Abstract
Deep Learning models are becoming widely used in many applications but they can often be improved through a fine-tuning process capable of enhancing their performances in specific scenarios.
In this paper we tackle the problem of autonomously inspecting the conditions of Collective Protection Equipment (CPE) such as fire extinguishers, warning signs, ground and wall signalization and others.
Work ministry imposes that such CPE are in good conditions to prevent accidents, carrying out periodic mandatory in loco auditions. Industry is increasingly applying the potential of Deep Learning (DL) models to automatize such Computer Vision (CV) tasks and a fiber-optic component provider proposed this demand.
Specifically, we assessed the performances of four DL models, namely, MobileNet V2 SSDLite, FPN Resnet-50 SSD, Inception Resnet v2 Faster R-CNN with Atrous Convolution and EfficientNet B0 SSD in the evaluation of CPE conditions. We provide results that highlight each architecture’s advantages and drawbacks in the aforementioned scenario.
Indeed, experiments have shown their potential in reducing time and costs of periodic inspections in factories.
Supported by organization x.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Aggarwal, C.C.: Neural Networks and Deep Learning, 1 edn. Springer International Publishing (2018). https://doi.org/10.1007/978-3-319-94463-0, https://www.springer.com/gp/book/9783319944623
Akinosho, T.D., et al.: Deep learning in the construction industry: A review of present status and future innovations. J. Building Eng. 32, 101827 (2020). https://doi.org/10.1016/j.jobe.2020.101827
Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834–848 (2017)
Choi, Y., Park, J.H., Jang, B.: A risk estimation approach based on deep learning in shipbuilding industry. In: 2019 International Conference on Information and Communication Technology Convergence (ICTC), pp. 1438–1441. IEEE (2019)
Chou, Y.C., et al.: Deep-learning-based defective bean inspection with gan-structured automated labeled data augmentation in coffee industry. Appl. Sci. 9(19), 4166 (2019)
Dargan, S., Kumar, M., Ayyagari, M.R., Kumar, G.: A survey of deep learning and its applications: a new paradigm to machine learning. Arch. Comput. Methods Eng. 27(4), 1071–1092 (2019). https://doi.org/10.1007/s11831-019-09344-w
Georgevich Ferreira, B., Lima., B.G.C., Vieira., T.F.: Visual inspection of collective protection equipment conditions with mobile deep learning models. In: Proceedings of the 1st International Conference on Deep Learning Theory and Applications - Volume 1: DeLTA, pp. 76–83. INSTICC, SciTePress (2020). https://doi.org/10.5220/0009834600760083
Hocenski, Ž., Matić, T., Vidović, I.: Technology transfer of computer vision defect detection to ceramic tiles industry. In: 2016 International Conference on Smart Systems and Technologies (SST), pp. 301–305. IEEE (2016)
Howard, A.G., et al.: Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)
Huang, J., et al.: Speed/accuracy trade-offs for modern convolutional object detectors. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7310–7311 (2017)
Li, L., Ota, K., Dong, M.: Deep learning for smart industry: Efficient manufacture inspection system with fog computing. IEEE Trans. Industr. Inf. 14(10), 4665–4673 (2018)
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)
Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48
Liu, W., et al.: 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
Rao, Q., Frtunikj, J.: Deep learning for self-driving cars: chances and challenges. In: Proceedings of the 1st International Workshop on Software Engineering for AI in Autonomous Systems, pp. 35–38 (2018)
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: Mobilenetv 2: Inverted residuals and linear bottlenecks. In: Proceedings of the Ieee Conference On Computer Vision and Pattern Recognition, pp. 4510–4520 (2018)
Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-resnet and the impact of residual connections on learning. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)
Tan, M., Le, Q.V.: Efficientnet: Rethinking model scaling for convolutional neural networks. arXiv preprint arXiv:1905.11946 (2019)
Veeraraghavan, A., Adithya, V., Bhave, A., Akella, S.: Battery aging estimation with deep learning. In: 2017 IEEE Transportation Electrification Conference (ITEC-India), pp. 1–4. IEEE (2017)
Zhang, N., et al.: Automatic recognition of oil industry facilities based on deep learning. In: IGARSS 2018–2018 IEEE International Geoscience and Remote Sensing Symposium, pp. 2519–2522. IEEE (2018)
Acknowledgements
The authors would like to thank the Edge laboratory http://edgebr.org/ at the Federal University of Alagoas https://ufal.br/ which funded this research through an agreement regulated by Brazil’s Information Technology Law.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ferreira, B.G., Lima, B.G.C., Vieira, T.F. (2023). Evaluating Deep Learning Models for the Automatic Inspection of Collective Protective Equipment. In: Fred, A., Sansone, C., Madani, K. (eds) Deep Learning Theory and Applications. DeLTA DeLTA 2020 2021. Communications in Computer and Information Science, vol 1854. Springer, Cham. https://doi.org/10.1007/978-3-031-37320-6_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-37320-6_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-37319-0
Online ISBN: 978-3-031-37320-6
eBook Packages: Computer ScienceComputer Science (R0)