Pothole detection in the woods: a deep learning approach for forest road surface monitoring with dashcams

References

• Ali L, Alnajjar F, Parambil MMA, Younes MI, Abdelhalim ZI, Aljassmi H. 2022. Development of YOLOv5-based real-time smart monitoring system for increasing lab safety awareness in educational institutions. Sensors. 22(22):8820. doi: 10.3390/s22228820.
   PubMed Web of Science ®Google Scholar
• Arya D, Maeda H, Ghosh SK, Toshniwal D, Mraz A, Kashiyama T, Sekimoto Y. 2021. Deep learning-based road damage detection and classification for multiple countries. Autom Constr. 132:103935. doi: 10.1016/j.autcon.2021.103935.
   Web of Science ®Google Scholar
• Barriera M, Pouget S, Lebental B, Van Rompu J. 2020. In situ pavement monitoring: a review. Infrastruct. 5(2):18. doi: 10.3390/infrastructures5020018.
   Google Scholar
• Benjumea A, Teeti I, Cuzzolin F, Bradley A. 2021. YOLO-Z: improving small object detection in YOLOv5 for autonomous vehicles [Internet]. [accessed 2023 Nov 17]. doi: 10.48550/ARXIV.2112.11798.
   Google Scholar
• Bewley A, Ge Z, Ott L, Ramos F, Upcroft B. 2016. Simple online and realtime tracking. In: 2016 IEEE International Conference on Image Processing (ICIP) [Internet]. Phoenix, AZ, USA: IEEE; [accessed 2023 Jan 9]. p. 3464–3468. doi: 10.1109/ICIP.2016.7533003.
   Google Scholar
• Bochinski E, Eiselein V, Sikora T. 2017. High-speed tracking-by-detection without using image information. In: 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) [Internet]. Lecce, Italy: IEEE; [accessed 2022 Dec 8]. p. 1–6. doi: 10.1109/AVSS.2017.8078516.
   Google Scholar
• Boston K. 2016. The potential effects of forest roads on the environment and mitigating their impacts. Curr For Rep. 2(4):215–222. doi: 10.1007/s40725-016-0044-x.
   Web of Science ®Google Scholar
• Broström M. 2022. Real-time multi-camera multi-object tracker using YOLOv5 and StrongSORT with OSNet [Internet]. https://github.com/mikel-brostrom/Yolov5_StrongSORT_OSNet.
   Google Scholar
• Brown M, Mercier S, Provencher Y. 2003. Road maintenance with opti-grade ®: maintaining road networks to achieve the best value. Transp Res Rec. 1819(1):282–286. doi: 10.3141/1819a-41.
   Google Scholar
• Cao MT, Tran QV, Nguyen NM, Chang KT. 2020. Survey on performance of deep learning models for detecting road damages using multiple dashcam image resources. Adv Eng Inform. 46:101182. doi: 10.1016/j.aei.2020.101182.
   Web of Science ®Google Scholar
• Dietz P, Knigge W, Löffler H. [1984] 2011. Walderschließung: ein Lehrbuch für Studium und Praxis unter besonderer Berücksichtigung des Waldwegebaus ; mit 65 Tabellen. Repr [der Ausg. Hamburg, Berlin, Parey]. Remagen-Oberwinter: Kessel.
   Google Scholar
• Dodson EM. 2021. Challenges in forest road maintenance in North America. Croat J For Eng (Online). 42(1):107–116. doi: 10.5552/crojfe.2021.777.
   Web of Science ®Google Scholar
• Du Y, Song Y, Yang B, Zhao Y. 2022. StrongSORT: make DeepSORT great again [Internet]. [accessed 2022 Dec 8]. doi: 10.48550/ARXIV.2202.13514.
   Google Scholar
• Erber G, Kroisleitner H, Huber C, Varch T, Stampfer K. 2021. Periodical maintenance of forest roads with a mobile stone crusher. Croat J For Eng (Online). 42(1):1–12. doi: 10.5552/crojfe.2021.862.
   Web of Science ®Google Scholar
• Ezzati S, Palma CD, Bettinger P, Eriksson LO, Awasthi A. 2021. An integrated multi-criteria decision analysis and optimization modeling approach to spatially operational road repair decisions. Can J For Res. 51(3):465–483. doi: 10.1139/cjfr-2020-0016.
   Google Scholar
• Ferenčík M, Kardoš M, Allman M, Slatkovská Z. 2019. Detection of forest road damage using mobile laser profilometry. Comput Electron Agric. 166:105010. doi: 10.1016/j.compag.2019.105010.
   Web of Science ®Google Scholar
• Heidari JH, Najafi A, Alavi S. 2018. Pavement deterioration modeling for forest roads based on logistic regression and artificial neural networks. Croat J For Eng. 39(2):271–287.
   Web of Science ®Google Scholar
• Heidari MJ, Najafi A, Borges JG. 2022. Forest roads damage detection based on deep learning algorithms. Scand J Forest Res. 37(5–8):366–375. doi: 10.1080/02827581.2022.2147213.
   Web of Science ®Google Scholar
• van der Horst BB, Lindenbergh RC, Puister SWJ. 2019. Mobile laser scan data for road surface damage detection. Int Arch Photogramm Remote Sens Spatial Inf Sci. XLII-2/W13:1141–1148. doi: 10.5194/isprs-archives-XLII-2-W13-1141-2019.
   Google Scholar
• Jocher G, Chaurasia A, Stoken A, Borovec J, Michael K, Fang J, Yifu Z, Wong C, Montes D, Wang Z. 2022. Ultralytics/Yolov5: V70 - YOLOv5 SOTA Realtime Instance Segmentation [Internet]. [accessed 2022 Dec 8]. doi: 10.5281/ZENODO.3908559.
   Google Scholar
• Kim YM, Kim YG, Son SY, Lim SY, Choi BY, Choi DH. 2022. Review of recent automated pothole-detection methods. Appl Sci. 12(11):5320. doi: 10.3390/app12115320.
   Google Scholar
• Lanbruksdirektorat. 2016. Normaler for landbruksveier med byggebeskrivelse [standards for agricultural roads with construction description]. https://s37614.pcdn.co/wp-content/uploads/Normaler_for_landbruksveier_2016.pdf.
   Google Scholar
• Luiten J, Ošep A, Dendorfer P, Torr P, Geiger A, Leal-Taixé L, Leibe B. 2021. HOTA: a higher order metric for evaluating multi-object tracking. Int J Comput Vis. 129(2):548–578. doi: 10.1007/s11263-020-01375-2.
   PubMed Web of Science ®Google Scholar
• Maeda H, Sekimoto Y, Seto T, Kashiyama T, Omata H. 2018. Road damage detection and classification using deep neural networks with smartphone images: road damage detection and classification. Comput Aided Civ Infrastruct Eng. 33(12):1127–1141. doi: 10.1111/mice.12387.
   Web of Science ®Google Scholar
• Mohiyuddin A, Basharat A, Ghani U, Peter V, Abbas S, Naeem OB, Rizwan M. 2022. Breast tumor detection and classification in mammogram images using modified YOLOv5. In: Network Asghar M, editor. Computational and mathematical methods in medicine. pp. 1–16. doi: 10.1155/2022/1359019.
   Google Scholar
• MOT Challenge. [accessed 2023 Jan 3]. https://motchallenge.net/instructions/.
   Google Scholar
• New Zealand forest road engineering manual. 2020. Updated February 2020. Wellington, New Zealand: NZ Forest Owners Association.
   Google Scholar
• Nienaber S, Booysen MJ, Kroon RS. 2015. Detecting potholes using simple image processing techniques and real-world footage [Internet]. [accessed 2022 Dec 8]. doi: 10.13140/RG.2.1.3121.8408.
   Google Scholar
• Nienaber S, Kroon RS, Booysen MJ. 2015. A comparison of low-cost monocular vision techniques for pothole distance estimation. In: 2015 IEEE Symposium Series on Computational Intelligence [Internet]. Cape Town, South Africa: IEEE; [accessed 2022 Dec 8]. p. 419–426. doi: 10.1109/SSCI.2015.69.
   Google Scholar
• OpenStreetMap. OpenStreetMap [Internet]. [accessed 2023 Jan 3]. https://www.openstreetmap.org/.
   Google Scholar
• Picchio R, Proto AR, Civitarese V, Di Marzio N, Latterini F. 2019. Recent contributions of some fields of the electronics in development of forest operations technologies. Electron. 8(12):1465. doi: 10.3390/electronics8121465.
   Web of Science ®Google Scholar
• Puliti S, Astrup R. 2022. Automatic detection of snow breakage at single tree level using YOLOv5 applied to UAV imagery. Int J App Earth Obser And Geoinfor. 112:102946. doi: 10.1016/j.jag.2022.102946.
   Web of Science ®Google Scholar
• Puliti S, McLean JP, Cattaneo N, Fischer C, Astrup R, Kattenborn T. 2022. Tree height-growth trajectory estimation using uni-temporal UAV laser scanning data and deep learning. An Int J For Res. 96(1):37–48. doi: 10.1093/forestry/cpac026.
   Google Scholar
• Redmon J, Divvala S, Girshick R, Farhadi A. 2016. You only look once: unified, real-time object detection. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) [Internet]. Las Vegas, NV, USA: IEEE; [accessed 2023 Jan 9]. p. 779–788. doi: 10.1109/CVPR.2016.91.
   Google Scholar
• Roberts R, Inzerillo L, Di Mino G. 2020. Exploiting low-cost 3D imagery for the purposes of detecting and analyzing pavement distresses. Infrastruct. 5(1):6. doi: 10.3390/infrastructures5010006.
   Google Scholar
• Saarenketo T, Aho S. 2005. Managing spring thaw weakening on low volume roads [Internet]. Inverness, Scotland: The Highland Council, Transport, Environmental & Community Service. https://www.roadex.org/wp-content/uploads/2014/01/2_3-Spring_Thaw_Weakening_l.pdf
   Google Scholar
• Sattar S, Li S, Chapman M. 2018. Road surface monitoring using smartphone sensors: a review. Sensors. 18(11):3845. doi: 10.3390/s18113845.
   PubMed Web of Science ®Google Scholar
• Starke M, Geiger C. 2022. Machine vision based waterlogged area detection for gravel road condition monitoring. Int J For Eng. 33(3):243–249. doi: 10.1080/14942119.2022.2064654.
   Web of Science ®Google Scholar
• Susnjar M, Pandur Z, Nevecerel H, Lepoglavec K, Bacic M. 2020. Development of a new method for assessing condition of forest road surface. JCE. 71(12):1121–1128. doi: 10.14256/JCE.2462.2018.
   Google Scholar
• Talbot B, Pierzchala M, Astrup R. 2017. Applications of remote and proximal sensing for improved precision in forest operations. Croat J For Eng. 38(2):327–336.
   Web of Science ®Google Scholar
• Waga K, Tompalski P, Coops NC, White JC, Wulder MA, Malinen J, Tokola T. 2020. Forest road status assessment using airborne laser scanning. Forest Sci. 66(4):501–508. doi: 10.1093/forsci/fxz053.
   Web of Science ®Google Scholar
• Zhou K, Yang Y, Cavallaro A, Xiang T. 2019. Omni-scale feature learning for person re-identification [Internet]. [accessed 2022 Dec 8]. doi: 10.48550/ARXIV.1905.00953.
   Google Scholar