Automated Oil Palm Health Assessment Using Object-Based Deep Learning and High-Resolution UAV Imagery in Indonesia

Atut Pindarwati; Arie Wahyu Wijayanto; I Putu Agus Karmawan; Ardhan Yeza; Asriadi Sakka

doi:10.59395/ijadis.v6i3.1391

Authors

Atut Pindarwati Department of Computer Science, Universitas Indonesia
Arie Wahyu Wijayanto Department of Statistical Computing, Politeknik Statistika STIS
I Putu Agus Karmawan Department of Geospatial Planning & Development, Bumitama Gunajaya Agro
Ardhan Yeza Department of Geospatial Planning & Development, Bumitama Gunajaya Agro
Asriadi Sakka Korea National University of Science and Technology (UST)

DOI:

https://doi.org/10.59395/ijadis.v6i3.1391

Keywords:

palm oil health status, remote sensing, precision agriculture, object based deep learning, aerial images

Abstract

Indonesia, as the world’s largest crude palm oil (CPO) producer, faces challenges in plantation monitoring due to reliance on manual data collection methods that are time-consuming, costly, and prone to human error. This study proposes an automated approach for assessing oil palm tree health using high-resolution UAV imagery (5–10 cm) and object-based deep learning models. We evaluate five state-of-the-art detectors—YOLOv5s, Faster R-CNN, Mask R-CNN, SSD, and RetinaNet—to classify individual trees into four health categories: Healthy, Moderately Healthy, Needs Improvement, and Urgent Condition. Using a dataset of 14,749 labeled trees from Kendawangan, Indonesia, YOLOv5s achieved the highest performance with a precision of 0.784, recall of 0.752, and mAP of 0.764. Our findings demonstrate the potential of AI-driven monitoring to enhance plantation management through rapid, accurate, and cost-effective health assessments—contributing a scalable solution to support precision agriculture and sustainable CPO production.

1316 698

Downloads

Download data is not yet available.

References

[1] BPS - Statistics Indonesia, "Statistik Kelapa Sawit Indonesia 2021," 2021. [Online]. Available: https://www.bps.go.id/publication/2020/11/30/36cba77a73179202def4ba14/statistik-kelapa-sawit-indonesia-2019.html.

[2] E. Agasta, "Prediksi Jumlah Produksi Kelapa Sawit Dengan Menggunakan Metode Extreme Learning Machine (ELM) (Studi kasus: PT. Sandabi Indah Lestari Kota Bengkulu)," J. Pengemb. Teknol. Inf. dan Ilmu Komput., vol. 2, no. 11, pp. 5751–5759, 2018.

[3] Y. C. Putra, A. W. Wijayanto, and G. A. Chulafak, "Oil palm trees detection and counting on Microsoft Bing Maps Very High Resolution (VHR) satellite imagery and Unmanned Aerial Vehicles (UAV) data using image processing thresholding approach," Ecol. Inform., 2022. DOI: https://doi.org/10.1016/j.ecoinf.2022.101878

[4] Y. C. Putra and A. W. Wijayanto, "Automatic detection and counting of oil palm trees using remote sensing and object-based deep learning," Remote Sens. Appl. Soc. Environ., vol. 29, no. July 2022, p. 100914, 2023, doi: 10.1016/j.rsase.2022.100914. DOI: https://doi.org/10.1016/j.rsase.2022.100914

[5] A. Syahza, "Effort to Spur Economic Growth in Rural Areas," Int. Reseacrh J. Bus. Stud., vol. 4, no. 3, pp. 171–188, 2011. DOI: https://doi.org/10.21632/irjbs.4.3.171-188

[6] D. Djawardi, "Kelayakan Perkebunan Kelapa Sawit Di Papua," J. Sains dan Teknol. Indones., vol. 11, no. 3, pp. 199–204, 2009, doi: 10.29122/jsti.v11i3.833. DOI: https://doi.org/10.29122/jsti.v11i3.833

[7] Y. Nurmasari and A. W. Wijayanto, "Oil Palm Plantation Detection in Indonesia using Sentinel-2 and Landsat-8 Optical Satellite Imagery (Case Study: Rokan Hulu Regency, Riau Province)," Int. J. Remote Sens. Earth Sci., pp. 1–18, 2021, [Online]. Available: http://dx.doi.org/10.30536/j.ijreses.2021.v18.a3537. DOI: https://doi.org/10.30536/j.ijreses.2021.v18.a3537

[8] J. Zheng et al., "Growing status observation for oil palm trees using Unmanned Aerial Vehicle (UAV) images," ISPRS J. Photogramm. Remote Sens., vol. 173, no. August 2020, pp. 95–121, 2021, doi: 10.1016/j.isprsjprs.2021.01.008. DOI: https://doi.org/10.1016/j.isprsjprs.2021.01.008

