Е-Публикации
Технически университет - София

Abstract: This paper investigates how remote sensing techniques can be used to estimate pasture biomass and assess vegetation health in free-range cattle systems. It introduces a lightweight, reproducible image processing method that relies solely on RGB images captured by autonomous drones. The technique uses a block-based spatial classification with the Excess Green (ExG) index to differentiate between green grass, dry vegetation, and bare soil. Each high-resolution image (1600 × 1600 pixels) is divided into uniform blocks, and the average ExG value within each block is used for classification. The generated vegetation condition maps and statistical summaries support efficient forage management and promote data-driven decisions in livestock production. This approach does not require multispectral sensors or field calibration, making it practical and scalable for low-cost biomass monitoring in grazing environments.

References

1. V. Hristov and I. Chekurov, "A Concept for Smart Warehouses Management for Cow Faeces, " 2024 59th International Scientific Conference on Information, Communication and Energy Systems and Technologies (ICEST), Sozopol, Bulgaria, 2024, pp. 1-4, doi: 10.1109/ICEST62335.2024.10639627.
2. I. Nachev, I. Iliev, A. Ilieva and T. Valkovski, "Model of Scanning Antenna Array with UAV Navigation and OATR Monitoring Applications, " 2024 59th International Scientific Conference on Information, Communication and Energy Systems and Technologies (ICEST), Sozopol, Bulgaria, 2024, pp. 1-4, doi: 10.1109/ICEST62335.2024.10639655.
3. M. Vahidi, S. Shafian, S. Thomas, R. Maguire, "Pasture Biomass Estimation Using Ultra-High-Resolution RGB UAVs Images and Deep Learning, " Remote Sensing, vol. 15, no. 24:5714, 2023, https://doi.org/10.3390/rs15245714
4. G. Meyer, J. Neto, "Verification of color vegetation indices for automated crop imaging applications, " Computers and Electronics in Agriculture, vol. 63(2), 2008, pp. 282-293, https://doi.org/10.1016/j.compag.2008.03.009
5. D. Montero, C. Aybar, M. Mahecha, F. Martinuzzi, M. Sochting, S. Wieneke, "A standardized catalogue of spectral indices to advance the use of remote sensing in Earth system research, " Scientific Data, vol. 10, Article number: 197, 2023, https://doi.org/10.1038/s41597-023-02096-0
6. S. Mardanisamani, M. Eramian, "Segmentation of vegetation and microplots in aerial agriculture images: A survey." The Plant Phenome Journal, vol. 5, e20042, 2022, https://doi.org/10.1002/ppj2.20042.
7. C. Matyukira, P. Mhangara, "Utilising RGB drone imagery and vegetation indices for accurate above-ground biomass estimation: a case study of the cradle nature reserve, Gauteng Province, South Africa, " Geocarto International, vol. 39(1), 2024, https://doi.org/10.1080/10106049.2024.2390512
8. W. Santos, L. Martins, A. Bezerra, L. Souza, A. Jardim, M. Silva, C. Souza, T. Silva, "Use of Unmanned Aerial Vehicles for Monitoring Pastures and Forages in Agricultural Sciences: A Systematic Review, " Drones, vol. 8, 585, 2024, https://doi.org/10.3390/drones8100585.
9. B. Hiebl, A. Mayr, A. Kollert, M. Rutzinger, M. Bremer, N. Helm, K. Chytry, "Vegetation Cover Mapping from RGB Webcam Time Series for Land Surface Emissivity Retrieval in High Mountain Areas, " ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, pp.367-374, 2022, DOI: 10.5194/isprs-annals-V-2-2022-367-2022.
10. V. Hristov, D. Pepedzhiev, "Digital Image Analysis of Surface Quality in Manufactured Flat Optical Lenses, " 14th Mediterranean Conference on Embedded Computing (MECO), Budva, Montenegro, 2025, doi: 10.1109/MECO66322.2025.11049202.
11. B. Ganev, H. Hristov, L. Laskov, A. Popov and M. Marinov, "Multisensor System for Monitoring in Agriculture, " 2022 13th National Conference with International Participation (ELECTRONICA), Sofia, Bulgaria, pp. 1-4, 2022. doi: 10.1109/ELECTRONICA55578.2022.9874374.
12. DroneDeploy software. [Online]. [Accessed: 11-Oct-2025], Available: https://www.dronedeploy.com/

Issue