Development of a Plant Weed Detection Model Using the Mask R-CNN Algorithm for Smart Farming

Budi Prayitno; Pritasari Palupiningsih; Atam Rifai Sujiwanto

doi:10.33365/teknoinfo.v20i1.873

Budi Prayitno Institut Teknologi PLN
Pritasari Palupiningsih Institut Teknologi PLN
Atam Rifai Sujiwanto Institut Teknologi PLN

DOI: https://doi.org/10.33365/teknoinfo.v20i1.873

Keywords: Deep learning, Mask R-CNN, Object detection, Smart farming, Weeds

Abstract

A more efficient and sustainable agricultural system is urgently needed during world population growth and global climate change. One of the main challenges is that ineffective weed management can significantly reduce crop yields. Conventional farming methods, such as large-scale herbicide application, also negatively impact the environment. Therefore, the development of smart farming technology based on artificial intelligence (AI) is a crucial innovative solution. This research is urgent in the context of developing AI-based systems that significantly contribute to agricultural technology. The urgency of this study is the creation of a plant weed detection model using deep learning to determine the readiness of planting land with high accuracy values. The importance of this research lies not only in the development of technology, but also in its contribution to the farmer economy and the progress of the agricultural sector in Indonesia. This research aims to build and develop a plant weed detection model using deep learning to determine the readiness of planting land, as well as evaluate the detection model built to produce high accuracy. The research method used follows a flow consisting of problem understanding, data understanding, data preprocessing, modelling, and evaluation. The deep learning method used is object detection by applying the Mask R-CNN algorithm with the ResNet-50 architecture as the backbone. The evaluation of model performance was carried out using Mean Average Precision (MAP). The results of this study demonstrated the development of a deep learning-based weed detection model using the Mask R-CNN algorithm, which achieved a MAP of 37.32 and was able to overcome the challenges of varying weed types, lighting conditions, and complex field conditions.

References

R. Mathur, “Artificial Intelligence in Sustainable Agriculture,” IJRASET, vol. 11, no. 6, pp. 4047–4052, Jun. 2023, doi: 10.22214/ijraset.2023.54360.

O. B. Akintuyi, “The Role of Artificial Intelligence in U.S. Agriculture: A Review: Assessing advancements, challenges, and the potential impact on food production and sustainability,” Open Access Res. J. Eng. Technol., vol. 6, no. 2, pp. 023–032, Apr. 2024, doi: 10.53022/oarjet.2024.6.2.0017.

P. R. Bhagat, F. Naz, and R. Magda, “Artificial intelligence solutions enabling sustainable agriculture: A bibliometric analysis,” PLoS ONE, vol. 17, no. 6, p. e0268989, Jun. 2022, doi: 10.1371/journal.pone.0268989.

N. Naman, J. T. G, J. K. Bhatia, N. Bhardwaj, and R. Rahul, “Utilizing artificial intelligence (AI) for sustainable agriculture: Precision farming as a catalyst for environmental conservation,” Int. J. Agric. Extension Social Dev., vol. 7, no. 3, pp. 405–409, Mar. 2024, doi: 10.33545/26180723.2024.v7.i3e.441.

S. Cakic, T. Popovic, S. Krco, D. Nedic, D. Babic, and I. Jovovic, “Developing Edge AI Computer Vision for Smart Poultry Farms Using Deep Learning and HPC,” Sensors, vol. 23, no. 6, p. 3002, Mar. 2023, doi: 10.3390/s23063002.

A. Kaur et al., “Artificial Intelligence Driven Smart Farming for Accurate Detection of Potato Diseases: A Systematic Review,” IEEE Access, vol. 12, pp. 193902–193922, 2024, doi: 10.1109/ACCESS.2024.3510456.

M. Nishio, S. Noguchi, and K. Fujimoto, “Automatic Pancreas Segmentation Using Coarse-Scaled 2D Model of Deep Learning: Usefulness of Data Augmentation and Deep U-Net,” Applied Sciences, vol. 10, no. 10, p. 3360, May 2020, doi: 10.3390/app10103360.

A. F. I. Osman, N. M. Tamam, and Y. A. M. Yousif, “A comparative study of deep learning‐based knowledge‐based planning methods for 3D dose distribution prediction of head and neck,” J Applied Clin Med Phys, vol. 24, no. 9, p. e14015, Sep. 2023, doi: 10.1002/acm2.14015.

