Multi-Class Semantic Segmentation of Oil Palm Areas Using a VGG-19 U-Net Improvement

Authors

  • Maura Widyaningsih STMIK Palangkaraya
  • Tri Kuntoro Priyambodo Universitas Gadjah Mada
  • Moh Edi Wibowo Universitas Gadjah Mada
  • Muhammad Kamal Universitas Gadjah Mada

DOI:

https://doi.org/10.29207/resti.v10i1.7062

Keywords:

multi-class, oil palm, residual block, semantic segmentation, U-Net, VGG-19

Abstract

UAV imagery-based semantic segmentation is crucial for mapping tropical agricultural areas such as oil palm plantations. The main challenges are overlapping vegetation objects, unclear boundaries, and spectral similarities between classes, which reduce the accuracy of conventional models. This study proposes a modified U-Net architecture with a VGG-19 backbone, achieved through hyperparameter tuning (M7) and the integration of residual blocks (M8), to enhance multi-class segmentation performance. Experiments were conducted on aerial imagery with two resolutions (512×512 and 256×256) using four-class and three-class scenarios. The results show that M7 and M8 consistently outperform the baseline model (M2) in terms of accuracy, precision, recall, and average Intersection over Union (IoU). In the 512x512 four-class scenario, M8 achieved the highest accuracy (87.40%), precision (88.32%), recall (86.32%), and MIoU (0.132). M7 reached similar accuracy (>86%) but trained significantly faster than the baseline. In the 256x256 scenario, M8 maintained strong performance with 86.44% accuracy and 0.302 MIoU. For the three-class experiment, M8 reached a top MIoU of 0.178. Accuracy, precision, and recall were all above 87%, showing improved recognition of minority classes such as waterways. Confusion matrix analysis confirmed that M8 provided more balanced class predictions. It also reduced false negatives for oil palm vegetation. M7 showed slight fluctuations, suggesting possible overfitting. These findings support M8 as a robust solution for UAV-based oil palm mapping and large-scale monitoring.

Downloads

Download data is not yet available.

References

R.A. Perdana, A.M. Arimurthy and Risnandar. “Remote Sensing Scene Classification using ConvNeXt-Tiny Model with Attention Mechanism and Label Smoothing,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) , vol. 5 number 2, pp. 389 – 400, 2024, doi: 10.29207/resti.v8i3.5731.

R. Li, L. Wang, C. Zhang, C. Duan, S. Zheng, “A2-fpn for semantic segmentation of fine-resolution remotely sensed images,” International Journal of Remote Sensing, 43, 1131–1155, 2022, doi : 10.1109/LGRS.2021.3052886.

M. Widyaningsih, T.K. Priyambodo, M.E. Wibowo, M. Kamal, “Optimization contrast enhancement and noise reduction for semantic segmentation of oil palm aerial imagery,” International Journal of Intelligent Engineering and Systems,16, 597–609, 2023, doi : 10.22266/ijies2023.0228.51.

Z. Su, W. Li, Z. Ma, R. Gao, “An improved u-net method for the semantic segmentation of remote sensing images,” Applied Intelligence, 52, 3276–3288, 2021, doi: 10.1007/s10489-021-02542-9.

B. Xu, W. Wang, G. Falzon, P.W.H. Kwan, L. Guo, Z. Sun, and C. Li, “Livestock classification and counting in quadcopter aerial images using Mask R-CNN,” International Journal of Remote Sensing, 41, 8121 – 8142, 2020, doi: 10.1080/01431161.2020.1734245.

M. Lan, Y. Zhang, L. Zhang, and B Du, “Global context based automatic road segmentation via dilated convolutional neural network,” Information Sciences, 535, 1–254, 2020, doi : 10.1016/j.ins.2020.05.062.

A. Tashk, J. Herp, T. Bjørsum-Meyer, A. Koulaouzidis, and E.S. Nadimi, “AID-U-Net: An Innovative Deep Convolutional Architecture for Semantic Segmentation of Biomedical Images”. Diagnostics, 12, 2022, doi: 10.3390/diagnostics12122952.

N. Islam, M.F. Hossain, and M. Hossain, “Semantic Segmentation in Satellite Imagery: An Attentive U - Net Approach,” 2024 2nd International Conference on Information and Communication Technology (ICICT), 259-263. 2024, doi : 10.1109/ICICT64387.2024.10839725.

M. Liang, and X. Wang, “A bidirectional semantic segmentation method for remote sensing image based on super-resolution and domain adaptation,” International Journal of Remote Sensing, 44, 666–689, 2023, doi : 10.1080/01431161.2023.2169593.

