Abstract
Currently, maintenance of wind valves in rail transit occurs frequently. The implementation of machine vision for remote operation and maintenance would significantly decrease labour requirements. As the number of wind valves on-site is high, it necessitates rich GPU resources. Although large deep learning algorithm models provide strong performance, they require expensive computing power. Therefore, the challenge lies in designing smaller models that reduce GPU computing power to increase efficiency and reduce costs. This study explores the use of a small model in combination with a “virtual coding” process, employing the itti encoder type device. The proposed approach achieves model size reduction while maintaining performance, resulting in a test set accuracy of 98.5%. The F1 index also reflects high accuracy at 99.6%, representing a 1% increase compared to no encoder operation. The approach meets the needs of remote operation and maintenance and can be applied in subway environments. Moreover, successful transition from manual detection to machine detection is realized. This paper suggests a “virtual coding” technique for flexible image transformation. The technique focuses on different data formats including image edge detection, segmentation, feature extraction, dimension reduction, fusion, saliency transformation and feature change. The proposed process offers significant technical summary value for deep learning to incorporate other image change technologies. To ascertain the efficacy of the method, this paper conducted verifications on additional datasets, and the findings confirmed a significant enhancement in its effectiveness.
Similar content being viewed by others
Data availability
The data used to support the findings of this study are available from the corresponding author upon request.
References
Zhai, Y., Shah, M.: Visual attention detection in video sequences using spatiotemporal cues. In ACM Multimedia, pp. 815–824 (2006)
Achanta, R., Hemami, S., Estrada, F., Susstrunk, S.: Frequency-tuned salient region detection. In IEEE CVPR, pp. 1597–1604 (2009)
Goferman, S., Zelnik-Manor, L., Tal, A.: Context-aware saliency detection. In IEEE CVPR, pp. 2376–2383 (2010)
Itti, L., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. IEEE TPAMI 20(11), 1254–1259 (1998)
Cheng, M.M., Mitra, N.J., Huang, X., Torr, P.H., Hu, S.M.: Global contrast based salient region detection. IEEE Trans. Pattern Anal. Mach. Intell. 37(3), 569–582 (2014)
Hou, X., Zhang, L.: Saliency detection: a spectral residual approach. In IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8 (2007)
Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: Visual explanations from deep networks via gradient-based localization. In ICCV2017 (2017)
Wen, G.A.O., Hai-feng, X.I.A.O.: Low illumination color image enhancement based on dynamic bistable stochastic resonance. Chin. J. Liquid Cryst. Disp. 36(6), 861–868 (2021)
Karasmanoglou, A., Antonakakis, M., Zervakis, M.: ECG-based semi-supervised anomaly detection for early detection and monitoring of epileptic seizures. Int. J. Environ. Res. Public Health 20(6), 5000 (2023). https://doi.org/10.3390/ijerph20065000
Hua, W., Jie, S., You, Q.: Semi-supervised learning of medical image classification based on anti-course learning. Mathematics 11, 1306 (2023). https://doi.org/10.3390/math11061306
Woo, S., Park, J., Lee, J., Kweon, I.S.: CBAM: convolutional block attention module, In ECCV, pp. 3–19 (2018)
Hou, Q., Zhou, D., Feng, J.: Coordinate attention for efficient mobile network design. In CVPR (2021)
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks, (2018) arxiv: 1709.01507
Senthilkumaran, N., Vaithegi, S.: Image segmentation by using thresholding techniques for medical images. Comput. Sci. Eng. Int. J. 6(1), 1–13 (2016)
Abbaskhah, A., Sedighi, H., Marvi, H.: Infant cry classification by MFCC feature extraction with MLP and CNN structures. Biomed. Signal Process. Control, 86, 105261, ISSN 1746–8094 (2023). https://doi.org/10.1016/j.bspc.2023
J. Tan et al.: GLCM-CNN: Gray Level Co-occurrence Matrix based CNN Model for Polyp Diagnosis, 2019 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI ), Chicago, IL, USA, pp. 1–4 (2019). https://doi.org/10.1109/BHI.2019.8834585
Xu, K., Qin, M., Sun, F., Wang, Y., Chen, Y. -K., Ren, F.: Learning in the frequency domain. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, pp. 1737–1746 (2020) https://doi.org/10.1109/CVPR42600.2020.00181
Qin, P., Zhang, F., Wu, F., Li, X.: FcaNet: frequency channel attention networks. In 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada, pp. 763–772 (2021) https://doi.org/10.1109/ICCV48922.2021.00082
Sujithra, B.S., Albert Jerome, S.: Adaptive cluster-based superpixel segmentation and BMWMMBO-based DCNN classification for glaucoma detection. SIViP (2023). https://doi.org/10.1007/s11760-023-02751-4
Liu, P., Zhang, H., Zhang, K., Lin, L., Zuo, W.: Multi-level wavelet-CNN for image restoration. In 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Salt Lake City, UT, USA, pp. 886–88609 (2018) https://doi.org/10.1109/CVPRW.2018.00121
Luan, S., Chen, C., Zhang, B., Han, J., Liu, J.: Gabor convolutional networks. IEEE Trans. Image Process. 27(9), 4357–4366 (2018). https://doi.org/10.1109/TIP.2018.2835143
Aggarwal, A., Bhutani, N., Kapur, R., et al.: Real-time hand gesture recognition using multiple deep learning architectures. SIViP17 (2023). https://doi.org/10.1007/s11760-023-02626-8
Huo, J., Shi, B., Zhang, Y.: An object detection method for the work of an unmanned sweeper in a noisy environment on an improved YOLO algorithm. SIViP17 (2023). https://doi.org/10.1007/s11760-023-02654-4
Uppada, R., Kumar, D.V.A.N.R.: Computer-aided fusion-based neural network in application to categorize tomato plants. SIViP17 (2023). https://doi.org/10.1007/s11760-023-02551-w
Acknowledgements
Supported by the fund:Shandong Natural Science Foundation, No.: zr2020qe268, Name: basic application of ABP-IOT technology in subway tunnel fan, research on energy saving technology of environmental control system. The Mount Tai Industry Leading Talent Project Special Fund Support.
Author information
Authors and Affiliations
Contributions
AF Write, concept, code. LJ, LM, LG, SH concept.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflicts of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Junfeng, A., Jiqiang, L., Mengmeng, L. et al. Image change combined with CNN power subway vent valve state monitoring. SIViP 18, 2151–2166 (2024). https://doi.org/10.1007/s11760-023-02874-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11760-023-02874-8