[9] N. A. Mubin, E. Nadarajoo, H. Z. M. Shafri, and A. Hamedianfar, "Young and mature oil palm tree detection and counting using convolutional neural network deep learning method," Int. J. Remote Sens., vol. 40, no. 19, pp. 7500–7515, 2019, doi: 10.1080/01431161.2019.1569282. DOI: https://doi.org/10.1080/01431161.2019.1569282

[10] H. M. Rizeei, H. Z. M. Shafri, M. A. Mohamoud, B. Pradhan, and B. Kalantar, "Oil palm counting and age estimation from WorldView-3 imagery and LiDAR data using an integrated OBIA height model and regression analysis," J. Sensors, vol. 2018, 2018, doi: 10.1155/2018/2536327. DOI: https://doi.org/10.1155/2018/2536327

[11] S. R. Putri and A. W. Wijayanto, "Estimating Rice Production using Machine Learning Models on Multitemporal Landsat-8 Satellite Images (Case Study: Ngawi Regency, East Java, Indonesia)," IEEE Int. Conf. Cybern. Comput. Intell., vol. 18, no. 1, pp. 280–285, 2022, doi: 10.1109/CyberneticsCom55287.2022.9865364. DOI: https://doi.org/10.1109/CyberneticsCom55287.2022.9865364

[12] A. W. Wijayanto, N. Afira, and W. Nurkarim, "Machine Learning Approaches using Satellite Data for Oil Palm Area Detection in Pekanbaru City, Riau," Mach. Learn. Approaches using Satell. Data Oil Palm Area Detect. Pekanbaru City, Riau, pp. 84–89, 2022, doi: 10.1109/CyberneticsCom55287.2022.9865301. DOI: https://doi.org/10.1109/CyberneticsCom55287.2022.9865301

[13] Caesarendra, R. Kurniawan, A. M. W. Saputra, and A. W. Wijayanto, "Eco-environment vulnerability assessment using remote sensing approach in East Kalimantan, Indonesia," Remote Sens. Appl., vol. v. 27, pp. 100791--2022 v.27, 2022, doi: 10.1016/j.rsase.2022.100791. DOI: https://doi.org/10.1016/j.rsase.2022.100791

[14] K. Aprianto, A. W. Wijayanto, and S. Pramana, "Deep Learning Approach using Satellite Imagery Data for Poverty Analysis in Banten, Indonesia," in 2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom), 2022, pp. 126–131, doi: 10.1109/CyberneticsCom55287.2022.9865480. DOI: https://doi.org/10.1109/CyberneticsCom55287.2022.9865480

[15] S. R. Putri, A. W. Wijayanto, and A. D. Sakti, "Developing Relative Spatial Poverty Index Using Integrated Remote Sensing and Geospatial Big Data Approach: A Case Study of East Java, Indonesia," ISPRS Int. J. Geo-Information, vol. 11, no. 5, 2022, doi: 10.3390/ijgi11050275. DOI: https://doi.org/10.3390/ijgi11050275

[16] S. R. Putri, A. W. Wijayanto, and S. Pramana, "Multi-source satellite imagery and point of interest data for poverty mapping in East Java, Indonesia: Machine learning and deep learning approaches," Remote Sens. Appl. Soc. Environ., vol. 29, p. 100889, 2023, doi: https://doi.org/10.1016/j.rsase.2022.100889. DOI: https://doi.org/10.1016/j.rsase.2022.100889

[17] N. Afira and A. W. Wijayanto, "Mono-temporal and multi-temporal approaches for burnt area detection using Sentinel-2 satellite imagery (a case study of Rokan Hilir Regency, Indonesia)," Ecol. Inform., vol. 69, p. 101677, 2022, doi: https://doi.org/10.1016/j.ecoinf.2022.101677. DOI: https://doi.org/10.1016/j.ecoinf.2022.101677

[18] W. Nurkarim and A. W. Wijayanto, "Building footprint extraction and counting on very high-resolution satellite imagery using object detection deep learning framework," Earth Sci. Informatics, no. 0123456789, 2022, doi: 10.1007/s12145-022-00895-4. DOI: https://doi.org/10.1007/s12145-022-00895-4

[19] A. C. Fitrianto, A. Darmawan, K. Tokimatsu, and M. Sufwandika, "Estimating the age of oil palm trees using remote sensing technique," IOP Conf. Ser. Earth Environ. Sci., vol. 148, no. 1, 2018, doi: 10.1088/1755-1315/148/1/012020. DOI: https://doi.org/10.1088/1755-1315/148/1/012020

[20] A. Tridawati, S. Darmawan, and A. Armijon, "Estimation the oil palm age based on optical remote sensing image in Landak Regency, West Kalimantan Indonesia," IOP Conf. Ser. Earth Environ. Sci., vol. 169, no. 1, 2018, doi: 10.1088/1755-1315/169/1/012063. DOI: https://doi.org/10.1088/1755-1315/169/1/012063