B. Cui, X. Chen, and Y. Lu, “Semantic segmentation of remote sensing images using transfer learning and deep convolutional neural network with dense connection,” IEEE Access, 8, 116744–116755, 2020, doi : 10.1109/ACCESS.2020.3003914.

H. Toba, H. Bunyamin, J.E. Widyaya, C. Wibisono, and L.S. Haryadi, “Masking preprocessing in transfer learning for damage building detection,” IAES International Journal of Artificial Intelligence (IJ-AI), 2022, doi: 10.11591/ijai.v12.i2.pp552-559.

S. Reza, O.B. Amin, and M.M. Hashem, “TransResUNet: Improving U-Net Architecture for Robust Lungs Segmentation in Chest X-rays”, IEEE Region 10 Symposium (TENSYMP), 1592-1595, 2020, doi : 10.1109/ TENSYMP50017. 2020.9230835.

M.I. Ahmed, M. Foysal, M.D. Chaity, and A.B. Hossain, “DeepRoadNet: A deep residual based segmentation network for road map detection from remote aerial image”, IET Image Process., 18, 265-279, 2020, doi : 10.1049/ipr2.12948.

N. Ali, A. Z. Ijaz, R. H. Ali, Z. Ul Abideen and A. Bais, "Scene Parsing Using Fully Convolutional Network for Semantic Segmentation," IEEE Canadian Conference on Electrical and Computer Engineering (CCECE), Regina, SK, Canada, 2023, pp. 180-185, 2023, doi : 10.1109/CCECE58730.2023.10288934.

S. Landgraf, M. Hillemann, K. Wursthorn, and M. Ulrich, “U-CE:Uncertainty-aware Cross-Entropy for Semantic Segmentation”. ArXiv, 2023, doi : 10.48550/arXiv.2307.09947.

S.I. Hussain and E. Toscano, “An Extensive Investigation into the Use of Machine Learning Tools and Deep Neural Networks for the Recognition of Skin Cancer: Challenges, Future Directions, and a Comprehensive Review,” Symmetry, 16, 366. 2024, doi : 10.3390/sym16030366.

F.K. Alarfaj, I. Malik, H.U. Khan, N. Almusallam, M. Ramzan, and M. Ahmed, “Credit Card Fraud Detection Using State-of-the-art Machine Learning and Deep Learning Algorithms,” IEEE Access, PP, 1-1, 2022, doi: 10.1109/ACCESS.2022.3166891.

E. Moliner, L.S. Romero, and V. Vilaplana, “Weakly supervised semantic segmentation for remote sensing hyperspectral imaging”, in: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), p. 2273–2277. 2020, doi :10.1109/ICASSP40776.2020.9053384.

X. Yang, R.B. Bist, S. Subedi, L. Chai, “A deep learning method for monitoring spatial distribution of cage-free hens,” Artificial Intelligence in Agriculture, 8, 20–29, 2023, doi : 10.1016/j.aiia.2023.03.003.

N. Shabrina, R.A. Lika, and S. Indarti, “Deep learning models for automatic identification of plant-parasitic nematode,” Artificial Intelligence in Agriculture, 7, 1–12, 2023, doi : 10.1016/j.aiia.2022.12.002.

S. Xu, S. Cheng, X. Min, N. Pan, dan H. Hu, “Left Ventricle Segmentation Based on a Dilated Dense Convolutional Networks,” IEEE Access, 8, 214087-214097, 2020, doi : 10.1109/ACCESS.2020.3040888.

S. Li, Y. Guo, Z. Pang, W. Song, A. Hao, B. Xia, and H. Qin, “Automatic Dental Plaque Segmentation Based on Local-to-Global Features Fused Self-Attention Network,” IEEE Journal of Biomedical and Health Informatics, 26, 2240-2251, 2022, doi: 10.1109/JBHI.2022.3141773.

C. Ma and Z. Wang, “Semi-Mamba-UNet: Pixel-Level Contrastive Cross-Supervised Visual Mamba-based UNet for Semi-Supervised Medical Image Segmentation”. ArXiv, 2024, doi: 10.48550/arXiv.2402.07245.

H.A. Tedja, and O.W. Purbo, “Performance and Efficiency Comparison of U-Net and Ghost U-Net in Road Crack Segmentation with Floating Point and Quantization Optimization,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), 2024, doi : 10.29207/resti.v8i6.6089.

Z. Zhehan, F. Wei, D. Lili, Q. Yanli, Z. Dongying, and D. Guoshen, “Semantic segmentation of remote sensing image based on encoder decoder convolutional neural network,” Acta Opt. Sin., vol. 40, no. 3, p. 0310001, 2020, doi: 10.3788/AOS202040.0310001.

