Published

2025-02-13

Classification of Remote Sensing Datasets with Different Deep Learning Architectures

Clasificación de grupos de datos de detección remota con diferentes arquitecturas de aprendizaje profundo

DOI:

https://doi.org/10.15446/esrj.v28n4.113518

Keywords:

Convolutional Neural Networks (CNN), AlexNet, Resnet-50, VGG16, Efficient-Net-B0, Remote Sensing (RS) Image Classification, AID, AIDER, Unmanned Aerial Vehicles (UAVs) (en)
Redes Neuronales Convolucionales (CNN), AlexNet, Resnet-50, VGG16, Efficient-Net-B0, clasificación de imágenes de detección remota, grupo de datos AID, grupo de datos AIDER, vehículos aéreos no tripulados (es)

Downloads

Authors

  • Maryam Mehmood Department of Computer and Software Engineering, National University of Sciences and Technology, Islamabad 44000, Pakistan
  • Farhan Hussain Department of Computer and Software Engineering, National University of Sciences and Technology, Islamabad 44000, Pakistan
  • Ahsan Shahzad Department of Computer and Software Engineering, National University of Sciences and Technology, Islamabad 44000, Pakistan
  • Nouman Ali Department of Software Engineering, Mirpur University of Science and Technology

Remote sensing image classification has great advantages in the areas of environmental monitoring, urban planning, disaster management and many others. Unmanned Aerial Vehicles (UAVs) have revolutionized remote sensing by providing high-resolution imagery. In this context, effective image classification is crucial for extracting meaningful information from UAV-captured images. This study presents a comparison of different deep learning-based approach for supervised image classification of UAV images. We have experimented on four different CNN models like VGG 16, Alex net, Resnet50 and a deep neural network Efficient-Net-B0 on different remote sensing datasets; AID and AIDER. Multiple combinations were tried to find out which model performs better on which type of datasets. We have used pre-trained initial layers of four CNN models (AlexNet, VGG 16, Resnet50 and Efficient-Net-Bo) then last three layers of each of the selected models are removed and new layers have been added with better tuned parameters. Two different schemes were analyzed. In Scheme-1 the original AlexNet, VGG 16, Resnet50 and Efficient-Net-B0 were experimented without changing and tuning their number of parameters, while in Scheme-2 transfer learning was applied on the pre-trained models and after removing last three layers new layers were added with better tuned hyper-parameters. The evaluation of above schemes was ensured through comprehensive metrics across diverse land cover classes, four different performance evaluation matrices namely; F1 score, precision, accuracy and recall. The main focus of this research is towards transfer learning and adding new layers into pre-trained models to get better classification accuracy.

La clasificación de imágenes de detección remota tiene grandes ventajas en las áreas de monitoreo ambiental, planeación urbana, manejo de desastres y muchos otros. Los vehículos aéreos no tripulados han revolucionizado la detección remota al proveer imágenes de alta resolución. En este contexto, la clasificación efectiva de imágenes es crucial para extraer información significativa de las imágenes capturadas por vehículos aéreos no tripulados. Este estudio presenta una comparación de diferentes técnicas de aprendizaje profundo para la clasificación supervisada de imágenes capturadas por vehículos aéreos no tripulados. Los autores experimentaron con diferentes grupos de datos AID y AIDER en cuatro modelos diferentes de Redes Neuronales Convolucionales (CNN), VGG 16, Alex net, Resnet50 y en la red neuronal profunda Efficient-Net-B0. Se intentaron múltiples combinaciones para encontrar el modelo con mayor desempeño en cada grupo de datos. Los autores usaron capas iniciales de preentrenamiento de los modelos CNN y luego se retiraron las tres últimas capas de cada uno de los modelos seleccionados para añadir luego capas con parámetros más acordes. Se analizaron dos esquemas diferentes. En el Esquema 1 se experimentaron los modelos CNN originales sin cambiar y sin adecuar el número de parámetros, mientras que en el Esquema 2 se aplicó la transferencia de aprendizaje en los modelos pre-entrenados y después de remover las tres últimas capas se añadieron nuevas capas con hiperparámetros más adecuados. La evaluación de estos esquemas fue asegurada a través de métricas completas para diversas clases de cobertura del suelo y con cuatro matrices de evaluación de desempeño llamadas puntuación F1, precisión, exactitud y exhaustividad. El foco principal de esta investigación se basa en la transferencia de aprendizaje y en la adición de nuevas capas en modelos pre-entrenados para tener una clasificación más precisa.

