Feature deformation network with multi-range feature enhancement for agricultural machinery operation mode identification

Weixin Zhai, Zhi Xu, Jinming Liu, Xiya Xiong, Jiawen Pan, Sunok chung, Dionysis Bochtis, Caicong Wu

Abstract


Utilizing the spatiotemporal features contained in extensive trajectory data for identifying operation modes of agricultural machinery is an important basis task for subsequent agricultural machinery trajectory research. In the present study, to effectively identify agricultural machinery operation mode, a feature deformation network with multi-range feature enhancement was proposed. First, a multi-range feature enhancement module was developed to fully explore the feature distribution of agricultural machinery trajectory data. Second, to further enrich the representation of trajectories, a feature deformation module was proposed that can map trajectory points to high-dimensional space to form feature maps. Then, EfficientNet-B0 was used to extract features of different scales and depths from the feature map, select features highly relevant to the results, and finally accurately predict the mode of each trajectory point. To validate the effectiveness of the proposed method, experiments were conducted to compare the results with those of other methods on a dataset of real agricultural trajectories. On the corn and wheat harvester trajectory datasets, the model achieved accuracies of 96.88% and 96.68%, as well as F1 scores of 93.54% and 94.19%, exhibiting improvements of 8.35% and 9.08% in accuracy and 20.99% and 20.04% in F1 score compared with the current state-of-the-art method.
Key words: road-field trajectory classification; efficientNet; feature deformation network; multi-range feature enhancement; agricultural machinery operation mode recognition
DOI: 10.25165/j.ijabe.20241704.8831

Citation: Zhai W X, Xu Z, Liu J M, Xiong X Y, Pan J W, Chung S, et al. Feature deformation network with multi-range feature enhancement for agricultural machinery operation mode identification. Int J Agric & Biol Eng, 2024; 17(4): 265–275.

Keywords


road-field trajectory classification; efficientNet; feature deformation network; multi-range feature enhancement; agricultural machinery operation mode recognition

Full Text:

PDF

References


Luan X D. Research on the application of artificial intelligence and computer technology in agricultural modernization. Computer Science, Agricultrual and Food Sciences, 2022; Corpus ID: 254579215.

Guo T T, Wang Y F. Big data application issues in the agricultural modernization of China. Ekoloji Dergisi, 2019; 107: 3677–3688.

Řezník T, Herman L, Klocová M, Leitner F, Pavelka T, Leitgeb Š, et al. Towards the development and verification of a 3D-based advanced optimized farm machinery trajectory algorithm. Sensors, 2021; 21(9): 2980.

Sun Q C, Xia J H C, Foster J, Falkmer T, Lee H. Pursuing precise vehicle movement trajectory in urban residential area using multi-GNSS RTK tracking. Transportation Research Procedia, 2017; 25: 2356–2372.

Quan Y M, Lau L. Development of a trajectory constrained rotating arm rig for testing GNSS kinematic positioning. Measurement, 2019; 140: 479–485.

Liu L, Chen T, Yang S G, Wang X. Analysis on the mode of trans-regional allocation of agricultural machinery. American Journal of Plant Sciences, 2020; 7: 1049–1056.

Li D, Liu X, Zhou K, Sun R Z, Wang C T, Zhai W X, et al. Discovering spatiotemporal characteristics of the trans-regional harvesting operation using big data of GNSS trajectories in China. Computers and Electronics in Agriculture, 2023; 211: 108003.

Rodias E, Berruto R, Busato P, Bochtis D, Sørensen C G, Zhou K. Energy savings from optimised in-field route planning for agricultural machinery. Sustainability, 2017; 9(11): 1956.

Liu Y, Shi L, Gao Y, Kou C Y, Yang S G, Liu L. Research on the optimized management of agricultural machinery allocation path based on teaching and learning optimization algorithm. Technical Gazette, 2022; 29(2): 456–463.

Li H C, Gao F, Zuo G C. Research on the agricultural machinery path tracking method based on deep reinforcement learning. Sci Program, 2022; 2022: 6385972.

