Deep Learning-Based Tree Stem Segmentation for Robotic Eucalyptus Selective Thinning Operations
Authors: 
Daniel Queirós da Silva, Tiago Ferreira Rodrigues, Armando Jorge Sousa, Filipe Neves dos Santos, Vítor FilipeAuthors Info & Claims
Pages 376 - 387
Abstract
Selective thinning is a crucial operation to reduce forest ignitable material, to control the eucalyptus species and maximise its profitability. The selection and removal of less vigorous stems allows the remaining stems to grow healthier and without competition for water, sunlight and nutrients. This operation is traditionally performed by a human operator and is time-intensive. This work simplifies selective thinning by removing the stem selection part from the human operator’s side using a computer vision algorithm. For this, two distinct datasets of eucalyptus stems (with and without foliage) were built and manually annotated, and three Deep Learning object detectors (YOLOv5, YOLOv7 and YOLOv8) were tested on real context images to perform instance segmentation. YOLOv8 was the best at this task, achieving an Average Precision of 74% and 66% on non-leafy and leafy test datasets, respectively. A computer vision algorithm for automatic stem selection was developed based on the YOLOv8 segmentation output. The algorithm managed to get a Precision above 97% and a 81% Recall. The findings of this work can have a positive impact in future developments for automatising selective thinning in forested contexts.
References
[1]
Bishop CM Pattern Recognition and Machine Learning 2006 Berlin, Heidelberg Springer
[2]
Bolya, D., Zhou, C., Xiao, F., Lee, Y.J.: Yolact: real-time instance segmentation. In: ICCV (2019)
[3]
Bolya D, Zhou C, Xiao F, and Lee YJ Yolact++ better real-time instance segmentation IEEE Trans. Pattern Anal. Mach. Intell. 2022 44 2 1108-1121
[4]
Cai Z and Vasconcelos N Cascade R-CNN: high quality object detection and instance segmentation IEEE Trans. Pattern Anal. Mach. Intell. 2021 43 5 1483-1498
[5]
Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1280–1289 (2022).
[6]
da Silva, D.Q., dos Santos, F.N., Filipe, V., Sousa, A.J.: Tree trunks cross-platform detection using deep learning strategies for forestry operations. In: Tardioli, D., Matellán, V., Heredia, G., Silva, M.F., Marques, L. (eds.) ROBOT2022: fifth Iberian Robotics Conference, pp. 40–52. Springer International Publishing, Cham (2023).
[7]
da Silva, D.Q., dos Santos, F.N., Filipe, V., Sousa, A.J., Oliveira, P.M.: Edge AI-based tree trunk detection for forestry monitoring robotics. Robotics 11(6) (2022).
[8]
da Silva, D.Q., dos Santos, F.N., Sousa, A.J., Filipe, V., Boaventura-Cunha, J.: Unimodal and multimodal perception for forest management: review and dataset. Computation 9(12) (2021).
[9]
da Silva, D.Q., dos Santos, F.N., Sousa, A.J., Filipe, V.: Visible and thermal image-based trunk detection with deep learning for forestry mobile robotics. J. Imaging 7(9) (2021).
[10]
FAO: The State of the World’s Forests 2022, p. 28. FAO, Rome (2022)
[11]
Ferreira, D., Morais, S.: Seleção de varas - Manual técnico de apoio á gestão de talhadias (2022)
[12]
Fortin, J.M., Gamache, O., Grondin, V., Pomerleau, F., Giguère, P.: Instance segmentation for autonomous log grasping in forestry operations. In: 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 6064–6071 (2022).
[13]
Fritz, A., Kattenborn, T., Koch, B.: UAV-based photogrammetric point clouds—Tree stem mapping in open stands in comparison to terrestrial laser scanner point clouds. In: The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XL-1/W2(September), pp. 141–146 (2013).