[21] A. Chemura, I. van Duren, and L. M. van Leeuwen, "Determination of the age of oil palm from crown projection area detected from WorldView-2 multispectral remote sensing data: The case of Ejisu-Juaben district, Ghana," ISPRS J. Photogramm. Remote Sens., vol. 100, pp. 118–127, 2015, doi: 10.1016/j.isprsjprs.2014.07.013. DOI: https://doi.org/10.1016/j.isprsjprs.2014.07.013

[22] I. Carolita, J. Sitorus, J. Manalu, and D. Wiratmoko, "Growth Profile Analysis of Oil Palm By Using Spot 6 the Case of North Sumatra," Int. J. Remote Sens. Earth Sci., vol. 12, no. 1, p. 21, 2017, doi: 10.30536/j.ijreses.2015.v12.a2669. DOI: https://doi.org/10.30536/j.ijreses.2015.v12.a2669

[23] N. Kamiran and M. L. R. Sarker, "Exploring the potential of high resolution remote sensing data for mapping vegetation and the age groups of oil palm plantation," IOP Conf. Ser. Earth Environ. Sci., vol. 18, no. 1, 2014, doi: 10.1088/1755-1315/18/1/012181. DOI: https://doi.org/10.1088/1755-1315/18/1/012181

[24] C. S. Hamsa, K. D. Kanniah, F. M. Muharam, N. H. Idris, Z. Abdullah, and L. Mohamed, "Textural measures for estimating oil palm age," Int. J. Remote Sens., vol. 40, no. 19, pp. 7516–7537, 2019, doi: 10.1080/01431161.2018.1530813. DOI: https://doi.org/10.1080/01431161.2018.1530813

[25] K. P. Tan, K. D. Kanniah, and A. P. Cracknell, "Use of UK-DMC 2 and ALOS PALSAR for studying the age of oil palm trees in southern peninsular Malaysia," Int. J. Remote Sens., vol. 34, no. 20, pp. 7424–7446, 2013, doi: 10.1080/01431161.2013.822601. DOI: https://doi.org/10.1080/01431161.2013.822601

[26] I. H. Al Amin and F. H. Arby, "Implementation of YOLO-v5 for a Real Time Social Distancing Detection," J. Appl. Informatics Comput., vol. 6, no. 1, pp. 01–06, 2022, doi: 10.30871/jaic.v6i1.3484. DOI: https://doi.org/10.30871/jaic.v6i1.3484

[27] J. Bai, J. Dai, Z. Wang, and S. Yang, "A detection method of the rescue targets in the marine casualty based on improved YOLOv5s," Front. Neurorobot., vol. 16, no. November, pp. 1–14, 2022, doi: 10.3389/fnbot.2022.1053124. DOI: https://doi.org/10.3389/fnbot.2022.1053124

[28] A. Ma’ruf, "Materi Kelapa Sawit 3: Pemeliharaan Tanaman," no. June. 2018. [Online]. Available: https://www.researchgate.net/publication/325961511.

[29] A. Aslam, A. Irtaza, and N. Nida, “Object detection and localization in natural scenes through single-step and two-step models,” 2020 International Conference on Emerging Trends in Smart Technologies (ICETST), 2020. doi:10.1109/icetst49965.2020.9080728 DOI: https://doi.org/10.1109/ICETST49965.2020.9080728

[30] B. Jaison, A. J. G, J. J, and D. P. C, “You only look once(yol O) object detection with coco using machine learning,” 2022 International Interdisciplinary Humanitarian Conference for Sustainability (IIHC), 2022. doi:10.1109/iihc55949.2022.10059737 DOI: https://doi.org/10.1109/IIHC55949.2022.10059737

[31] B. Sun, Y. Wang, and S. Wu, “An efficient lightweight CNN model for real-time fire smoke detection,” Journal of Real-Time Image Processing, vol. 20, no. 4, 2023. doi:10.1007/s11554-023-01331-6 DOI: https://doi.org/10.1007/s11554-023-01331-6

[32] Ultralytics, “YOLOv5 Documentation,” 2021. [Online]. Available: https://github.com/ultralytics/yolov5. [Accessed: 10-Oct-2024].

[33] W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu, and A. C. Berg, “SSD: Single Shot MultiBox Detector,” in Proc. European Conference on Computer Vision (ECCV), Amsterdam, Netherlands, 2016, pp. 21–37, doi: 10.1007/978-3-319-46448-0_2. DOI: https://doi.org/10.1007/978-3-319-46448-0_2

[34] T.-Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár, “Focal Loss for Dense Object Detection,” in Proc. IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 2017, pp. 2980–2988, doi: 10.1109/ICCV.2017.324. DOI: https://doi.org/10.1109/ICCV.2017.324

[35] R. Girshick, “Fast R-CNN,” in Proc. IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, 2015, pp. 1440–1448, doi: 10.1109/ICCV.2015.169. DOI: https://doi.org/10.1109/ICCV.2015.169

[36] K. He, G. Gkioxari, P. Dollár, and R. Girshick, “Mask R-CNN,” in Proc. IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 2017, pp. 2961–2969, doi: 10.1109/ICCV.2017.322. DOI: https://doi.org/10.1109/ICCV.2017.322