Li S C, Xu H Z, Ji Y H, Cao R Y, Zhang M, Li H. Development of a following agricultural machinery automatic navigation system. Computers and Electronics in Agriculture, 2019; 158: 335–344.

Yang Y, Li Y K, Wen X, Zhang G, Ma Q L, Cheng S K, et al. An optimal goal point determination algorithm for automatic navigation of agricultural machinery: Improving the tracking accuracy of the Pure Pursuit algorithm. Computers and Electronics in Agriculture, 2022; 194: 106760.

Spooner P G. Minor rural road networks: values, challenges, and opportunities for biodiversity conservation. Nature Conservation, 2015; 11: 129–142.

Kearney S P, Coops N C, Sethi S, Stenhouse G B. Maintaining accurate, current, rural road network data: An extraction and updating routine using RapidEye, participatory GIS and deep learning. International Journal of Applied Earth Observation and Geoinformation, 2020; 87: 102031.

Bhat S A, Huang N-F. Big data and AI revolution in precision agriculture: Survey and challenges. IEEE Access, 2021; 9: 110209–110222.

Kamilaris A, Kartakoullis A, Prenafeta-Boldú F X. A review on the practice of big data analysis in agriculture. Computers and Electronics in Agriculture, 2017; 143: 23–37.

Liakos K G, Busato P, Moshou D, Pearson S, Bochtis D. Machine learning in agriculture: A review. Sensors, 2018; 18(8): 2674.

Lacour S, Burgun C, Perilhon C, Descombes G, Doyen V. A model to assess tractor operational efficiency from bench test data. Journal of Terramechanics, 2014; 54: 1–18.

Lee J W, Kim J S, Kim K U. Computer simulations to maximise fuel efficiency and work performance of agricultural tractors in rotovating and ploughing operations. Biosystems Engineering, 2016; 142: 1–11.

Chen B W, Dennis E J, Featherstone A. Weather impacts the agricultural production efficiency of wheat: The emerging role of precipitation shocks. Journal of Agricultural and Resource Economics, 2022; 47: 544–562.

Chen Y, Zhang X Q, Wu C C, Li G Y. Field-road trajectory segmentation for agricultural machinery based on direction distribution. Computers and Electronics in Agriculture, 2021; 186: 106180.

Poteko J, Eder D, Noack P O. Identifying operation modes of agricultural vehicles based on GNSS measurements. Computers and Electronics in Agriculture, 2021; 185: 106105.

Xiao Y Z, Mo G Z, Xiong X Y, Pan J W, Hu B B, Wu C C, et al. DR-XGBoost: An XGBoost model for field-road segmentation based on dual feature extraction and recursive feature elimination. Int J Agric & Biol Eng, 2023; 16(3): 169–179.

Chen Y, Li G Y, Zhang X Q, Jia J P, Zhou K, Wu C C. Identifying field and road modes of agricultural Machinery based on GNSS Recordings: A graph convolutional neural network approach. Computers and Electronics in Agriculture, 2022; 198: 107082.

Zhang X Q, Chen Y, Jia J P, Kuang K M, Lan Y B, Wu C C. Multi-view density-based field-road classification for agricultural machinery: DBSCAN and object detection. Computers and Electronics in Agriculture, 2022; 200: 107263.

Chen Y, Quan L, Zhang X Q, Zhou K, Wu C C. Field-road classification for GNSS recordings of agricultural machinery using pixel-level visual features. Computers and Electronics in Agriculture, 2023; 210: 107937.

Zhai W X, Mo G Z, Xiao Y Z, Xiong X Y, Wu C C, Zhang X Q, et al. GAN-BiLSTM network for field-road classification on imbalanced GNSS recordings. Computers and Electronics in Agriculture, 2023; 216: 108457.

Xu Y J, Liu X, Cao X, Huang C P, Liu E K, Qian S, et al. Artificial intelligence: A powerful paradigm for scientific research. The Innovation, 2021; 2(4): 100179.




Copyright (c) 2024 International Journal of Agricultural and Biological Engineering

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

2023-2026 Copyright IJABE Editing and Publishing Office