access icon openaccess Object detection method on station logo with single shot multi-box detector

This is an open access article published by the IET under the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0/)
Received 14/10/2019, Accepted 12/11/2019, Published 13/01/2020

In this work, the authors design an object detection method by the characteristics of the station with convolutional neural network, such as small scale-to-height ratio change and relatively fixed position. In order to realise the pre-processing and feature extraction of the station data, they collect the video samples and filter, frame, label and process to these samples. Also then, the training sample data and the test sample data are divided proportionally to train the station detection model. After that, the sample is tested to evaluate the effect of the training model in practice. The simulation experiments proved its validity.

Inspec keywords: convolutional neural nets; filtering theory; feature extraction; object detection; video signal processing

Other keywords: station logo; scale-to-height ratio change; test sample data; station detection model; convolutional neural network; object detection method; station data; video samples; authors design; training sample data; single shot multibox detector

Subjects: Neural computing techniques; Computer vision and image processing techniques; Video signal processing; Optical, image and video signal processing; Filtering methods in signal processing

References

    1. 1)
      • 21. Cao, G., Xie, X., Yang, W., et al: ‘Feature-fused SSD: fast detection for small objects’. 9th Int. Conf. on Graphic and Image Processing (ICGIP 2017), Qingdao, People's Republic of China, 2017, arXiv:1709.05054.
    2. 2)
      • 15. Yousong, H., Chaoyang, Z., Haiyun, G.: ‘Attention CoupleNet: Fully Convolutional Attention Coupling Network for Object Detection’, IEEE Trans. Image Process., 2019, 28, (1), pp. 113–126.
    3. 3)
      • 19. Li, H., Jiang, G., Zhang, J., et al: ‘Fully convolutional network ensembles for white matter hyperintensities segmentation in MR images’, NeuroImage, 2018, 183, pp. 650–665.
    4. 4)
      • 11. Wang, J.: ‘New color segmentation method and its applications’, Photonics East, International Society for Optics and Photonics, (1999).
    5. 5)
      • 5. Ahmadi, S., Manivarnosfaderani, A., Habibi, B.: ‘Motor oil classification using color histograms and pattern recognition techniques’, J. AOAC Int., 2018, 101, (6), pp. 1967–1976.
    6. 6)
      • 10. Routray, S., Ray, A.K., Mishra, C., et al: ‘Efficient hybrid image denoising scheme based on SVM classification’, Optik, 2018, 157, pp. 503–511.
    7. 7)
      • 23. Bao, Y., Li, H., Fan, X., et al: ‘Region-based CNN for logo detection’. Int. Conf. on Internet Multimedia Computing and Service. ACM, Xi'an, People's Republic of China, 2016, pp. 319–322.
    8. 8)
      • 9. Zhang, H., Nie, F., Zhang, R., et al: ‘Auto-weighted 2-dimensional maximum margin criterion’, Pattern Recognit., 2018, 83, (2018), pp. 220–229.
    9. 9)
      • 16. Guo, Y.J., Wang, J.H., Ming-Ming, J.I.: ‘Analysis of SSD method's inference’, Modern Comput., 2018, 2.
    10. 10)
      • 17. Leng, J., Liu, Y.: ‘An enhanced SSD with feature fusion and visual reasoning for object detection’, Neural Comput. Appl., 2019, 31, (2), pp. 6549–6558.
    11. 11)
      • 1. Chen, W., Lan, S., Xu, P.: ‘Multiple feature fusion via hierarchical matching for TV logo recognition’. Int. Congress on Image and Signal Processing. IEEE, Shenyang, People's Republic of China, 2015, pp. 659–663.
    12. 12)
      • 20. Zheng, L., Fu, C., Zhao, Y.: ‘Extend the shallow part of single shot MultiBox detector via convolutional neural network’, 2018, p. 141, arXiv:1801.05918.
    13. 13)
      • 7. Liang, C.H., Chang, Q.: ‘Weighted modified Hu moment in human behavior recognition’, Adv. Mater. Res., 2013, 765–767, pp. 2603–2607.
    14. 14)
      • 13. Qu, H., Lei, L., Tang, X., et al: ‘A lightweight intrusion detection method based on fuzzy clustering algorithm for wireless sensor networks’, Adv. Fuzzy Syst., 2018, 2018, pp. 1–12.
    15. 15)
      • 22. Simonyan, K., Zisserman, A.: ‘Very deep convolutional networks for large-scale image recognition’. Proc. Int. Conf. Learn. Representat., San Diego, CA, USA, 2015, pp. 1–14.
    16. 16)
      • 12. Shi, Y., Wang, T., Zhou, X.: ‘Real-time video detection based on local accumulative histogram in non-equational similar hue region of partition’, Comput. Eng., 2004, 30, (10), pp. 153–155.
    17. 17)
      • 18. Liu, W., Anguelov, D., Erhan, D., et al: ‘SSD: single shot MultiBox detector’. European Conf. on Computer Vision, Cham, 2016, pp. 21–37.
    18. 18)
      • 8. Liu, P., Miao, Z., Guo, H., et al: ‘Adding spatial distribution clue to aggregated vector in image retrieval’, EURASIP J. Image Video Process., 2018, 2018, (1), pp. 9–22.
    19. 19)
      • 2. Bianco, S., Buzzelli, M., Mazzini, D., et al: ‘Deep learning for logo recognition’, Neurocomputing, 2017, 245, (C), pp. 23–30.
    20. 20)
      • 6. Zhang, X., Yang, J., Nguyen, E.: ‘Breast cancer detection via Hu moment invariant and feedforward neural network’. American Institute of Physics Conf. Series, Ho Chi Minh City, Vietnam, May 2018.
    21. 21)
      • 4. Oliveira, G., Frazo, X., Pimentel, A., et al: ‘Automatic graphic logo detection via fast region-based convolutional networks’. Int. Joint Conf. on Neural Networks (IJCNN), Vancouver, BC, Canada, 24–29 July 2016.
    22. 22)
      • 14. Yang, J., Ma, J.F., Liu, Y.Y., et al: ‘A series of Cu(II) complexes based on different bis(imidazole) ligands and organic acids: formation of water clusters and fixation of atmospheric carbon dioxide’, Cryst. Growth Des., 2008, 8, (12), pp. 4383–4393.
    23. 23)
      • 3. Shin, H.C., Roth, H.R., Gao, M., et al: ‘Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning’, IEEE Trans. Med. Imaging, 2016, 35, (5), pp. 1285–1298.
http://iet.metastore.ingenta.com/content/journals/10.1049/joe.2019.1213
Loading

Related content

content/journals/10.1049/joe.2019.1213
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading