On the issue of accuracy of tree curvature and height recognition

The article discusses an innovative approach to assessing tree morphometric parameters using artificial intelligence (AI) and computer vision technologies. The main focus is on the development of a methodology for accurately measuring such characteristics as tree height, base and top diameters, trunk curvature, volume, and surface area. The authors emphasize that traditional measurement methods based on visual inspection and manual measurements have significant errors and require significant labor costs, while automated AI-based systems provide more accurate and reproducible results. Aerial photography from drones and ground photography were used to collect data, which provided comprehensive coverage of tree trunks from different angles. The resulting images were processed using computer vision algorithms, including convolutional neural networks (CNN), as well as 3D modeling methods based on point clouds. This made it possible to create detailed digital models of trees suitable for accurate analysis of their geometric parameters. The results of the study demonstrated the high accuracy of the proposed method: comparison with manual measurements showed minimal discrepancies. In addition, the authors conducted a correlation analysis that revealed the relationships between various tree parameters, which is important for assessing the quality of wood and planning logging. The developed methodology opens up new opportunities for sustainable forest management, allowing to minimize the negative impact on ecosystems and optimize forest management processes. The use of AI in forestry contributes to the transition to more accurate and environmentally friendly working methods, which is especially important in the context of growing demand for wood and the need to preserve biodiversity.

1. Buchelt A., Adrowitzer A., Kieseberg P., Gollob C., Nothdurft A, Eresheim S., Tschiatschek S., Stampfer K., Holzinger A. Exploring artificial intelligence for applications of drones in forest ecology and management. Forest Ecology and Management, 2024, vol. 551, art. no. 121530. DOI: 10.1016/j.foreco.2023.121530.

2. Dorofeeva M.M., Bonetskaya S.A. Comparative analysis of some classical and modern methods for determining leaf surface area. Plant Resources, 2020, vol. 56, no. 2, pp. 182–192. DOI: 10.31857/S0033994620020041. (In Russ.)

3. Gao Q., Kan J. Automatic Forest DBH Measurement Based on Structure from Motion Photogrammetry. Remote Sensing, 2022, vol. 14, iss. 9, art. no. 2064. DOI: 10.3390/rs14092064.

4. Glukhikh V.N., Chernykh A.G. Reasoning of Tree Cross Sections Oval Shaping while Growing with an Inclination. IVUZ. Lesnoy Zhurnal, 2020, no. 5, pp. 166–175. DOI: 10.37482/0536-1036-2020-5-166-175. (In Russ.)

5. Govyadin I.K. Innovative approaches to collecting data on the heights and diameters of trees in plantations. Prospects for the development of the forestry complex: Collection of scientific papers of the international scientific and practical conference. Bryansk, 2023, pp. 179–182. (In Russ.)

6. Govyadin I.K., Karimov B.M. Certificate of state registration of a computer program No. 2023686447 Russian Federation. Accounting and analysis system: No. 2023686474: application. 12.05.2023: publ. 12.06.2023. (In Russ.)

7. Govyadin I.K., Chubinsky A.N., Alekseev A.S. Method for measuring tree diameters based on artificial intelligence technologies. Izvestia Sankt-Peterburgskoj Lesotehniceskoj Akademii, 2024, iss. 249, pp. 177–194. DOI: 10.21266/2079-4304.2024.249.177-194. (In Russ.)

8. Govyadin I.K., Karimov B.M., Sheremet V.A. Certificate of state registration of a computer program No. 2023612089 Russian Federation. Data visualization system: No. 2022668020: appl. 09.30.2022: publ. 01.30.2023. (In Russ.)

9. Lebedev A.V. Inventory of tree plantations in urban areas using a smartphone. Forestry Journal, 2023, T. 13, no. 3 (51), pp. 56–70. DOI: 10.34220/issn.2222-7962/2023.3/5. (In Russ.)

10. Liang J., Gadow K. Applications of Artificial Intelligence in Forest Research and Management. Figshare. Journal Contribution, 2023, pp. 42–45.

11. López-Serrano F.R., Rubio E., Garcia Morote F.A., Manuela Andrés Abellán M., Picazo Córdoba M.I., García Saucedo F. Martínez García E., Sánchez García J.M., Serena Innerarity J., Lucas Carrasco L., García González O., García González J.C. Artificial intelligence-based software (AID-FOREST) for tree detection: A new framework for fast and accurate forest inventorying using LiDAR point clouds. International Journal of Applied Earth Observation and Geoinformation, 2022, vol. 113, art. no. 103014. DOI: 10.1016/j.jag.2022.103014.

12. Mishra R., Mishra D., Agarwal R. Artificial intelligence and machine learning applications in forestry. Journal of Science Research International, 2024, vol. 10, pp. 43–55. DOI: 10.5281/zenodo.14028208.

13. Montaño R.A.N.R., Sanquetta C.R., Wojciechowski J., Mattar E., Corte A.P.D., Todt E. Artificial Intelligence Models to Estimate Biomass of Tropical Forest Trees. Polibits, 2017, vol. 56, pp. 29–37.

14. Raihan A. Artificial intelligence and machine learning applications in forest management and biodiversity conservation. Natural Resources Conservation and Research, 2023, vol. 6, iss. 2, art. no. 3825. DOI: 10.24294/nrcr.v6i2.3825.

15. Sheng W., Li R., Li H., Ma X., Ji Q., Xu F., Fu H. An Automated Method For Stem Diameter Measurement Based on Laser Module and Deep Learning. Plant methods, 2023, vol. 19, art. no. 68. DOI: 10.21203/rs.3.rs-2107489/v1.

16. Voitov D.Yu., Vasilyev S.B., Kormilitsyn D.V. Development of technology for determining tree species using computer vision. Forestry Bulletin, 2023, T. 27, no. 1, pp. 60–66. DOI: 10.18698/2542-1468-2023-1-60-66.