B. Padmavathi, A. BhagyaLakshmi, G. Vishnupriya, and K. Datchanamoorthy, “IoT-based prediction and classification framework for smart farming using adaptive multi-scale deep networks,” Expert Systems with Applications, vol. 254, p. 124318, Nov. 2024, doi: 10.1016/j.eswa.2024.124318.

H. Ko et al., “A Deep Residual U-Net Algorithm for Automatic Detection and Quantification of Ascites on Abdominopelvic Computed Tomography Images Acquired in the Emergency Department: Model Development and Validation,” J Med Internet Res, vol. 24, no. 1, p. e34415, Jan. 2022, doi: 10.2196/34415.

C. L. Nazalia, P. Palupiningsih, B. Prayitno, and Y. S. Purwanto, “Implementation of Convolutional Neural Network Algorithm to Pest Detection in Caisim,” in 2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE), Jakarta, Indonesia: IEEE, Feb. 2023, pp. 609–614. doi: 10.1109/ICCoSITE57641.2023.10127792.

L. Zimmermann, E. Faustmann, C. Ramsl, D. Georg, and G. Heilemann, “Technical Note: Dose prediction for radiation therapy using feature‐based losses and One Cycle Learning,” Medical Physics, vol. 48, no. 9, pp. 5562–5566, Sep. 2021, doi: 10.1002/mp.14774.

G. Storey, Q. Meng, and B. Li, “Leaf Disease Segmentation and Detection in Apple Orchards for Precise Smart Spraying in Sustainable Agriculture,” Sustainability, vol. 14, no. 3, p. 1458, Jan. 2022, doi: 10.3390/su14031458.

Y. Shao et al., “Detection of Straw Coverage under Conservation Tillage Based on an Improved Mask Regional Convolutional Neural Network (Mask R-CNN),” Agronomy, vol. 14, no. 7, p. 1409, Jun. 2024, doi: 10.3390/agronomy14071409.

M. Macías-Macías, H. Sánchez-Santamaria, C. J. García Orellana, H. M. González-Velasco, R. Gallardo-Caballero, and A. García-Manso, “Mask R-CNN for quality control of table olives,” Multimed Tools Appl, vol. 82, no. 14, pp. 21657–21671, Jun. 2023, doi: 10.1007/s11042-023-14668-8.

J. S. Buatti et al., “Standardizing and improving dose predictions for head and neck cancers using complete sets of OAR contours,” Medical Physics, vol. 51, no. 2, pp. 898–909, Feb. 2024, doi: 10.1002/mp.16898.

J. Pan, “Image Segmentation Based On U-Net and Adjusted U-Nets,” HSET, vol. 85, pp. 316–327, Mar. 2024, doi: 10.54097/accm2w81.

U. Afzaal, B. Bhattarai, Y. R. Pandeya, and J. Lee, “An Instance Segmentation Model for Strawberry Diseases Based on Mask R-CNN,” Sensors, vol. 21, no. 19, p. 6565, Sep. 2021, doi: 10.3390/s21196565.

D. Nguyen et al., “3D radiotherapy dose prediction on head and neck cancer patients with a hierarchically densely connected U-net deep learning architecture,” Phys. Med. Biol., vol. 64, no. 6, p. 065020, Mar. 2019, doi: 10.1088/1361-6560/ab039b.

S. Cai, Y. Tian, H. Lui, H. Zeng, Y. Wu, and G. Chen, “Dense-UNet: a novel multiphoton in vivo cellular image segmentation model based on a convolutional neural network,” Quant Imaging Med Surg, vol. 10, no. 6, pp. 1275–1285, Jun. 2020, doi: 10.21037/qims-19-1090.

N. Zhu et al., “Deep learning for smart agriculture: Concepts, tools, applications, and opportunities,” International Journal of Agricultural and Biological Engineering, vol. 11, no. 4, pp. 21–28, 2018, doi: 10.25165/j.ijabe.20181104.4475.

A. Kamilaris and F. X. Prenafeta-Boldú, “Deep learning in agriculture: A survey,” Computers and Electronics in Agriculture, vol. 147, pp. 70–90, Apr. 2018, doi: 10.1016/j.compag.2018.02.016.

F. Martinez-Plumed et al., “CRISP-DM Twenty Years Later: From Data Mining Processes to Data Science Trajectories,” IEEE Trans. Knowl. Data Eng., vol. 33, no. 8, pp. 3048–3061, Aug. 2021, doi: 10.1109/TKDE.2019.2962680.