Accurate estimation of tree stem perimeter is essential for robotic forest mapping and inventory applications. While light detection and ranging (LiDAR)–camera fusion enables automated stem detection and geometric reconstruction, perimeter estimates derived from partial LiDAR observations exhibit systematic bias due to occlusions, limited angular coverage, and violations of ideal cylindrical assumptions. These effects introduce systematic errors that cannot be fully resolved by geometric reconstruction or temporal smoothing alone. This paper proposes a residual learning framework that enhances geometric perimeter estimation by learning a data-driven correction term while preserving the interpretability of the underlying model. A mobile robot equipped with a three-dimensional LiDAR and an RGB camera collects synchronized data in forest environments. Tree stems are detected in RGB images and associated with LiDAR points through calibrated projection. A geometric baseline perimeter is computed by fitting a circular model to a diameter-at-breast-height cross-section extracted from incomplete LiDAR observations. A shallow multilayer perceptron then predicts the residual between the geometric estimate and manually measured ground-truth perimeter using observation-derived features. Filtering improves stability but does not remove systematic bias, whereas residual learning achieves consistent bias correction. Experimental results demonstrate reductions exceeding 40% in both mean absolute and root mean squared errors, together with a substantial improvement in the coefficient of determination from 0.48 to 0.86. Error distributions become more centered and consistent across varying sensing distances and stem sizes, confirming robust generalization to unseen trees. The proposed method operates as a lightweight post-processing module, making it suitable for real-time deployment on mobile forestry robots.

1. [1] L. Deng, M. Fujio, X. Lin, and R. Ota, “Labor shortage and early robotization in Japan,” Econ. Lett., Vol.233, Article No.111404, 2023. https://doi.org/10.1016/j.econlet.2023.111404
2. [2] H. Gupta, H. Andreasson, A. J. Lilienthal, and P. Kurtser, “Robust scan registration for navigation in forest environment using low-resolution LiDAR sensors,” Sensors, Vol.23, No.10, Article No.4736, 2023. https://doi.org/10.3390/s23104736
3. [3] Y. Sheng, Q. Zhao, X. Wang, Y. Liu, and X. Yin, “Tree diameter at breast height extraction based on mobile laser scanning point cloud,” Forests, Vol.15, No.4, Article No.590, 2024. https://doi.org/10.3390/f15040590
4. [4] D. Tiozzo Fasiolo, L. Scalera, E. Maset, and A. Gasparetto, “Field evaluation of an autonomous mobile robot for navigation and mapping in forest,” Robotics, Vol.14, No.7, Article No.89, 2025. https://doi.org/10.3390/robotics14070089
5. [5] T. Ota et al., “Estimating aboveground carbon using airborne LiDAR in Cambodian tropical seasonal forests for REDD+ implementation,” J. For. Res., Vol.20, No.6, pp. 484-492, 2015. https://doi.org/10.1007/s10310-015-0504-3
6. [6] J. Gonzalez de Tanago et al., “Estimation of above-ground biomass of large tropical trees with terrestrial LiDAR,” Methods Ecol. Evol., Vol.9, No.2, pp. 223-234, 2018. https://doi.org/10.1111/2041-210X.12904
7. [7] G. Fan, L. Nan, Y. Dong, X. Su, and F. Chen, “AdQSM: A new method for estimating above-ground biomass from TLS point clouds,” Remote Sens., Vol.12, No.18, Article No.3089, 2020. https://doi.org/10.3390/RS12183089
8. [8] L. Xu et al., “Forest aboveground biomass estimation based on spaceborne LiDAR combining machine learning model and geostatistical method,” Front. Plant Sci., Vol.15, Article No.1428268, 2024. https://doi.org/10.3389/fpls.2024.1428268
9. [9] Z. M. Bhebhe, X. Liu, Z. Zhang, and D. R. Paudyal, “Estimation of tree diameter at breast height (DBH) and biomass from allometric models using LiDAR data: A case of the Lake Broadwater Forest in Southeast Queensland, Australia,” Remote Sens., Vol.17, No.14, Article No.2523, 2025. https://doi.org/10.3390/rs17142523
