Feature Extraction for Multispectral Analysis of Cereal Crops Using Optimized Computer Vision Pipelines 44
DOI:
https://doi.org/10.18372/1990-5548.86.20561Keywords:
multispectral analysis, computer vision, unmanned aerial vehicle, precision farming, feature stabilizationAbstract
The article presents the results of a study aimed at improving the stability, reproducibility, and structural consistency of computer vision pipelines for multispectral UAV imagery of winter wheat canopies. A new adaptive preprocessing model is introduced, incorporating illumination normalization based on a modified Retinex/MSRCR algorithm, entropy-regulated spatial-spectral filtering for noise suppression, and instability-driven spectral feature fusion to obtain stable multispectral descriptors. The model is formulated as a multi-objective preprocessing framework, jointly optimizing illumination invariance, noise robustness, structural preservation, and information richness. Experiments conducted on the open-access UAV dataset of nine winter-wheat fields (Switzerland) demonstrated a reduction of the coefficient of variation to 0.12 and RMSE to 0.089, together with improvements in structural similarity (SSIM = 0.923) and spectral entropy (H = 5.9), significantly outperforming classical normalization methods. The results confirm the effectiveness of the proposed approach in mitigating illumination heterogeneity and sensor-induced distortions, ensuring stable and phenologically consistent feature extraction. The developed framework can be integrated into computer-integrated and robotic precision-farming systems to enhance the reliability of automated monitoring and decision-support processes in winter-wheat production.
References
IPPC Secretariat. Climate-change impacts on plant pests: a technical resource to support national and regional plant protection organizations. Rome: FAO on behalf of the Secretariat of the International Plant Protection Convention, 2024. 53 p. https://doi.org/10.4060/cd1615en.
C. Zhang, H. Kerner, S. Wang, P. Hao, Z. Li, K. A. Hunt, J. Abernethy, H. Zhao, F. Gao, L. Di, C. Guo, Z. Liu, Z. Yang, R. Mueller, C. Boryan, Q. Chen, P. C. Beeson, H. K. Zhang, and Y. Shen, “Remote sensing for crop mapping: A perspective on current and future crop-specific land cover data products,” Remote Sensing of Environment, vol. 330, p. 114995, 2025. https://doi.org/10.1016/j.rse.2025.114995
H. O. Velesaca, P. L. Suárez, R. Mira, and A. D. Sappa, “Computer vision based food grain classification: A comprehensive survey,” Computers and Electronics in Agriculture, vol. 187, p. 106287, 2021. https://doi.org/10.1016/j.compag.2021.106287
K. Halder, A. K. Srivastava, W. Zheng, K. Alsafadi, G. Zhao, M. Maerker, M. Singh, L. Guoging, A. Ghosh, M. Vianna, S. C. Pal, R. Shukla, M. Utthasini, P. Rosso, A. Bhattacharya, U. Chatterjee, D. Bisai, T. Gaiser, D. Behrend, L. Han, and F. Ewert, “A robust and scalable crop mapping framework using advanced machine learning and optical and SAR imageries,” Smart Agricultural Technology, vol. 12, p. 101354, 2025. https://doi.org/10.1016/j.atech.2025.101354
M. Ashraf, M. Abrar, N. Qadeer, A. A. Alshdadi, T. Sabbah, and M. A. Khan, “A convolutional neural network model for wheat crop disease prediction,” Computers, Materials & Continua, vol. 75, no. 2, pp. 3867–3882, 2023. https://doi.org/10.32604/cmc.2023.035498
W. Zhang, S. Zhu, D. Han, T. Yang, Y. Jiang, J. Wang, F. Wu, Z. Yao, C. Sun, and T. Liu, “Classification of pre-winter wheat seedling conditions based on UAV images and local optimized features (LOFs),” Journal of Integrative Agriculture, 2025. https://doi.org/10.1016/j.jia.2025.07.031
H. Zhou, Q. Li, B. Qin, H. Min, S. Liang, X. Wang, J. Cai, Q. Zhou, M. Huang, D. Jiang, Y. Zhong, and J. Chen, “High-throughput wheat seedling phenotyping via UAV-based semantic segmentation and ground sample distance driven pixel-to-area mapping,” Computers and Electronics in Agriculture, vol. 238, p. 110819, 2025. https://doi.org/10.1016/j.compag.2025.110819
L. Sandoval-Pillajo, I. García-Santillán, M. Pusdá-Chulde, and A. Giret, “Weed detection based on deep learning from UAV imagery: A review,” Smart Agricultural Technology, vol. 12, p. 101147, 2025. https://doi.org/10.1016/j.atech.2025.101147
Anderegg J. UAV dataset of nine wheat fields in Switzerland with raw, processed and meta data [Electronic resource] / Jonas Anderegg, Flavian Tschurr // ETH Zurich. – Mode of access: https://doi.org/10.3929/ethz-b-000662770.
Downloads
Published
Issue
Section
License
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).
