Abstract
It is critical to assess the standards of disabled facilities in order to ensure the comfort and safety of disabled individuals who use them. In this study, deep convolutional neural networks (CNNs) with multi-label classification capability are employed for a preliminary evaluation of the car park for the disabled and the elderly in accordance with ministerial regulations, reducing the burden of on-site inspection by specialists. Using a transfer learning technique, the weights of an Inception-V3, Xception, and EfficientNet-B2 architectures previously trained on the ImageNet dataset were updated with the disabled car park image dataset. We used 4,812 training images and 355 test images to train, evaluate, and compare the model. The results revealed that the EfficientNet-B2 model yielded the best performance for 5 out of 6 classes, with the F1-score between 79.8% and 95.6%. In contrast, the remaining one class was best predicted by the Xception model, where the F1-score was 83.33%. This implies that it is possible to apply CNNs to aid in the evaluation of handicap facilities.
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
Similar content being viewed by others
References
Institute for Human Centered Design, ada checklist for existing facilities (2016). https://www.adachecklist.org/doc/fullchecklist/ada-checklist.pdf
Keras. https://keras.io/
Keras applications. https://keras.io/api/applications/
Ministry of interior, ministerial regulations prescribing facilities in buildings for the disabled or handicapped and the elderly, b.e. 2548 (in thai). https://download.asa.or.th/03media/04law/cba/mr/mr48-58e-upd(02).pdf
Ministry of interior, ministerial regulations prescribing facilities in buildings for the disabled or handicapped and the elderly (no. 2), b.e. 2564 (in thai). http://www.ratchakitcha.soc.go.th/DATA/PDF/2564/A/016/T_0019.PDF
Ministry of interior, ministerial regulations prescribing the characteristics or provision of equipment, facilities or services in buildings, places or other public services for the disabled to access and utilize, b.e. 2555 (in thai). https://www.doe.go.th/prd/assets/upload/files/BKK_th/d2d8c77204d9b6d2853cd9cd9240c23f.pdf
Parliament of the United Kingdom, equality act (2010). https://www.legislation.gov.uk/ukpga/2010/15/contents
Tensorflow. https://www.tensorflow.org/
Transfer learning and fine-tuning. https://www.tensorflow.org/tutorials/images/transfer_learning/
United Nations, disability laws and acts by country/area. https://www.un.org/development/desa/disabilities/disability-laws-and-acts-by-country-area.html
World Health Organization, 10 facts on disability. https://www.who.int/news-room/facts-in-pictures/detail/disabilities
Abbott, A., Deshowitz, A., Murray, D., Larson, E.C.: Walknet: a deep learning approach to improving sidewalk quality and accessibility. SMU Data Sci. Rev. 1(1), 7 (2018)
Adams, M.A., Phillips, C.B., Patel, A., Middel, A.: Training computers to see the built environment related to physical activity: detection of micro-scale walkability features using computer vision (2022)
Ahmetovic, D., Manduchi, R., Coughlan, J.M., Mascetti, S.: Zebra crossing spotter: automatic population of spatial databases for increased safety of blind travelers. In: Proceedings of the 17th International ACM SIGACCESS Conference on Computers & Accessibility, pp. 251–258 (2015)
Anguelov, D., et al.: Google street view: capturing the world at street level. Computer 43(6), 32–38 (2010)
Berriel, R.F., Rossi, F.S., de Souza, A.F., Oliveira-Santos, T.: Automatic large-scale data acquisition via crowdsourcing for crosswalk classification: a deep learning approach. Comput. Graph. 68, 32–42 (2017)
Blanc, N., et al.: Building a crowdsourcing based disabled pedestrian level of service routing application using computer vision and machine learning. In: 2019 16th IEEE Annual Consumer Communications & Networking Conference (CCNC), pp. 1–5. IEEE (2019)
Chollet, F.: Xception: Deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1251–1258 (2017)
Felzenszwalb, P., McAllester, D., Ramanan, D.: A discriminatively trained, multiscale, deformable part model. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8. IEEE (2008)
Froehlich, J.: Combining crowdsourcing and machine learning to collect sidewalk accessibility data at scale. Technical report (2021)
Hara, K., Froehlich, J.E.: Characterizing and visualizing physical world accessibility at scale using crowdsourcing, computer vision, and machine learning. ACM SIGACCESS Accessibility Comput. 113, 13–21 (2015)
Hara, K., Le, V., Sun, J., Jacobs, D., Froehlich, J.: Exploring early solutions for automatically identifying inaccessible sidewalks in the physical world using google street view. Human Comput. Interact. Consortium (2013)
Hara, K., Sun, J., Moore, R., Jacobs, D., Froehlich, J.: Tohme: detecting curb ramps in google street view using crowdsourcing, computer vision, and machine learning. In: Proceedings of the 27th Annual ACM Symposium on User Interface Software and Technology, pp. 189–204 (2014)
Kent, J.: ADA in Details: Interpreting the 2010 Americans with Disabilities Act Standards for Accessible Design. John Wiley & Sons, Hoboken (2017)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint. arXiv:1412.6980 (2014)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, vol. 25 (2012)
Sagi, O., Rokach, L.: Ensemble learning: a survey. Wiley Interdisc. Rev. Data Min. Knowl. Discovery 8(4), e1249 (2018)
Stivaktakis, R., Tsagkatakis, G., Tsakalides, P.: Deep learning for multilabel land cover scene categorization using data augmentation. IEEE Geosci. Remote Sens. Lett. 16(7), 1031–1035 (2019). https://doi.org/10.1109/LGRS.2019.2893306
Sun, J., Jacobs, D.W.: Seeing what is not there: learning context to determine where objects are missing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5716–5724 (2017)
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Tan, M., Le, Q.: Efficientnet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105–6114. PMLR (2019)
Torrey, L., Shavlik, J.: Transfer learning. In: Handbook of Research on Machine Learning Applications and Trends: Algorithms, Methods, and Techniques, pp. 242–264. IGI global (2010)
Weld, G., Jang, E., Li, A., Zeng, A., Heimerl, K., Froehlich, J.E.: Deep learning for automatically detecting sidewalk accessibility problems using streetscape imagery. In: The 21st International ACM SIGACCESS Conference on Computers and Accessibility, pp. 196–209 (2019)
Wu, J., et al.: Multi-label active learning algorithms for image classification: overview and future promise. ACM Comput. Surv. (CSUR) 53(2), 1–35 (2020)
Xue, D., et al.: An application of transfer learning and ensemble learning techniques for cervical histopathology image classification. IEEE Access 8, 104603–104618 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Hanpinitsak, P., Posawang, P., Phankaweerat, S., Pattara-atikom, W. (2022). Method for Image-Based Preliminary Assessment of Car Park for the Disabled and the Elderly Using Convolutional Neural Networks and Transfer Learning. In: Surinta, O., Kam Fung Yuen, K. (eds) Multi-disciplinary Trends in Artificial Intelligence. MIWAI 2022. Lecture Notes in Computer Science(), vol 13651. Springer, Cham. https://doi.org/10.1007/978-3-031-20992-5_9
Download citation
DOI: https://doi.org/10.1007/978-3-031-20992-5_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20991-8
Online ISBN: 978-3-031-20992-5
eBook Packages: Computer ScienceComputer Science (R0)