Deep Convolutional Neural Network enabled unmanned agricultural machine visual navigation system: architecture design, model optimization and empirical evaluation

Authors

  • Xin Gao
  • Shaojia Yuan
  • Jiazheng Zhu
  • Yifei Zhao

DOI:

https://doi.org/10.62051/4nanch44

Keywords:

Convolutional Neural Network (CNN); Unmanned Agricultural Machinery; Visual Navigation; Deep Learning; Precision Agriculture; Image Processing; SLAM (Simultaneous Localization and Mapping); Path Planning.

Abstract

In response to the pressing need for intelligent navigation technology in modern agriculture, this paper introduces a visual navigation system for unmanned agricultural machinery based on deep convolutional neural networks (CNNs). The system integrates the strong representational power of deep learning with rich visual information to facilitate high-precision, adaptive autonomous navigation in complex agricultural environments. Key innovations encompass: (1) the development of a customized deep CNN model proficient in extracting critical features from agricultural images, such as obstacles, landmarks, and crop rows; (2) the integration of the CNN model with visual SLAM (Simultaneous Localization and Mapping) technology for real-time localization and three-dimensional mapping of agricultural landscapes; (3) the creation of a decision-making system that merges deep learning predictions with conventional path planning algorithms to ensure machinery navigates around obstacles while adhering to optimal trajectories. Experimental validation across diverse agricultural scenarios demonstrates that the proposed visual navigation system sustains high localization accuracy (RMSE < 0.2 meters) and robust obstacle avoidance performance (success rate exceeding 95%) even in GPS-denied or weak GPS environments. Furthermore, the system significantly improves the continuity and efficiency of machinery operations by reducing unnecessary repositioning and redundant tasks. Practically, it is readily integrable into existing agricultural machinery platforms, offering broad applicability and potential for widespread adoption.

Downloads

Download data is not yet available.

References

[1] H. Yalcin and S. Razavi, Plant classification using convolutional neural networks, Income 2016 Fifth International Conference on Agro-Geoinformatics, IEEE, 2016, pp. 1-5. See: on April 9, 2024. [online]. In: https://ieeexplore.ieee.org/abstract/document/7577698/

[2] D. Tedesco-Oliveira, R. P. da Silva, W. Maldonado Jr., and C. Zerbato, Convolutional neural networks in predicting cotton yield from images of commercial fields, Comput. Electron. Agric., Vol. 171, p. 105307, 2020.

[3] M. H. Asad and A. Bais, "Weed detection in canola fields using maximum likelihood classification and deep convolutional neural network", Inf. Process. Agric., volume 7, issue 4, pp. 535-545, December 2020, doi: 10.1016 / j.i npa. 2019.12.002.

[4] A. S. Paymode and V. B. Malode, "Transfer Learning for Multi-Crop Leaf Disease Image Classification using Convolutional Neural Network VGG", Artif. J Intell. Agric., volume 6, pp. 23-33, in January 2022, doi: 10.1016 / j.a type iia 2021.12.002.

[5] H. S. Abdullahi, R. Sheriff and F. Mahieddine, "Convolution neural network in precision agriculture for plant image recognition and classification", Revenue 2017 Seventh International Conference on Innovative Computing Technology (INTECH), Ieee New York, 2017, pp. 256-272. Seen at: April 9, 2024. [Online]. Available at: https://www.researchgate.net/profile/Halimatu-Abdullahi/publication/320971643_Convolution_neural_network_in_precision_ag riculture_for_plant_image_recognition_and_classification/links/5a1d4fee4585153731898423/Convolution-neural-network-in-pr ecision-agriculture-for-plant-image-recognition-and-classification.pdf

[6] Z. Zhang, H. Liu, Z. Meng and J. Chen, Deep learning-based automatic recognition network of agricultural machinery images, Comput. Electron. Agric., vol. 166, Pp. 104978, 2019.

[7] Y. Chen, G. Li, X. Zhang, J. Jia, K. Zhou and C. Wu, Identifying field and road modes of agricultural Machinery based on GNSS Recordings: A graph convolutional neural network approach, Comput. Electron. Agric., vol. 198, p. 107082, 2022.

[8] A. Subeesh et al., Deep convolutional neural network models for weed detection in polyhouse grown bell peppers, Artif. J Intell. Agric., volume 6, pp. 47-54, in January 2022, doi: 10.1016 / j.a type iia 2022.01.002.

[9] H. Li, W. Yao, Y. Dong, Q. Gao and Y. Deng, Deep Kernel-Based Optimal Control Prediction in Aerospace Missions, IEEE Trans. Aerosp. Electron., price and volume 58, issue 3, pp. 1621-1633, June 2022, doi: 10.1109 / TAES. 2021.3133225.

[10] J. Kolli, D. M. Vamsi and V. M. Manikandan, Plant disease detection using convolutional neural network, Revenue 2021 IEEE Bombay Section Signature Conference (IBSSC), IEEE, 2021, pp. 1-6. See: on April 9, 2024. [online]. In: https://ieeexplore.ieee.org/abstract/document/9673493/

Downloads

Published

12-08-2024

How to Cite

Gao, X. (2024) “Deep Convolutional Neural Network enabled unmanned agricultural machine visual navigation system: architecture design, model optimization and empirical evaluation”, Transactions on Computer Science and Intelligent Systems Research, 5, pp. 1705–1720. doi:10.62051/4nanch44.