INVENTARIO FORESTAL CON VISION ARTIFICIAL EMPLEANDO UN CARRO ROBOT GUIADO POR GPS (FOREST INVENTORY WITH ARTIFICIAL VISION USING A ROBOT CART GUIDED BY GPS)
Resumen
El inventario forestal es una herramienta que provee de información periódica donde se muestra la estructura, condiciones y dinámica de los bosques del país. En este trabajo se presenta un diseño utilizando un robot móvil autónomo que usa una tarjeta RaspBerry Pi 4B como controlador y guiado por un módulo GPS controlado por un Arduino Uno conectado por comunicación serial a la tarjeta principal. El robot tiene implementada una cámara, que realiza la captura de imágenes de los árboles que se están reconociendo, los cuales se dividen en 3: jobo (spondias mombin), aguacate (persea americana) y común, que fueron detectados gracias al entrenamiento de un modelo de aprendizaje que uso 87 imágenes. Se utiliza el modelo de visión artificial Yolov8s, obteniéndose una precisión de casi el 90%. Los resultados muestran un reconocimiento efectivo, que puede mejorarse ampliando la base de datos de los árboles y una mayor cantidad de imágenes.
Palabras Clave: Inventario forestal, Robot autónomo móvil, Visión artificial, Yolov8.
Abstract
The forest inventory is a tool that provides periodic information showing the structure, conditions and dynamics of the country's forests. This work presents a design using an autonomous mobile robot that uses a RaspBerry Pi 4B board as a controller and guided by a GPS module controlled by an Arduino Uno connected by serial communication to the main board. The robot has a camera implemented, which captures images of the trees that are being recognized, which are divided into 3: jobo (spondias mombin), avocado (Persea Americana) and common, which were detected thanks to the training of a learning model that uses 87 images. The Yolov8s artificial vision model is used, obtaining an accuracy of almost 90%. The results show effective recognition, which can be improved by expanding the tree database and a greater number of images.
Keywords: Artificial vision, Forest inventory, Mobile autonomous robot, Yolov8.
Texto completo:
PDFReferencias
Ayrey, E., & Hayes, D. J., (2018). The Use of Three-Dimensional Convolutional Neural Networks to Interpret LiDAR for Forest Inventory. Remote Sensing, 10(4), 649.
Chirici, G., Giannetti, F., D’Amico, G., Vangi, E., Francini, S., Borghi, C., Corona, P., & Travaglini, D., (2023). Robotics in Forest Inventories: SPOT’s First Steps. Forests, 14(11), 2170. https://doi.org/10.3390/f14112170.
Da Silva, D. Q., dos Santos, F. N., Filipe, V., Sousa, A. J., & Oliveira, P. M., (2022). Edge AI-Based Tree Trunk Detection for Forestry Monitoring Robotics. Robotics, 11(6), 136. https://doi.org/10.3390/robotics11060136.
De Dios, J., (2022). Inventario nacional forestal y de suelos, estrategia de campo y análisis de datos. https://www.gob.mx/inifap/articulos/inventario-nacional-forestal-y-de-suelos-estrategia-de-campo-y-analisis-de-datos.
Eroshenkova, D. A., Terekhov, V. I., Khusnetdinov, D. R., & Chumachenko, S. I., (2020). Automated Determination of Forest-Vegetation Characteristics with the Use of a Neural Network of Deep Learning, pp. 295–302. https://doi.org/10.1007/978-3-030-30425-6_34.
FAO. Organización de las Naciones Unidas para la Alimentación y la Agricultura, (2024). Inventario Forestal. https://www.fao.org/sustainable-forest-management/toolbox/modules/forest-inventory/basic-knowledge/es/.
Ferdoush, S., & Li, X., (2014). Wireless Sensor Network System Design Using Raspberry Pi and Arduino for Environmental Monitoring Applications. Procedia Computer Science, 34, 103–110. https://doi.org/10.1016/j.procs.2014.07.059.
Hamedianfar, A., Mohamedou, C., Kangas, A., & Vauhkonen, J., (2022). Deep learning for forest inventory and planning: a critical review on the remote sensing approaches so far and prospects for further applications. Forestry: An International Journal of Forest Research, 95(4), 451–465. https://doi.org/10.1093/forestry/cpac002.
INEGI, (2022). Censo Agropecuario. https://www.inegi.org.mx/programas/ca/2022.
James, N., Ong, L. Y., & Leow, M. C., (2022). Exploring Distributed Deep Learning Inference Using Raspberry Pi Spark Cluster. Future Internet, 14(8), 220. https://doi.org/10.3390/fi14080220.
Reyes, J., Rodríguez, J., Pimienta, D., Fuentes, M., Marroquín, P., Merino, A., Aguirre, J., (2022). Diversidad y estructura de los árboles de sombra asociados a Coffea arabica L. en el Soconusco, Chiapas. Revista Mexicana de Ciencias Forestales, 13(71). https://doi.org/10.29298/rmcf.v13i71.1191.
Sun, H., Yan, H., Hassanalian, M., Zhang, J., & Abdelkefi, A., (2023). UAV Platforms for Data Acquisition and Intervention Practices in Forestry: Towards More Intelligent Applications. Aerospace, 10(3), 317. https://doi.org/10.3390/aerospace10030317.
Vandapel, N., Donamukkala, R. R., & Hebert, M., (2006). Unmanned Ground Vehicle Navigation Using Aerial Ladar Data. The International Journal of Robotics Research, 25(1), 31–51. https://doi.org/10.1177/0278364906061161.
Wei, J., Gong, H., Li, S., You, M., Zhu, H., Ni, L., Luo, L., Chen, M., Chao, H., Hu, J., Zhu, C., Wang, H., Liu, J., Nian, J., Fan, W., Mu, Y., & Sun, Y., (2024). Improving the Accuracy of Agricultural Pest Identification: Application of AEC-YOLOv8n to Large-Scale Pest Datasets. Agronomy, 14(8), 1640. https://doi.org/10.3390/agronomy14081640.
Wu, B., Liang, A., Zhang, H., Zhu, T., Zou, Z., Yang, D., Tang, W., Li, J., & Su, J., (2021). Application of conventional UAV-based high-throughput object detection to the early diagnosis of pine wilt disease by deep learning. Forest Ecology and Management, 486, 118986. https://doi.org/10.1016/j.foreco.2021.118986.
Xiao, X., Chen, C., Skitmore, M., Li, H., & Deng, Y., (2024). Exploring Edge Computing for Sustainable CV-Based Worker Detection in Construction Site Monitoring: Performance and Feasibility Analysis. Buildings, 14(8), 2299. https://doi.org/10.3390/buildings14082299.
URL de la licencia: https://creativecommons.org/licenses/by/3.0/deed.es
Pistas Educativas está bajo la Licencia Creative Commons Atribución 3.0 No portada. 
TECNOLÓGICO NACIONAL DE MÉXICO / INSTITUTO TECNOLÓGICO DE CELAYA
Antonio García Cubas Pte #600 esq. Av. Tecnológico, Celaya, Gto. México
Tel. 461 61 17575 Ext 5450 y 5146
pistaseducativas@itcelaya.edu.mx