References

Adegun, A. A., Viriri, S., & Tapamo, J. R. (2023). Review of deep learning methods for remote sensing satellite images classification: experimental survey and comparative analysis. Journal of Big Data, 10(1), 93. https://doi.org/10.1186/s40537-023-00772-x

Alganci, U., Soydas, M., & Sertel, E. (2020). Comparative research on deep learning approaches for airplane detection from very high-resolution satellite images. Remote sensing, 12(3), 458. https://doi.org/10.3390/rs12030458

Ansith, S., & Bini, A. (2022). Land use classification of high resolution remote sensing images using an encoder based modified GAN architecture. Displays, 74, 102229. https://doi.org/10.1016/j.displa.2022.102229

Arif, E., Shahzad, S. K., Iqbal, M. W., Jaffar, M. A., Alshahrani, A. S., & Alghamdi, A. (2022). Automatic Detection of Weapons in Surveillance Cameras Using Efficient-Net. Computers, Materials & Continua, 72(3). DOI: 10.32604/cmc.2022.027571

Basodi, S., Ji, C., Zhang, H., & Pan, Y. (2020). Gradient amplification: An efficient way to train deep neural networks. Big Data Mining and Analytics, 3(3), 196-207.

Broni-Bediako, C., Murata, Y., Mormille, L. H., & Atsumi, M. (2021). Searching for CNN architectures for remote sensing scene classification. IEEE Transactions on Geoscience and Remote Sensing, 60, 1-13. https://doi.org/10.26599/BDMA.2020.9020004

Chaudhari, S., Sardar, V., Rahul, D., Chandan, M., Shivakale, M. S., & Harini, K. (2021). Performance analysis of CNN, Alexnet and VGGNET models for drought prediction using satellite images. Paper presented at the 2021 Asian Conference on Innovation in Technology (ASIANCON). https://doi.org/10.1109/ASIANCON51346.2021.9545068

Cheng, Q., Huang, H., Xu, Y., Zhou, Y., Li, H., & Wang, Z. (2022). NWPU-captions dataset and MLCA-net for remote sensing image captioning. IEEE Transactions on Geoscience and Remote Sensing, 60, 1-19. https://doi.org/10.1109/TGRS.2022.3201474

Cheng, X., He, X., Qiao, M., Li, P., Hu, S., Chang, P., & Tian, Z. (2022). Enhanced contextual representation with deep neural networks for land cover classification based on remote sensing images. International Journal of Applied Earth Observation and Geoinformation, 107, 102706. https://doi.org/10.1016/j.jag.2022.102706

Hao, W., Han, M., Yang, H., Hao, F., & Li, F. (2021). A novel Chinese herbal medicine classification approach based on EfficientNet. Systems Science & Control Engineering, 9(1), 304-313. https://doi.org/10.1080/21642583.2021.1901159

He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition.

He, X., Zhao, K., & Chu, X. (2021). AutoML: A survey of the state-of-the-art. Knowledge-based systems, 212, 106622. https://doi.org/10.1016/j.knosys.2020.106622

Hoang, V. T., & Jo, K. H. (2021). Practical analysis on architecture of EfficientNet. Paper presented at the 2021 14th International Conference on Human System Interaction (HSI). https://doi.org/10.1109/HSI52170.2021.9538782

Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition.