D. Tribuana, Hazriani, and A.L. Arda, “Image Preprocessing Approaches Toward Better Learning Performance with CNN,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), 2024, doi : 10.29207/resti.v8i1.5417.

G. Ulutaş, and B. Ustubioglu, “Underwater image enhancement using contrast limited adaptive histogram equalization and layered difference representation,” Multimedia Tools and Applications, 80, 15067–15091, 2021, doi : 10.1007/s11042-020-10426-2.

U. Erkan, S. Enginoğlu, D.N.H. Thanh, and L.M. Hieu, “Adaptive frequency median filter for the salt and pepper denoising problem,” IET Image Process, 14, 1291–1302. 2020, doi : 10.1049/iet-ipr.2019.0398.

B. Xu, W. Wang, G. Falzon, P.W.H. Kwan, L. Guo, Z. Sun, and C. Li, “Livestock classification and counting in quadcopter aerial images using Mask R-CNN,” International Journal of Remote Sensing, 41, 8121 – 8142, 2020, doi: 10.1080/01431161.2020.1734245.

J. Yu, J. Wang, Z. Xu, D. Li, and W. Lin, “A similarity-based method for evaluating single-stroke regions,” Other Conferences, 2024, doi : 10.1117/12.3049017.

N.S.M. Asri, H. Sakidin, M. Othman, A.N. Matori, and A. Ahmad, “Analysis of the hydrocarbon seepage detection in oil palm vegetation stress using unmanned aerial vehicle (uav) multispectral data,” in: Proceedings of the 27th National Symposium on Mathematical Sciences (SKSM27), 2020, doi: 10.1063/5.0018054.

Y. Muralimohanbabu and K. Radhika, “Multi spectral image classification based on deep feature extraction using deep learning technique,” Int. J. Bioinform Res. Appl., 17, 250-261. 2021, doi : 10.1504/IJBRA.2021.117169.

Z. Xia, “Overfitting of CNN model in cifar-10: Problem and solutions,” Applied and Computational Engineering. 2024, doi: 10.54254/2755-2721/37/20230511.

S. Dereich, and A. Jentzen, “Convergence rates for the Adam optimizer”, ArXiv, 2024, doi: 10.48550/arXiv.2407.21078abs/ 2407.21078.

J. Kong, Y. Cheng, K. Li, and J. Xing, “Dsam: A distance shrinking with angular marginalizing loss for high performance vehicle re-identificatio,” ArXiv, 2020, doi: 10.48550/ arXiv.2011.06228.

Y. Chen, B. Zou, Z. Guo, Y. Huang, F. Qin, Q. Li, and C. Wang, “SCUNet++: Swin-UNet and CNN Bottleneck Hybrid Architecture with Multi-Fusion Dense Skip Connection for Pulmonary Embolism CT Image Segmentation”, IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 7744-7752, 2024, doi: 10.1109/ WACV57701.2024.00758.

C. Ranjan, “Understanding Deep Learning: Application in Rare Event Prediction,” J. Chem. Inf. Model., vol. 1, no. 1, pp. 1–426, 2021, https://www.researchgate.net/publication/348077077_ Understanding_Deep_Learning_Application_in_Rare_Event_Prediction.

J. Kong, Y. Cheng, K. Li, and J. Xing, “Dsam: A distance shrinking with angular marginalizing loss for high performance vehicle re-identificatio,” ArXiv, 2020, doi: 10.48550/ arXiv.2011.06228.

P. Fränti and R, Mariescu-Istodor, “Soft precision and recall,” Pattern Recognition Letters, 167, 115–121, 2023, doi : 10.1016/ j.patrec.2023.02.005.

M. Widyaningsih, T.K. Priyambodo, M.E. Wibowo, M. Kamal, “Modification U-Net VGG-19 to Improve Semantic Segmentation Using Aerial Imagery of Oil Palm,” Ssrn, 2023, doi : 10.2139/ssrn.4596338.

Downloads

Published

2026-02-23

Issue

Section

Computer Vision and Pattern Recognition

How to Cite

Widyaningsih, M., Priyambodo, T. K., Wibowo, M. E., & Kamal, M. (2026). Multi-Class Semantic Segmentation of Oil Palm Areas Using a VGG-19 U-Net Improvement . Jurnal RESTI (Rekayasa Sistem Dan Teknologi Informasi), 10(1), 113-126. https://doi.org/10.29207/resti.v10i1.7062