Abstract
The focus of policymaking in Korea has changed from vehicle-centric road environments to people-centric environments. As the importance of walking has increased, the construction of pedestrian paths and interest in pedestrian environments have also increased. However, problem recognition and resolution require considerable time in the event of a problem in a pedestrian path. People with reduced mobility tend to resist changes in roads that they use. Thus, damaged pedestrian paths and obstacles pose a considerable risk and economic loss to transportation. In this study, we aimed to minimize the time and cost required for the evaluation of pedestrian paths by developing an automatic system for determining damage using integrated You Only Look Once (YOLO) and convolutional neural network (CNN) image deep learning algorithms. We constructed a model using image deep learning by dividing the steps into walkway breakage detection and score evaluation according to the degree of breakage. The accuracy of the model was determined to be 92%. In the future, the evaluation of pedestrian path damage is expected to be automated using images and videos, thereby reducing the time required for the detection and restoration of damage.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Abbott A, Deshowitz A, Murray D, Larson EC (2018) WalkNet: A deep learning approach to improving sidewalk quality and accessibility. SMU Data Science Review 1(1):7
Ahmed F, Yeasi M (2017) Optimization and evaluation of deep architectures for ambient awareness on a sidewalk. 2017 international joint conference on neural networks (IJCNN), May 14–19, Anchorage, AK, USA, 2692–2697, DOI: https://doi.org/10.1109/IJCNN.2017.7966186
Cha YJ, Choi W, Büyüköztürk O (2017) Deep learning-based crack damage detection using convolutional neural networks. Computer-Aided Civil and Infrastructure 32(5):361–378, DOI: https://doi.org/10.1111/mice.12263
Choi S, Lee H, Choo S, Kim S (2015) A study on pedestrian accessibility considering social path. Korean Society of Transportation 33(1):50–60, DOI: https://doi.org/10.7470/jkst.2015.33.1.50 (in Korean)
Gonzalez D, Granados G, Battini J, Carter R, Nguyen T, Lim J, Abbot R (2019) Case study: Environmental safety monitoring system for sidewalk. 2019 8th mediterranean conference on embedded computing (MECO), June 10–14, Budva, Montenegro, DOI: https://doi.org/10.1109/MECO.2019.8760037
Gopalakrishnan K (2018) Deep learning in data-driven pavement image analysis and automated distress detection: A review. Data 3(3):28, DOI: https://doi.org/10.3390/data3030028
Hara Y, Hasegawa R, Uchiyama A, Umedu T, Higashino T (2020). FlowScan: Estimating people flows on sidewalks using dashboard cameras based on deep learning. Journal of Information Processing 28:55–64, DOI: https://doi.org/10.2197/ipsjjip.28.55
Hara K, Sun J, Moore R, Jacobs D, Froehlich J (2014) Tohme: Detecting curb ramps in google street view using crowdsourcing, computer vision, and machine learning. Proceedings of the 27th annual ACM symposium on User interface software and technology, October 5–8, Honolulu, HI, USA, DOI: https://doi.org/10.1145/2642918.2647403
Jang JA, Jang WJ, Choe JD (2013) Interview survey of vulnerable road user for pedestrian services. Transportation Technology and Policy 10(5):42–50
Kim S, Her J, Kim Y (2020) A study on the performance and effectiveness evaluation of the 2019 pedestrian environment improvement projects. General 2020–6, Architecture and Urban Research Institute, Sejong, Korea
Kim T, Jeong E, You S (2018a) Development of pedestrian property estimation method based on deep neural networks using LiDAR Sensor. Korean Society of Transportation 36(5):319–330, DOI: https://doi.org/10.7470/jkst.2018.36.5.319 (in Korean)
Kim AR, Kim D, Byun YS, Lee SW (2018b) Crack detection of concrete structure using deep learning and image processing method in geotechnical engineering. Journal of the Korean Geotechnical Society 34(12):145–154, DOI: https://doi.org/10.7843/kgs.2018.34.12.145 (in Korean)
Kim S, Lee K, Choi K (2014) A study on assessment indicator of walking environment considering land use characteristics. Journal of the Korean Society of Civil Engineers 34(3):931–938, DOI: https://doi.org/10.12652/Ksce.2014.34.3.0931 (in Korean)
Ku D, Kim J, Na S, Lee S (2020) Real-time taxi demand prediction using recurrent neural network. Proceedings of the Institution of Civil Engineers — Municipal Engineer 174(2):75–87, DOI: https://doi.org/10.1680/jmuen.20.00005
Lee Y, Kim Y (2020) Comparison of CNN and YOLO for object detection. Journal of the Semiconductor & Display Technology 19(1):85–92
Li Y, Han Z, Xu H, Liu L, Li X, Zhang K (2019) YOLOv3-lite: A lightweight crack detection network for aircraft structure based on depthwise separable convolutions. Applied Sciences 9(18), DOI: https://doi.org/10.3390/app9183781
Li W, Wang G, Fidon L, Ourselin S, Cardoso MJ, Vercauteren T (2017) On the compactness, efficiency, and representation of 3D convolutional networks: Brain parcellation as a pretext task. In: Information processing in medical imaging. Springer, Cham, Switzerland, DOI: https://doi.org/10.1007/978-3-319-59050-9_28
Lim S, Choo S, Choi ST (2016) A study on the determination of walkway level-of-service considering classification of pedestrian walkway: Focusing on Gangnam-gu. Journal of Korea Planning Association 51(2):161–178, DOI: https://doi.org/10.17208/jkpa.2016.04.51.2.161 (in Korean)
Park K, Lee S (2018). Application and validation of a deep learning model to predict the walking satisfaction on street level. Journal of The Urban Design Institute of Korea 19:19–34, DOI: https://doi.org/10.38195/judik.2018.12.19.6.19 (in Korean)
Redmon J, Farhadi A (2018) Yolov3: An incremental improvement
Weld G, Jang E, Li A, Zeng A, Heimerl K, Froehlich JE (2019) Deep learning for automatically detecting sidewalk accessibility problems using streetscape imagery. The 21st international ACM SIGACCESS conference on computers and accessibility, October 28–30, Pittsburgh, PA, USA, DOI: https://doi.org/10.1145/3308561.3353798
Acknowledgments
This work was supported by the Korea Agency for Infrastructure Technology Advancement (KAIA) grant funded by the Ministry of Land, Infrastructure, and Transport (Grant 22TLRP-C148659-05) and Korea Ministry of Land, Infrastructure and Transport (MOLIT) as 「Innovative Talent Education Program for Smart City」.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Choi, M.J., Ku, D.G. & Lee, S.J. Integrated YOLO and CNN Algorithms for Evaluating Degree of Walkway Breakage. KSCE J Civ Eng 26, 3570–3577 (2022). https://doi.org/10.1007/s12205-022-1017-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12205-022-1017-1