Detection of the farm road positioning scene classification for unmanned driving based on GNSS
Abstract
The positioning environment of farm roads is complex and variable, with defined scenes including open sky, forest, overpass, and tunnel. Relying solely on the Global Navigation Satellite System (GNSS) for positioning throughout the operation of unmanned agricultural machines is insufficient. This study addressed the need for rapid and accurate identification of farm road scene types to select appropriate positioning devices for unmanned agricultural machines. Real-time satellite signal data, obtained through onboard GNSS receivers and combined with broadcast ephemeris data, were used to extract positioning status and track satellite statistics and distribution features. A classifier based on a sliding window was developed, and an inference based on tracked satellite numbers was proposed to detect the farm road positioning scene and calculate the length of different road segments. This study was conducted using real-world working conditions at an agricultural machinery cooperative in Miyun, Beijing, China, where three sets of GNSS data were collected from the farm road using a vehicle-mounted all-frequency GNSS receiver. The results showed that the classification accuracy for open-sky, overpass, and tunnel scenes was 93.96%, with a recall rate of 98.31% and an F1 score of 95.82%. Compared with random forest and XGBoost, the F1 scores improved by 17.83 and 5.70, respectively. This method, based on GNSS multi-feature fusion, can provide a reference for selecting multi-source positioning devices and planning the routes of unmanned agricultural machines.
Keywords: farm road, feature fusion, GNSS, scene detection, unmanned driving
DOI: 10.25165/j.ijabe.20261902.9654
Citation: Lin B H, Wu C C, Song W, Jaafar H A. Detection of the farm road positioning scene classification for unmanned driving based on GNSS. Int J Agric & Biol Eng, 2026; 19(2): 226–234.
References
[1] Zhou W J, Liu L Z, Liu R Q, Chen F, Yang L Y, Qin L F, et al. Precise mapping of linear shelterbelt forests in agricultural landscapes: A deep learning benchmarking study. Forests, 2026; 17（1）: 91.
[2] Luo X W, Hu L, He J, Zhang Z G, Zhou Z Y, Zhang W Y, et al. Key technologies and practice of unmanned farm in China. Transactions of the CSAE, 2024; 40: 1–16. （in Chinese）
[3] Luo X W, Liao J, Hu L, Zhou Z Y, Zhang Z G, Zang Y, et al. Research progress of intelligent agricultural machinery and practice of unmanned farm in China. Journal of South China Agricultural University, 2021; 42: 8–17. （in Chinese）
[4] Yao Z X, Zhao C J, Zhang T H. Agricultural machinery automatic navigation technology. iScience, 2024; 27（2）: 108714.
[5] Hu L, Wang Z M, Wang P, He J, Jiao J K, Wang C Y, et al. Agricultural robot positioning system based on laser sensing. Transactions of the CSAE, 2023; 39: 1–7. （in Chinese）
[6] Kowalczyk W Z, Hadas T. A comparative analysis of the performance of various GNSS positioning concepts dedicated to precision agriculture. Reports on Geodesy and Geoinformatics, 2024; 117（1）: 11–20.
[7] Kou R X, Yang B S, Dong Z, Liang F X, Yang S W. Mapping the spatio-temporal visibility of global navigation satellites in the urban road areas based on panoramic imagery. International Journal of Digital Earth, 2021; 14: 807–820.
[8] Xu H S, Hsu L T, Lu D B, Cai B G. Sky visibility estimation based on GNSS satellite visibility: An approach of GNSS-based context awareness. GPS Solutions, 2020; 24（2）: 59.
[9] Kim D, Youn J, Kim T, Kim G. 3D grid-based global positioning system satellite signal shadowing range modeling in urban area. Sensors and Materials, 2019; 31（11）: 3835–3848.
[10] Kou R X, Tan R C, Wang S Y, Yang B S, Dong Z, Yang S W, et al. Satellite visibility analysis considering signal attenuation by trees using airborne laser scanning point cloud. GPS Solutions, 2023; 27: 64.
[11] Zhang T, Cai B G, Lu D B, Wang J, Xiao Y. Train localization environmental scenario identification using features extracted from historical data. In: China Satellite Navigation Conference （CSNC 2021） Proceedings, Springer, 2021; pp.12–21. doi: 10.1007/978-981-16-3138-2_2.
[12] Chen W J, Zhu F, Guo F, Zhang X H. GNSS signal characteristics analysis in different water layers and navigation context clustering. Geomatics and Information Science of Wuhan University, 2024; 49: 139–145. （in Chinese）
[13] Liang Y J, Zhou K, Wu C C. Environment scenario identification based on GNSS recordings for agricultural tractors. Computers and Electronics in Agriculture, 2022; 195: 106829.
[14] Xia Y, Pan S G, Gao W, Yu B G, Gan X L, Zhao Y, et al. Recurrent neural network based scenario recognition with multi-constellation GNSS measurements on a smartphone. Measurement, 2020; 153: 107420.
[15] Groves P, Martin H F S, Voutsis K, Walter D. Context detection, categorization and connectivity for advanced adaptive integrated navigation. In: Proceedings of the 26th International Technical Meeting of the Satellite Division of The Institute of Navigation （ION GNSS+2013）, 2013; pp.1039-1056.
[16] Feriol F, Vivet D, Watanabe Y. A review of environmental context detection for navigation based on multiple sensors. Sensors, 2020; 20（16）: 4532.
[17] Wang T H, Chen B, Zhang Z Q, Li H, Zhang M. Applications of machine vision in agricultural robot navigation: A review. Computers and Electronics in Agriculture, 2022; 198: 107085.
[18] Attia D, Meurie C, Ruichek Y, Marais J. Counting of satellites with direct GNSS signals using Fisheye camera: A comparison of clustering algorithms. In: 2011 14th International IEEE Conference on Intelligent Transportation Systems - （ITSC 2011）, Washington: IEEE, 2011; pp.7–12. doi: 10.1109/ITSC.2011.6082955.
[19] Chawla N V, Bowyer K W, Hall L O, Kegelmeyer W P. SMOTE: Synthetic minority over-sampling technique. Journal of Artificial Intelligence Research, 2002; 16: 321–357.
[20] Breiman L. Random forests. Machine Learning, 2001; 45: 5–32.
[21] Feng Y H, Huang G W, Wang M F, Li X, Li Z H, Li H, et al. GNSS/MEMS INS tightly coupled algorithm for agricultural machinery navigation enhanced by random forest-based behavioral state awareness. Computers and Electronics in Agriculture, 2026; 242: 111350.
[22] Zhen W K, Scherer S. Estimating the localizability in tunnel-like environments using LiDAR and UWB. In: 2019 International Conference on Robotics and Automation （ICRA）, Montreal: IEEE, 2019; pp.4903–4908. doi: 10.1109/ICRA.2019.8794167.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 International Journal of Agricultural and Biological Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
IJABE is an international peer reviewed, open access journal, adopting Creative Commons Copyright Notices as follows.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