10. [10] A. Bornand, N. Rehush, F. Morsdorf, E. Thürig, and M. Abegg, “Individual tree volume estimation with terrestrial laser scanning: Evaluating reconstructive and allometric approaches,” Agric. For. Meteorol., Vol.341, Article No.109654, 2023. https://doi.org/10.16904/envid
11. [11] Y. Wu, S. Zhong, Y. Ma, Y. Zhang, and M. Liu, “Application of SLAM-based mobile laser scanning in forest inventory: Methods, progress, challenges, and perspectives,” Forests, Vol.16, No.6, Article No.920, 2025. https://doi.org/10.3390/f16060920
12. [12] S. Ma, Y. Chen, Z. Li, J. Chen, and X. Zhong, “Improved cylinder-based tree trunk detection in LiDAR point clouds for forestry applications,” Sensors, Vol.25, No.3, Article No.714, 2025. https://doi.org/10.3390/s25030714
13. [13] T. P. Pitkänen, P. Raumonen, and A. Kangas, “Measuring stem diameters with TLS in boreal forests by complementary fitting procedure,” ISPRS J. Photogramm. Remote Sens., Vol.147, pp. 294-306, 2019. https://doi.org/10.1016/j.isprsjprs.2018.11.027
14. [14] S. C. Florea, I. Dutcă, and M.-D. Niță, “Tradeoffs and limitations in determining tree characteristics using 3D pointclouds from terrestrial laser scanning: A comparison of reconstruction algorithms on European bech (Fagus sylvatica L.) trees,” Ann. For. Res., Vol.67, No.2, pp. 185-199, 2024. https://doi.org/10.15287/afr.2024.3885
15. [15] X. Liang et al., “Close-range remote sensing of forests: The state of the art, challenges, and opportunities for systems and data acquisitions,” IEEE Geosci. Remote Sens. Mag., Vol.10, No.3, pp. 32-71, 2022. https://doi.org/10.1109/MGRS.2022.3168135
16. [16] M. Mokroš et al., “Evaluation of close-range photogrammetry image collection methods for estimating tree diameters,” ISPRS Int. J. Geo-Inf., Vol.7, No.3, Article No.93, 2018. https://doi.org/10.3390/ijgi7030093
17. [17] R. Fekry, W. Yao, L. Cao, and X. Shen, “Ground-based/UAV-LiDAR data fusion for quantitative structure modeling and tree parameter retrieval in subtropical planted forest,” For. Ecosyst., Vol.9, Article No.100065, 2022. https://doi.org/10.1016/j.fecs.2022.100065
18. [18] P. Wan et al., “Quantification of occlusions influencing the tree stem curve retrieving from single-scan terrestrial laser scanning data,” For. Ecosyst., Vol.6, Article No.43, 2019. https://doi.org/10.1186/s40663-019-0203-1
19. [19] A. Nurunnabi, F. Teferle, A. Novo, J. Balado, and E. Ientilucci, “Derivation of tree stem curve and volume using point clouds,” Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci., Vol.XLVIII-4/W11-2024, pp. 81-88, 2024. https://doi.org/10.5194/isprs-archives-XLVIII-4-W11-2024-81-2024
20. [20] S. Macenski, T. Foote, B. Gerkey, C. Lalancette, and W. Woodall, “Robot operating system 2: Design, architecture, and uses in the wild,” Sci. Robot., Vol.7, No.66, Article No.eabm6074, 2022. https://doi.org/10.1126/scirobotics.abm6074
21. [21] T. Diwan, G. Anirudh, and J. V. Tembhurne, “Object detection using YOLO: Challenges, architectural successors, datasets and applications,” Multimed. Tools Appl., Vol.82, No.6, pp. 9243-9275, 2023. https://doi.org/10.1007/s11042-022-13644-y
22. [22] A. A. Murat and M. S. Kiran, “A comprehensive review on YOLO versions for object detection,” Eng. Sci. Technol. Int. J., Vol.70, Article No.102161, 2025. https://doi.org/10.1016/j.jestch.2025.102161
23. [23] M. L. Ali and Z. Zhang, “The YOLO framework: A comprehensive review of evolution, applications, and benchmarks in object detection,” Computers, Vol.13, No.12, Article No.336, 2024. https://doi.org/10.3390/computers13120336
24. [24] K. Levenberg, “A method for the solution of certain non-linear problems in least squares,” Q. Appl. Math., Vol.2, No.2, pp. 164-168, 1944. https://doi.org/10.1090/qam/10666
25. [25] D. W. Marquardt, “An algorithm for least-squares estimation of nonlinear parameters,” J. Soc. Ind. Appl. Math., Vol.11, No.2, pp. 431-441, 1963. https://doi.org/10.1137/0111030