Abstract
The development cadence of Deep Learning algorithms is extremely high, with the development of autonomous navigation systems and especially autonomous vehicles in the forefront. Growing environmental awareness has directed efforts toward the development of autonomous systems for the maintenance and preservation of forested areas. Unlike urban areas, available datasets on these environments are scarce and incomplete. In addition, the complex and unstructured nature of forested areas and the tedious labeling process lead to a high rate of mislabeling. Given the success that the use of synthetic data has had in model training, this work proposes an approach that helps overcome these limitations. The SynPhoRest simulator can generate photorealistic synthetic data in the form of RGB images, semantic segmentation maps, and depth maps from procedurally generated virtual forest environments. The system supports both manual and automatic extraction and can generate 100 sets of data in about an hour.
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
Notes
- 1.
AAA (triple-A). Video-games with a high quality and production value, developed by established and reputable game development studios.
References
FAO of the United Nations. A Fresh Perspective - Global Forest Resources Assessment 2020. https://www.fao.org/forest-resourcesassessment/2020/en/. Accessed 05 July 2023
Giusti, A., et al.: A machine learning approach to visual perception of forest trails for mobile robots. IEEE Robot. Automat. Lett. 1(2), 661–667 (2016). https://doi.org/10.1109/LRA.2015.2509024
Munappy, A., Bosch, J., Olsson, H.H., Arpteg, A., Brinne, B.: Data management challenges for deep learning. In: 2019 45th Euromicro Conference on Software Engineering and Advanced Applications (SEAA), Kallithea, pp. 140–147 (2019). https://doi.org/10.1109/SEAA.2019.00030
Hu, Q., et al.: RandLA-net: efficient semantic segmentation of large-scale point clouds. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, pp. 11105–11114 (2020). https://doi.org/10.1109/CVPR42600.2020.01112
V7Labs. V7 Darwin - Auto-Annotate Complex Objects 10x Faster. https://www.v7labs.com/auto-annotation. Accessed 04 July 2023
He, R., et al.: Is synthetic data from generative models ready for image recognition? arXiv preprint arXiv:2210.07574 [cs.CV] (2023)
Richter, S.R., Vineet, V., Roth, S., Koltun, V.: Playing for data: ground truth from computer games. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) Computer Vision. ECCV 2016. LNCS, vol. 9906, pp. 102–118. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46475-6_7
Brostow, G.J., Fauqueur, J., Cipolla, R.: Semantic object classes in video: a high-definition ground truth database. Pattern Recogn. Lett. 30(2), 88–97 (2009). https://doi.org/10.1016/j.patrec.2008.04.005
Yue, X., Wu, B., Seshia, S.A., Keutzer, K., Sangiovanni-Vincentelli, A.L.: A LiDAR Point Cloud Generator: From a Virtual World to Autonomous Driving. arXiv preprint arXiv: 1804.00103 [cs.CV] (2018)
Wu, B., Wan, A., Yue, X., Keutzer, K.: SqueezeSeg: convolutional neural nets with recurrent CRF for real-time road-object segmentation from 3D LiDAR point cloud. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), Brisbane, pp. 1887–1893 (2018). https://doi.org/10.1109/ICRA.2018.8462926
Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, pp. 3354–3361 (2012). https://doi.org/10.1109/CVPR.2012.6248074
Hurl, B., Czarnecki, K., Waslander, S.: Precise synthetic image and LiDAR (PreSIL) dataset for autonomous vehicle perception. IEEE Intell. Veh. Symp. (IV) Paris, France 2019, 2522–2529 (2019). https://doi.org/10.1109/IVS.2019.8813809
Griffiths, D., Boehm, J.: Synthcity: a large scale synthetic point cloud. arXiv:1907.04758 [cs.CV] (2019)
Wrenninge, M., Unger, J.: Synscapes: a photorealistic synthetic dataset for street scene parsing. arXiv:1810.08705 [cs.CV] (2018)
Nunes, R., Ferreira, J., Peixoto, P.: Procedural generation of synthetic forest environments to train machine learning algorithms. https://openreview.net/forum?id=rpzgjNCe4G9
Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). arXiv:1604.01685 [cs.CV] (2016)
Perlin, K.: An image synthesizer. SIGGRAPH Comput. Graph. 19(3), 287–296 (1985). https://doi.org/10.1145/325165.325247
Perlin, K.: Noise hardware (2001). https://redirect.cs.umbc.edu/~olano/s2001c24/ch09.pdf. Accessed 30 June 2023
devdad. Simplexnoise plugin (2020). https://github.com/devdad/SimplexNoise. Accessed 14 Jan 2023. Commit: b57598706afd8fc4d50164da1ed58515595699b2
Unreal Engine 5.1 Documentation - Procedural Mesh Component (2022). https://docs.unrealengine.com/5.1/enUS/API/Plugins/ProceduralMeshComponent/UProceduralMeshComponent/. Accessed 23 June 2023
Adobe Inc. Adobe Photoshop. https://www.adobe.com/products/photoshop.html. Accessed 04 July 2023
Acknowledgement
This publication was co-financed by Programa Operacional Regional do Centro, Portugal 2020, European Union FEDER Fund, Project: CENTRO-01-0247-FEDER-045931 (SAFEFOREST - Semi-Autonomous Robotic System for Forest Cleaning and Fire Prevention).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Bidault, R., Peixoto, P. (2024). SynPhoRest - A Procedural Generation Tool of Synthetic Photorealistic Forest Datasets. In: Marques, L., Santos, C., Lima, J.L., Tardioli, D., Ferre, M. (eds) Robot 2023: Sixth Iberian Robotics Conference. ROBOT 2023. Lecture Notes in Networks and Systems, vol 976. Springer, Cham. https://doi.org/10.1007/978-3-031-58676-7_6
Download citation
DOI: https://doi.org/10.1007/978-3-031-58676-7_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-58675-0
Online ISBN: 978-3-031-58676-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)