Abstract
Walking has been widely promoted by various medical institutions as a major contributor to physical activity that keeps people healthy. However, pedestrian safety remains a critical concern due to barriers present on sidewalks, such as bins, poles, and trees. Although pedestrians are generally cautious, these barriers can pose a significant risk to vulnerable groups, such as the visually impaired and elderly. To address this issue, accurate and robust computer vision models can be used to detect barriers on pedestrian pathways in real-time. In this study, we assess the performance of fine-tuned egocentric barrier recognition models under various conditions, such as lighting variations, angles of view, video frame rates and levels of obstruction. In this context, we collected a dataset of different barriers, and fine-tuned two representative image recognition models, assessing their performances on a set of videos taken from a predefined route. Our findings provide guidelines for retaining model performance for applications using barrier recognition models in varying environmental conditions.
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
Angın, M., Ali, S.I.A.: Analysis of factors affecting road traffic accidents in North Cyprus. Eng. Technol. Appl. Sci. Res. 11(6), 7938–7943 (2021)
Ding, Z., Shen, Z., Guo, N., Zhu, K., Long, J.: Evacuation through area with obstacle that can be stepped over: experimental study. J. Stat. Mech: Theory Exp. 2020(2), 023404 (2020)
Dosovitskiy, A., et al.: An image is worth 16\(\times \)16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (ICLR 2021) (2021)
Foerster, K.T., Gross, A., Hail, N., Uitto, J., Wattenhofer, R.: SpareEye: enhancing the safety of inattentionally blind smartphone users. In: Proceedings of the 13th International Conference on Mobile and Ubiquitous Multimedia, MUM 2014, pp. 68–72. ACM (2014)
Grauman, K., et al.: Ego4D: around the world in 3,000 hours of egocentric video. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 18973–18990 (2022)
Haghighi, M., Nadrian, H., Sadeghi-Bazargani, H., Hdr, D.B., Bakhtari Aghdam, F.: Challenges related to pedestrian safety: a qualitative study identifying Iranian residents’ perspectives. Int. J. Inj. Contr. Saf. Promot. 27(3), 327–335 (2020)
Hasan, R., Hasan, R.: Pedestrian safety using the internet of things and sensors: issues, challenges, and open problems. Futur. Gener. Comput. Syst. 134, 187–203 (2022)
Jain, S., Borgiattino, C., Ren, Y., Gruteser, M., Chen, Y., Chiasserini, C.F.: LookUp: enabling pedestrian safety services via shoe sensing. In: Proceedings of the 13th Annual International Conference on Mobile Systems, Applications, and Services, MobiSys 2015, pp. 257–271. ACM (2015)
Jain, S., Gruteser, M.: Recognizing textures with mobile cameras for pedestrian safety applications. IEEE Trans. Mob. Comput. 18(8), 1911–1923 (2019)
Lee, Y.J., Ghosh, J., Grauman, K.: Discovering important people and objects for egocentric video summarization. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1346–1353 (2012)
Liu, X., Cao, J., Wen, J., Tang, S.: InfraSee: an unobtrusive alertness system for pedestrian mobile phone users. IEEE Trans. Mob. Comput. 16(2), 394–407 (2017)
Mann, S., Kitani, K.M., Lee, Y.J., Ryoo, M.S., Fathi, A.: An introduction to the 3rd workshop on egocentric (first-person) vision. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 827–832 (2014)
Piercy, K.L., et al.: The physical activity guidelines for Americans. JAMA 320(19), 2020–2028 (2018)
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510–4520 (2018)
Tang, M., Nguyen, C.T., Wang, X., Lu, S.: An efficient walking safety service for distracted mobile users. In: 2016 IEEE 13th International Conference on Mobile Ad Hoc and Sensor Systems (MASS), pp. 84–91 (2016)
Theodosiou, Z., Partaourides, H., Atun, T., Panayi, S., Lanitis, A.: A first-person database for detecting barriers for pedestrians. In: VISIGRAPP 2020 - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, vol. 5, pp. 660–666 (2020)
Theodosiou, Z., Partaourides, H., Panayi, S., Kitsis, A., Lanitis, A.: Detection and recognition of barriers in egocentric images for safe urban sidewalks. In: Bouatouch, K., et al. (eds.) VISIGRAPP 2020. CCIS, vol. 1474, pp. 530–543. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-94893-1_25
Theodosiou, Z., Thoma, M., Partaourides, H., Lanitis, A.: A systematic approach for developing a robust artwork recognition framework using smartphone cameras. Algorithms 15(9), 305 (2022)
Thoma, M., Theodosiou, Z., Partaourides, H., Tylliros, C., Antoniades, D., Lanitis, A.: A smartphone application designed to detect obstacles for pedestrians’ safety. In: Paiva, S., Lopes, S.I., Zitouni, R., Gupta, N., Lopes, S.F., Yonezawa, T. (eds.) SmartCity360\(^{\circ }\) 2020. LNICST, vol. 372, pp. 358–371. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-76063-2_25
Wang, T., Cardone, G., Corradi, A., Torresani, L., Campbell, A.T.: WalkSafe: a pedestrian safety app for mobile phone users who walk and talk while crossing roads. In: Proceedings of the Twelfth Workshop on Mobile Computing Systems & Applications, HotMobile 2012, pp. 1–6. ACM (2012)
Wang, Z., Tan, S., Zhang, L., Yang, J.: ObstacleWatch: acoustic-based obstacle collision detection for pedestrian using smartphone. Proc. ACM Interact. Mob. Wearable Ubiquit. Technol. 2(4), 1–22 (2018)
Wei, Z., Lo, S.W., Liang, Y., Li, T., Shen, J., Deng, R.H.: Automatic accident detection and alarm system. In: Proceedings of the 23rd ACM International Conference on Multimedia, MM 2015, pp. 781–784. ACM (2015)
XOIO-AIR: Cutout people - Greenscreen volume 1 (2012). https://xoio-air.de/2012/greenscreen_people_01/
Acknowledgements
This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 739578 complemented by the Government of the Republic of Cyprus through the Directorate General for European Programmes, Coordination and Development.
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
Thoma, M., Partaourides, H., Sreedharan, I., Theodosiou, Z., Michael, L., Lanitis, A. (2023). Performance Assessment of Fine-Tuned Barrier Recognition Models in Varying Conditions. In: Tsapatsoulis, N., et al. Computer Analysis of Images and Patterns. CAIP 2023. Lecture Notes in Computer Science, vol 14185. Springer, Cham. https://doi.org/10.1007/978-3-031-44240-7_17
Download citation
DOI: https://doi.org/10.1007/978-3-031-44240-7_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44239-1
Online ISBN: 978-3-031-44240-7
eBook Packages: Computer ScienceComputer Science (R0)