[14]
Gomide, L., Mello, J., Acerbi Júnior, F., Scolforo, J.: Automated selective thinning via multicriteria maetaheuristic procedure. Scientia Forestalis/Forest Sci. 42, 299–306 (2014)
[15]
Grondin, V., Fortin, J.M., Pomerleau, F., Giguère, P.: Tree detection and diameter estimation based on deep learning. Forest.: Int. J. Forest Res. (2022)
[16]
He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask R-CNN. In: Proceedings of the International Conference on Computer Vision (ICCV) (2017)
[17]
Jocher, G.: YOLOv5 by Ultralytics (2020).
[18]
Jocher, G., Chaurasia, A., Qiu, J.: YOLO by Ultralytics (2023)
[19]
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (2021)
[20]
Mokroš, M., Mikita, T., Singh, A., Tomaštík, J., Chudá, J., Wȩżyk, P., Kuželka, K., Surový, P., Klimánek, M., Ziȩba-Kulawik, K., Bobrowski, R., Liang, X.: Novel low-cost mobile mapping systems for forest inventories as terrestrial laser scanning alternatives. Int. J. Appl. Earth Observ. Geoinf. 104 (2021).
[21]
Söderbergh I and Ledermann T Algorithms for simulating thinning and harvesting in five European individual-tree growth simulators: a review Comput. Electron. Agric. 2003 39 2 115-140
[22]
Vestlund K and Hellström T Requirements and system design for a robot performing selective cleaning in young forest stands J. Terrramech. 2006 43 4 505-525
[23]
Vestlund, K., Nordfjell, T., Eliasson, L.: Comparison of human and computer-based selective cleaning. Silva Fennica Monogr. 39(4), 509–523 (2005).
[24]
Vestlund, K., Nordfjell, T., Eliasson, L., Karlsson, A.: A decision support system for selective cleaning. Silva Fennica 40(2), 271–289 (2006).
[25]
Wang, C.Y., Bochkovskiy, A., Liao, H.Y.M.: YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors (2022). arXiv:2207.02696
[26]
Zhen Z, Quackenbush LJ, and Zhang L Trends in automatic individual tree crown detection and delineation-evolution of LiDAR data Remote Sens. 2016 8 4 1-26
Index Terms
- Deep Learning-Based Tree Stem Segmentation for Robotic Eucalyptus Selective Thinning Operations
Index terms have been assigned to the content through auto-classification.
Recommendations
Green fruit segmentation and orientation estimation for robotic green fruit thinning of apples
Highlights- Mask R-CNN was used for green fruit and stem instance segmentation.
- Green fruit ...
AbstractApple is a highly valued specialty crop in the U.S. Green fruit thinning is an important operation of apple production, which is the removal of excess fruitlets in the early summer. The task ensures that remaining fruits at harvest ...
Automated segmentation of individual leafy potato stems after canopy consolidation using YOLOv8x with spatial and spectral features for UAV-based dense crop identification
Highlights- YOLOv8x with spatial and spectral information is capable for stem segmentation.
- 0.1 m is a suitable interpolating distance to generate accurate crop height model.
- Height mutation is beneficial to segment dense crop.
- Millimeter-...
AbstractHigh throughput phenotyping of potatoes after canopy consolidation is crucial to crop breeding and management. A prior step is to segment their leafy potato stems, which is challenging after canopy consolidation because potato stems are dense and ...
Transect-Plot Inventory, a Method for Arid and Semi Arid Forest: Case Study Rahim Abad Pistachio Forest
IACSIT-SC '09: Proceedings of the 2009 International Association of Computer Science and Information Technology - Spring ConferenceDetermining the proper inventory method in arid and semi arid region is of great importance, hence transect-plot inventory method was proposed. Rahim Abad Pistachio forest with an area about 1882 ha located in 75 km of north of Mashhad city. These ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
Sep 2023
605 pages
ISBN:978-3-031-49010-1
DOI:10.1007/978-3-031-49011-8
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 15 December 2023
Author Tags
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 23 Feb 2025