Article  Google Scholar 

  • Jiang N, Tian F, Li J, Yuan X, Zheng J (2020b) MAN: mutual attention neural networks model for aspect-level sentiment classification in SIoT. IEEE Internet Things J 7(4):2901–2913

    Article  Google Scholar 

  • Jiang N, Xu D, Zhou J, Yan H, Wan T, Zheng J (2020c) Toward optimal participant decisions with voting-based incentive model for crowd sensing. Inf Sci 512:1–17

    Article  Google Scholar 

  • Jin YF, Gao Y (2016) Optimal piecewise real-time pricing strategy for smart grid. Comput Simul 33(4):171–175

    Google Scholar 

  • Koga Y, Miyazaki H, Shibasaki R (2020) A method for vehicle detection in high-resolution satellite images that uses a region-based object detector and unsupervised domain adaptation. Remote Sens 12(3):575

    Article  Google Scholar 

  • Li Y, Wang ZW, Xu SF (2016) Image encryption algorithm based on multiple-parameter fractional Fourier and Arnold transforms. J China Acad Electron Inform Technol 11(2):164–168

    MathSciNet  Google Scholar 

  • Li S, Lin J, Li G, Bai T, Wang H, Pang Y (2018) Vehicle type detection based on deep learning in traffic scene. Proced Comput Sci 131:564–572

    Article  Google Scholar 

  • Lu DM (2017) Strong consistency of kernel estimator of density function for ALNQD sequence. J Jilin Univ (Sci Ed) 5(06):1461–1464

    MathSciNet  MATH  Google Scholar 

  • Mansour A, Hassan A, Hussein WM et al (2019) Automated vehicle detection in satellite images using deep learning. IOP Conf Ser 610(1):012–027

    Article  Google Scholar 

  • Nie S, Zheng M, Ji Q (2018) The deep regression bayesian network and its applications: probabilistic deep learning for computer vision. IEEE Signal Process Mag 35(1):101–111

    Article  Google Scholar 

  • Rajeev R, Swami S, Ankan B (2018) Deep learning for understanding faces: machines may be just as good, or better, than humans. IEEE Signal Process Mag 35(1):66–83

    Article  Google Scholar 

  • Ruo MY, Ling S (2016) Blind image blur estimation via deep learning. IEEE Trans Image Process 25(4):1910–1921

    MathSciNet  MATH  Google Scholar 

  • Shen J, Liu N, Sun H, Zhou H (2019) Vehicle detection in aerial images based on lightweight deep convolutional network and generative adversarial network. IEEE Access 7:148119–148130

    Article  Google Scholar 

  • Sheng M, Liu C, Zhang Q, Lou L, Zhen Y (2018) Vehicle detection and classification using convolutional neural networks. In: 2018 IEEE 7th Data Driven Control and Learning Systems Conference (DDCLS), pp. 581–587.

  • Sheng M, Liu C, Zhang Q, Lou L, Zheng Y (2018) Vehicle detection and classification using convolutional neural networks. In: 2018 IEEE 7th Data Driven Control and Learning Systems Conference (DDCLS), pp. 581–587.

  • Thanh N, Vy B, Van VL (2017) Automatic phase aberration compensation for digital holographic microscopy based on deep learning background detection. Opt Express 25(13):15043–15057

    Article  Google Scholar 

  • Wang JG, Zhou L, Pan Y, Lee S, Song Z, Han BS, Saputra VB (2016) Appearance-based brake-lights recognition using deep learning and vehicle detection. In: 2016 IEEE Intelligent Vehicles Symposium (IV), pp. 815–820.

  • Xu ZH, Huang WQ, Wang Y (2019a) Multi-class vehicle detection in surveillance video based on deep learning. J Comput Appl 39(3):700–705

  • Xu Y, Li D, Wang Z (2019b) A deep learning method based on convolutional neural network for automatic modulation classification of wireless signals. Wireless Netw 25(7):3735–3746

    Article  Google Scholar 

  • Yang J, Li Y, Zhang Q, Ren Y (2019) Surface vehicle detection and tracking with deep learning and appearance feature. In: 2019 5th International Conference on Control, Automation and Robotics (ICCAR), pp. 276–280.

  • Yu S, Wu Y, Li W, Song Z, Zeng W (2017) A model for fine-grained vehicle classification based on deep learning. Neurocomputing 257:97–103

    Article  Google Scholar 

  • Yuan G, Zhong FQ (2016) On computing the edge-connectivity of an uncertain graph. IEEE Trans Fuzzy Syst 24(4):981–991

    Article  Google Scholar 

  • Zhang R, Wang J, Chen ZX (2018) Wireless digital communication technology for parallel DC-DC converter. J Power Supply 16(3):44–47

    Google Scholar 

  • Zhao GZ, Liu YJ, Shi YC (2018) Real-time assessment of the cross-task mental workload using physiological measures during anomaly detection. IEEE Trans Hum-Mach Syst 48(2):149–160

    Article  Google Scholar 

  • Zhou Y, Cheung NM (2016) Vehicle classification using transferable deep neural network features. Comput Vision Pattern Recognit. arXiv:1601.01145

  • Zhou Y, Nejati H, Do TT, Cheung N M, Cheah L (2016) Image-based vehicle analysis using deep neural network: a systematic study. In: 2016 IEEE international conference on digital signal processing (DSP), pp 276–280

Download references

Acknowledgements

We are grateful for Yong Hu, Qi Liu and Fei Du from East China Jiaotong University for their constructive suggestions on the experiments. We are also grateful for the supports from National Natural Science Foundation of China, Natural Science Foundation of Jiangxi Province, Transportation Department of Jiangxi Province, Education Department of Jiangxi Province.

Funding

This study was funded by National Natural Science Foundation of China (Grant Number: 11862006, 61862025), Natural Science Foundation of Jiangxi Province (Grant Number: 2018ACB21032, 20181BAB211016), Research Project of Transportation Department of Jiangxi Province (Grant Number: 2018X0016), Education Department of Jiangxi Province (Grant Number: GJJ170381, GJJ170383) and China Scholarship Council (Grant Number: 201808360320).

Author information

Author notes

  1. Juan Wang and Meng Wang contributed equally.

Authors and Affiliations

  1. School of Information Engineering, East China Jiaotong University, Nanchang, 330013, China

    Juan Wang, Meng Wang, Guanxiang Yin & Yuejin Zhang

  2. College of Information and Communication Engineering, Harbin Engineering University, Harbin, China

    Qingling Liu

Authors
  1. Juan Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Meng Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Qingling Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Guanxiang Yin
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Yuejin Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

All authors contributed to the study conception and design. The project was conceived by YZ and QL. The experiments were designed and performed by JW, MW and GY. YZ and JW wrote the manuscript with inputs from all other authors. All authors have read and approved the final version of the manuscript.

Corresponding author

Correspondence to Yuejin Zhang.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, J., Wang, M., Liu, Q. et al. Deep anomaly detection in expressway based on edge computing and deep learning. J Ambient Intell Human Comput 13, 1293–1305 (2022). https://doi.org/10.1007/s12652-020-02574-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12652-020-02574-y

Keywords

Search

Navigation