Skip to main content
SpringerLink
Log in

Object Detection Model Training Framework for Very Small Datasets Applied to Outdoor Industrial Structures

  • Conference paper
  • First Online:
Advances in Visual Informatics (IVIC 2021)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 13051))

Included in the following conference series:

  • 1359 Accesses

Abstract

Visual inspection of electrical utility assets is crucial in ensuring the continuous operation of a system or plant. With the advent of digital imagery using mobile devices, it has become easy to collect a vast amount of asset pictures from sites. To further enhance inspection efficiency, we propose RetinaNet, a deep learning-based object detection model that can be trained to automatically detect specific objects and features from images of outdoor industrial structures. The model is capable of detecting features such as intrusions, tree or bushes in the vicinity of the lattice towers. We also introduce a model training framework for use with very small datasets which consists of rigorous data augmentation, image pre-sizing, focal loss function, progressive resizing, learning rate finder, and the Ranger optimizer. Experiment results show that the proposed model used in conjunction with the aforementioned training framework results in the lowest validation loss and highest mean average precision of 31.36

Supported by Uniten R&D Seed Grant U-TS-RD-19-31.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Zhou, W., Yang, Y., Yu, C., Liu, J., Duan, X., Weng, Z., Chen, D., Liang, Q., Fang, Q., Zhou, J., et al.: Ensembled deep learning model outperforms human experts in diagnosing biliary atresia from sonographic gallbladder images. Nature Commun. 12(1), 1–14 (2021)

    Article  Google Scholar 

  2. Zhao, Z.-Q., Zheng, P., Xu, S.-T., Wu, X.: Object detection with deep learning: a review. IEEE Trans. Neural Networks Learn. Syst. 30(11), 3212–3232 (2019)

    Article  Google Scholar 

  3. Bochkovskiy, A., Wang, C.-Y., Liao, H.-Y.M.: Yolov4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934, 2020

  4. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)

    Google Scholar 

  5. Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)

  6. Tan, M., Le, Q.: Efficientnet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning. PMLR, pp. 6105–6114 (2019)

    Google Scholar 

  7. Du, X., et al.: Spinenet: learning scale-permuted backbone for recognition and localization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11 592–11 601 (2020)

    Google Scholar 

  8. Wang, C.-Y., Liao, H.-Y.M., Wu, Y.-H., Chen, P.-Y., Hsieh, J.-W., Yeh, I.-H.: Cspnet: a new backbone that can enhance learning capability of cnn. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 390–391 (2020)

    Google Scholar 

  9. Lin, T.-Y., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117–2125 (2017)

    Google Scholar 

  10. Tan, M., Pang, R., Le, Q.V.: Efficientdet: scalable and efficient object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10 781–10 790 (2020)

    Google Scholar 

  11. Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8759–8768 (2018)

    Google Scholar 

  12. Faster, R.: Towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 9199 (2015)

    Google Scholar 

  13. Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788 (2016)

    Google Scholar 

  14. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A.C.: SSD: single shot MultiBox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21–37. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46448-0_2

    Chapter  Google Scholar 

  15. T.-Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár, "Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980–2988 (2017)

    Google Scholar 

  16. Tian, Z., Shen, C., Chen, H., He, T.: Fcos: fully convolutional one-stage object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9627–9636 (2019)

    Google Scholar 

  17. Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: Towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems 28, pp. 91–99 (2015)

    Google Scholar 

  18. He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961–2969 (2017)

    Google Scholar 

  19. Dai, J., Li, Y., He, K., Sun, J.: R-fcn: object detection via region-based fully convolutional networks. In: Advances in Neural Information Processing Systems, pp. 379–387 (2016)

    Google Scholar 

  20. Yang, Z., Liu, S., Hu, H., Wang, L., Lin, S.: Reppoints: point set representation for object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9657–9666 (2019)

    Google Scholar 

  21. Howard, J., Gugger, S.: Fastai: a layered api for deep learning. Information 11(2), 108 (2020)

    Article  Google Scholar 

  22. Howard, J.: Deep Learning for Coders with fastai and PyTorch. O’Reilly Media (2020)

    Google Scholar 

  23. Bhatt, A., Ganatra, A., Kotecha, K.: Covid-19 pulmonary consolidations detection in chest x-ray using progressive resizing and transfer learning techniques. Heliyon, p. e07211 (2021)

    Google Scholar 

  24. Van Rijn, J.N., Hutter, F.: Hyperparameter importance across datasets. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 2367–2376 (2018)

    Google Scholar 

  25. Smith, L.N.: A disciplined approach to neural network hyper-parameters: Part 1-learning rate, batch size, momentum, and weight decay. arXiv preprint arXiv:1803.09820 (2018)

  26. Wright, L., Demeure, N.: Ranger21: a synergistic deep learning optimizer. arXiv preprint arXiv:2106.13731 (2021)

  27. Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. Advances in neural information processing systems 32, 8026–8037 (2019)

    Google Scholar 

  28. Vazquez, L., Hassainia, F.: Icevision: an agnostic computer vision framework (2020)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Electrical and Electronics Engineering, Universiti Tenaga Nasional, Kajang, Malaysia

    M. Z. Baharuddin, D. N. T. How & K. S. M. Sahari

  2. Tenaga Nasional Berhad, Kuala Lumpur, Malaysia

    A. Z. Abas & M. K. Ramlee

Authors
  1. M. Z. Baharuddin
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. D. N. T. How
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. K. S. M. Sahari
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. A. Z. Abas
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. M. K. Ramlee
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to M. Z. Baharuddin .

Editor information

Editors and Affiliations

  1. Universiti Tenaga Nasional, Selangor, Malaysia

    Halimah Badioze Zaman

  2. Dublin City University, Dublin, Ireland

    Alan F. Smeaton

  3. National Central University, Jhongli, Taiwan

    Timothy K. Shih

  4. Queen Mary University of London, London, UK

    Sergio Velastin

  5. Toyo University, Tokyo, Japan

    Tada Terutoshi

  6. University of Southern Denmark, Odense, Denmark

    Bo Nørregaard Jørgensen

  7. Universiti Tenaga Nasional, Selangor, Malaysia

    Hazleen Aris

  8. Universiti Tenaga Nasional, Selangor, Malaysia

    Nazrita Ibrahim

Rights and permissions

Reprints and permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Baharuddin, M.Z., How, D.N.T., Sahari, K.S.M., Abas, A.Z., Ramlee, M.K. (2021). Object Detection Model Training Framework for Very Small Datasets Applied to Outdoor Industrial Structures. In: Badioze Zaman, H., et al. Advances in Visual Informatics. IVIC 2021. Lecture Notes in Computer Science(), vol 13051. Springer, Cham. https://doi.org/10.1007/978-3-030-90235-3_47

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-90235-3_47

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-90234-6

  • Online ISBN: 978-3-030-90235-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation