Abstract
Accurate location of access roads is important for forest management, in particular in mountain areas. In this paper, we are interested in their detection from LiDAR data using deep learning approaches. For this, we use images computed from an interpolated surface, called digital terrain model (DTM), of the 3D point cloud. In order to train and validate the neural network models, two ground truth datasets associated to DTM images are considered: (1) manual digitization of the road centerlines and (2) automatic extraction followed by supervised completion using two softwares based on discrete geometry tools. The trained network models are then evaluated over a test dataset using standard measures such as precision, recall, F-measure and prediction time.
Keywords
- Road detection
- mountainous area
- LiDAR images
- CNN
This is a preview of subscription content, access via your institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Clode, S., Rottensteiner, F., Kootsookos, P., Zelnicker, E.: Detection and vectorization of roads from lidar data. Photogramm. Eng. Remote Sens. 73(5), 517–536 (2007). https://doi.org/10.14358/PERS.73.5.517
David, N., Mallet, C., Pons, T., Chauve, A., Bretar, F.: Pathway detection and geometrical description from ALS data in forested montaneous areas. Int. Archives Photogramm., Remote Sens. Spatial Inform. Sci. 38(part 3/W8), 242–247 (2009)
Debled-Rennesson, I., Feschet, F., Rouyer-Degli, J.: Optimal blurred segments decomposition of noisy shapes in linear time. Comput. Graph. 30(1), 30–36 (2006). https://doi.org/10.1016/j.cag.2005.10.007
Even, P., Grzesznik, A., Gebhardt, A., Chenal, T., Even, P., Ngo, P.: Interactive extraction of linear structures from LiDAR raw data for archaeomorphological structure prospection. Int. Archives Photogramm., Remote Sensing Spatial Inform. Sci. XLIII-B2-2021, pp. 153–161 (2021). https://doi.org/10.5194/isprs-archives-XLIII-B2-2021-153-2021
Even, P., Ngo, P.: AMREL: Automatic mountain road extraction from LiDAR data. https://github.com/evenp/AMREL.git/ (2022)
Even, P., Ngo, P.: ILSD: Interactive linear structure detector. https://github.com/evenp/ILSD.git/ (2022)
Even, P., Ngo, P.: Live extraction of curvilinear structures from LiDAR raw data. ISPRS Ann. Photogramm. Remote Sensing Spatial Inform. Sci. 2 211–219 (2020). https://doi.org/10.5194/isprs-annals-V-2-2020-211-2020
Even, P., Ngo, P.: Automatic forest road extraction from lidar data of mountainous areas. In: First Joint Conference on Discrete Geometry and Mathematical Morphology, pp. 93–106 (2021). https://doi.org/10.1007/978-3-030-76657-3_6
Even, P., Ngo, P., Kerautret, B.: Thick line segment detection with fast directional tracking. In: Proceedings of 20th International Conference on Image Analysis and Processing, pp. 159–170 (2019). https://doi.org/10.1007/978-3-030-30645-8_15
Ferraz, A., Mallet, C., Chehata, N.: Large-scale road detection in forested montainous areas using airborne topographic lidar data. ISPSR J. Photogramm. Remote Sensing 112, 23–36 (2016). https://doi.org/10.1016/j.isprsjprs.2015.12.002
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press (2016)
Hui, Z., Hu, Y., Jin, S., Yevenyo, Y.Z.: Road centerline extraction from airborne LiDAR point cloud based on hierarchical fusion and optimization. ISPRS J. Photogramm. Remote. Sens. 118, 22–36 (2016). https://doi.org/10.1016/j.isprsjprs.2016.04.003
IGN: LIDAR HD - Une cartographie 3D du sol et du sursol de la France. https://geoservices.ign.fr/lidarhd/ (2022)
Keras: Python interface for artificial neural networks. https://keras.io/ (2022)
Kraemer, C., et al.: ArchéoGÉographie du premier Remiremont et de ses abords : le Saint-Mont et le massif du Fossard. Rapport de Projet AGER 1, Université de Lorraine (2018)
Liu, Q., Kampffmeyer, M., Jenssen, R., Salberg, A.B.: Road mapping in LiDAR images using a joint-task dense dilated convolutions merging network. In: IEEE International Geoscience and Remote Sensing Symposium, pp. 5041–5044 (2019). https://doi.org/10.1109/IGARSS.2019.8900082
Liu, Q., Kampffmeyer, M., Jenssen, R., Salberg, A.B.: Dense dilated convolutions’ merging network for land cover classification. IEEE Trans. Geosci. Remote Sens. 58(9), 6309–6320 (2020). https://doi.org/10.1109/TGRS.2020.2976658
Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: 7th International Conference on Learning Representations (2019). https://doi.org/10.48550/arXiv.1711.05101
Merveille, O., Naegel, B., Talbot, H., Najman, L., Passat, N.: 2D filtering of curvilinear structures by ranking the orientation responses of path operators (RORPO). Image Processing On Line 7, 246–261 (2017). https://doi.org/10.5201/ipol.2017.207
Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. In: 18\(^{th}\) International Conference on Medical Image Computing and Computer-Assisted Interventions, pp. 234–241 (10 2015). https://doi.org/10.1007/978-3-319-24574-4_28
Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211–252 (2015). https://doi.org/10.1007/s11263-015-0816-y
Salberg, A.B., Trier, Ø.D., Kampffmeyer, M.: Large-scale mapping of small roads in lidar images using deep convolutional neural networks. In: Scandinavian Conference on Image Analysis, pp. 193–204 (2017). https://doi.org/10.1007/978-3-319-59129-2_17
TensorFlow: Software library for machine learning and artificial intelligence. https://www.tensorflow.org/ (2022)
White, R.A., Dietterick, B.C., Mastin, T., Strohman, R.: Forest roads mapped using LiDAR in steep forested terrain. Remote Sensing 2(4), 1120–1141 (2010). https://doi.org/10.3390/rs2041120
Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: CBAM: Convolutional block attention module. In: Proceedings of the European Conference on Computer Vision, pp. 3–19 (2018). https://doi.org/10.1007/978-3-030-01234-2_1
Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. In: International Conference on Learning Representations (2016). https://doi.org/10.48550/arXiv.1511.07122
Zhang, T.Y., Suen, C.Y.: A fast parallel algorithm for thinning digital patterns. Commun. ACM 27(3), 236–239 (1984). https://doi.org/10.1145/357994.358023
Acknowledgements
DTM images are derived from Fossard LiDAR data acquired in scope of the PCR AGER project (Projet collectif de recherche ”Archéologie et GEoarchéologie du premier Remiremont et de ses abords”), dir. Charles Kraemer, HISCANT Laboratory, Université de Lorraine.
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
Georges, P., Ngo, P., Even, P. (2023). Automatic Forest Road Extraction from LiDAR Data Using Convolutional Neural Networks. In: Kerautret, B., Colom, M., Krähenbühl, A., Lopresti, D., Monasse, P., Perret, B. (eds) Reproducible Research in Pattern Recognition. RRPR 2022. Lecture Notes in Computer Science, vol 14068. Springer, Cham. https://doi.org/10.1007/978-3-031-40773-4_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-40773-4_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-40772-7
Online ISBN: 978-3-031-40773-4
eBook Packages: Computer ScienceComputer Science (R0)
-
Published in cooperation with
http://www.iapr.org/