Jeddi, A. B., Shafieezadeh, A., & Nateghi, R. (2023). PDP-CNN: A Deep Learning Model for Post-Hurricane Reconnaissance of Electricity Infrastructure on Resource-Constrained Embedded Systems at the Edge. IEEE Transactions on Instrumentation and Measurement, 72, 1-9. https://doi.org/10.1109/TIM.2023.3236321

Khan, S. D., Alarabi, L., & Basalamah, S. (2023a). DSMSA-Net: Deep spatial and multi-scale attention network for road extraction in high spatial resolution satellite images. Arabian Journal for Science and Engineering, 48(2), 1907-1920. https://doi.org/10.1007/s13369-022-07082-z

Khan, S. D., Alarabi, L., & Basalamah, S. (2023b). Segmentation of farmlands in aerial images by deep learning framework with feature fusion and context aggregation modules. Multimedia Tools and Applications, 82(27), 42353-42372. https://doi.org/10.1007/s11042-023-14962-5

Khan, S. D., & Basalamah, S. (2023). Multi-branch deep learning framework for land scene classification in satellite imagery. Remote Sensing, 15(13), 3408. https://doi.org/10.3390/rs15133408

Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 25.

Kuang, D., & He, L. (2014). Classification on ADHD with deep learning. Paper presented at the 2014 International Conference on Cloud Computing and Big Data. https://doi.org/10.1109/CCBD.2014.42

Kurakin, A., Song, S., Chien, S., Geambasu, R., Terzis, A., & Thakurta, A. (2022). Toward training at imagenet scale with differential privacy. arXiv preprint arXiv:2201.12328. https://doi.org/10.48550/arXiv.2201.12328

Li, W., Chen, K., Chen, H., & Shi, Z. (2021). Geographical knowledge-driven representation learning for remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, 60, 1-16. https://doi.org/10.1109/TGRS.2021.3115569

Lilay, M. Y., & Taye, G. D. (2023). Semantic segmentation model for land cover classification from satellite images in Gambella National Park, Ethiopia. SN Applied Sciences, 5(3), 76. https://doi.org/10.1007/s42452-023-05280-4

Luo, C.-Y., Pearson, P., Xu, G., & Rich, S. M. (2022). A computer vision-based approach for tick identification using deep learning models. Insects, 13(2), 116. https://doi.org/10.3390/insects13020116

Mandal, B., Okeukwu, A., & Theis, Y. (2021). Masked face recognition using resnet-50. arXiv preprint arXiv:2104.08997. https://doi.org/10.48550/arXiv.2104.08997

Mehmood, M., Shahzad, A., Zafar, B., Shabbir, A., & Ali, N. (2022). Remote sensing image classification: A comprehensive review and applications. Mathematical Problems in Engineering, 1-24. https://doi.org/10.1155/2022/5880959

Müller, S. G., & Hutter, F. (2021). Trivialaugment: Tuning-free yet state-of-the-art data augmentation. Paper presented at the Proceedings of the IEEE/CVF international conference on computer vision.

Neris, R., Guerra, R., López, S., & Sarmiento, R. (2021). Performance evaluation of state-of-the-art CNN architectures for the on-board processing of remotely sensed images. Paper presented at the 2021 XXXVI Conference on Design of Circuits and Integrated Systems (DCIS). https://doi.org/10.1109/DCIS53048.2021.9666179

Pittaras, N., Giannakopoulos, G., Stamatopoulos, P., & Karkaletsis, V. (2023). Content-based and knowledge-enriched representations for classification across modalities: a survey. ACM Computing Surveys, 55(14s), 1-40. https://doi.org/10.1145/3583682

Pronina, O., & Piatykop, O. (2023). The recognition of speech defects using convolutional neural network. Paper presented at the CTE Workshop Proceedings. https://doi.org/10.55056/cte.554

Reddy, K. V. V. K. (2023). Comparing Linear Discriminant Analysis to AlexNet as a Novel Approach for Better Remote Sensing Image Segmentation and Classification with Improved Accuracy. Journal of Survey in Fisheries Sciences, 10(1S), 2894-2903. https://doi.org/10.17762/sfs.v10i1S.522 https://doi.org/10.3390/rs14030592

Reedha, R., Dericquebourg, E., Canals, R., & Hafiane, A. (2022). Transformer neural network for weed and crop classification of high resolution UAV images. Remote sensing, 14(3), 592.

Rodriguez-Conde, I., Campos, C., & Fernandez-Riverola, F. (2022). Optimized convolutional neural network architectures for efficient on-device vision-based object detection. Neural Computing and Applications, 34(13), 10469-10501. https://doi.org/10.1007/s00521-021-06830-w

Saini, D., Khosla, A., Chand, T., Chouhan, D. K., & Prakash, M. (2023). Automated knee osteoarthritis severity classification using three‐stage preprocessing method and VGG16 architecture. International Journal of Imaging Systems and Technology, 33(3), 1028-1047. https://doi.org/10.1002/ima.22845

Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L. C. (2018). Mobilenetv2: Inverted residuals and linear bottlenecks. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition.

Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556. https://doi.org/10.48550/arXiv.1409.1556

Sinaga, K. B., Yudistira, N., & Santoso, E. (2023). Efficient CNN for high-resolution remote sensing imagery understanding. Multimedia Tools and Applications, 1-23.

Song, J., Gao, S., Zhu, Y., & Ma, C. (2019). A survey of remote sensing image classification based on CNNs. Big earth data, 3(3), 232-254. https://doi.org/10.1080/20964471.2019.1657720

Song, S., Yu, H., Miao, Z., Zhang, Q., Lin, Y., & Wang, S. (2019). Domain adaptation for convolutional neural networks-based remote sensing scene classification. IEEE Geoscience and Remote Sensing Letters, 16(8), 1324-1328. https://doi.org/10.1109/LGRS.2019.2896411

Subramanian, M., Shanmugavadivel, K., & Nandhini, P. (2022). On fine-tuning deep learning models using transfer learning and hyper-parameters optimization for disease identification in maize leaves. Neural Computing and Applications, 34(16), 13951-13968. https://doi.org/10.1007/s00521-022-07246-w

Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., . . . Rabinovich, A. (2015). Going deeper with convolutions. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition.

Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the inception architecture for computer vision. Paper presented at the Proceedings of the IEEE conference on computer vision and pattern recognition.

Tan, M., & Le, Q. (2019). Efficientnet: Rethinking model scaling for convolutional neural networks. Paper presented at the International conference on machine learning.

Tellez, D., Litjens, G., Bándi, P., Bulten, W., Bokhorst, J.-M., Ciompi, F., & Van Der Laak, J. (2019). Quantifying the effects of data augmentation and stain color normalization in convolutional neural networks for computational pathology. Medical image analysis, 58, 101544.

Thribhuvan, N., & Elayidom, S. (2022). Transfer Learning for Feature Dimensionality Reduction. The International Arab Journal of Information Technology, 19(5), 721-727. https://doi.org/10.34028/iajit/19/5/3

Velayudhan, D., Hassan, T., Ahmed, A. H., Damiani, E., & Werghi, N. (2022). Baggage threat recognition using deep low-rank broad learning detector. Paper presented at the 2022 IEEE 21st Mediterranean Electrotechnical Conference (MELECON). DOI: 10.1109/MELECON53508.2022.9842976

Wu, F., Maleki, R., Oubara, A., Gómez, D., Eftekhari, A., & Yang, G. (2022). Machine Learning Approaches for Crop Identification from Remote Sensing Imagery: A Review. Paper presented at the International Conference on Soft Computing and Pattern Recognition. https://doi.org/10.1007/978-3-031-27524-1_31

Yeşilmen, S., & Tatar, B. (2022). Efficiency of convolutional neural networks (CNN) based image classification for monitoring construction related activities: A case study on aggregate mining for concrete production. Case Studies in Construction Materials, 17, e01372. https://doi.org/10.1016/j.cscm.2022.e01372

Zhang, S., Yang, P., Xia, J., Wang, W., Cai, W., Chen, N., . . . Zhan, C. (2023). Remote sensing inversion and prediction of land use land cover in the middle reaches of the Yangtze River basin, China. Environmental Science and Pollution Research, 30(16), 46306-46320. https://doi.org/10.1007/s11356-023-25424-8

Zhang, X., Han, L., Han, L., & Zhu, L. (2020). How well do deep learning-based methods for land cover classification and object detection perform on high resolution remote sensing imagery? Remote Sensing, 12(3), 417. https://doi.org/10.3390/rs12030417

How to Cite

APA

Mehmood, M., Hussain, F., Shahzad, A. and Ali, N. (2025). Classification of Remote Sensing Datasets with Different Deep Learning Architectures. Earth Sciences Research Journal, 28(4), 409–419. https://doi.org/10.15446/esrj.v28n4.113518

ACM

[1]
Mehmood, M., Hussain, F., Shahzad, A. and Ali, N. 2025. Classification of Remote Sensing Datasets with Different Deep Learning Architectures. Earth Sciences Research Journal. 28, 4 (Feb. 2025), 409–419. DOI:https://doi.org/10.15446/esrj.v28n4.113518.

ACS

(1)
Mehmood, M.; Hussain, F.; Shahzad, A.; Ali, N. Classification of Remote Sensing Datasets with Different Deep Learning Architectures. Earth sci. res. j. 2025, 28, 409-419.

ABNT

MEHMOOD, M.; HUSSAIN, F.; SHAHZAD, A.; ALI, N. Classification of Remote Sensing Datasets with Different Deep Learning Architectures. Earth Sciences Research Journal, [S. l.], v. 28, n. 4, p. 409–419, 2025. DOI: 10.15446/esrj.v28n4.113518. Disponível em: https://revistas.unal.edu.co/index.php/esrj/article/view/113518. Acesso em: 19 apr. 2025.

Chicago

Mehmood, Maryam, Farhan Hussain, Ahsan Shahzad, and Nouman Ali. 2025. “Classification of Remote Sensing Datasets with Different Deep Learning Architectures”. Earth Sciences Research Journal 28 (4):409-19. https://doi.org/10.15446/esrj.v28n4.113518.

Harvard

Mehmood, M., Hussain, F., Shahzad, A. and Ali, N. (2025) “Classification of Remote Sensing Datasets with Different Deep Learning Architectures”, Earth Sciences Research Journal, 28(4), pp. 409–419. doi: 10.15446/esrj.v28n4.113518.

IEEE

[1]
M. Mehmood, F. Hussain, A. Shahzad, and N. Ali, “Classification of Remote Sensing Datasets with Different Deep Learning Architectures”, Earth sci. res. j., vol. 28, no. 4, pp. 409–419, Feb. 2025.

MLA

Mehmood, M., F. Hussain, A. Shahzad, and N. Ali. “Classification of Remote Sensing Datasets with Different Deep Learning Architectures”. Earth Sciences Research Journal, vol. 28, no. 4, Feb. 2025, pp. 409-1, doi:10.15446/esrj.v28n4.113518.

Turabian

Mehmood, Maryam, Farhan Hussain, Ahsan Shahzad, and Nouman Ali. “Classification of Remote Sensing Datasets with Different Deep Learning Architectures”. Earth Sciences Research Journal 28, no. 4 (February 13, 2025): 409–419. Accessed April 19, 2025. https://revistas.unal.edu.co/index.php/esrj/article/view/113518.

Vancouver

1.
Mehmood M, Hussain F, Shahzad A, Ali N. Classification of Remote Sensing Datasets with Different Deep Learning Architectures. Earth sci. res. j. [Internet]. 2025 Feb. 13 [cited 2025 Apr. 19];28(4):409-1. Available from: https://revistas.unal.edu.co/index.php/esrj/article/view/113518

Download Citation

CrossRef Cited-by

CrossRef citations0

Dimensions

PlumX

Article abstract page views

49

Downloads

Download data is not yet available.